Transformer

Transformer

• 2021-10-15 Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation    Patrick Ruhkamp, Daoyi Gao, Hanzhi Chen, Nassir Navab, Benjamin Busam arXiv_CV arXiv_CV  Transformer  3D  Regularization  Self-Supervised  Pose  Attention  Prediction  PDF
• 2021-10-15 Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm    Shaoyi Huang, Dongkuan Xu, Ian E.H. Yen, Sung-en Chang, Bingbing Li, Shiyang Chen, Mimi Xie, Hang Liu, Caiwen Ding arXiv_CL arXiv_CL  Transformer  Sparse  Knowledge  Pose  Language_Model  PDF
• 2021-10-15 DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization    Ziming Mao, Chen Henry Wu, Ansong Ni, Yusen Zhang, Rui Zhang, Tao Yu, Budhaditya Deb, Chenguang Zhu, Ahmed H. Awadallah, Dragomir Radev arXiv_CL arXiv_CL  Transformer  Pose  Action  Summarization  PDF
• 2021-10-15 Kronecker Decomposition for GPT Compression    Ali Edalati, Marzieh Tahaei, Ahmad Rashid, Vahid Partovi Nia, James J. Clark, Mehdi Rezagholizadeh arXiv_CL arXiv_CL  Transformer  Zero-Shot  Knowledge  Pose  Few-Shot  Attention  Language_Model  PDF
• 2021-10-15 StreaMulT: Streaming Multimodal Transformer for Heterogeneous and Arbitrary Long Sequential Data    Victor Pellegrain (1 and 2), Myriam Tami (2), Michel Batteux (1), Céline Hudelot (2) ((1) Institut de Recherche Technologique SystemX, (2) Université Paris-Saclay, CentraleSupélec, MICS) arXiv_CL arXiv_CL  Transformer  Pose  Attention  Inference  PDF
• 2021-10-15 Crisis Domain Adaptation Using Sequence-to-sequence Transformers    Congcong Wang, Paul Nulty, David Lillis arXiv_CL arXiv_CL  Transformer  Knowledge  Pose  Classification  Language_Model  PDF
• 2021-10-15 Transformer-based Multi-task Learning for Disaster Tweet Categorisation    Congcong Wang, Paul Nulty, David Lillis arXiv_CL arXiv_CL  Transformer  Classification  PDF
• 2021-10-15 Combining CNNs With Transformer for Multimodal 3D MRI Brain Tumor Segmentation With Self-Supervised Pretraining    Mariia Dobko, Danylo-Ivan Kolinko, Ostap Viniavskyi, Yurii Yelisieiev arXiv_CV arXiv_CV  Transformer  Segmentation  Embedding  3D  Self-Supervised  Inference  PDF
• 2021-10-15 Receptive Field Broadening and Boosting for Salient Object Detection    Mingcan Ma, Changqun Xia, Chenxi Xie, Xiaowu Chen, Jia Li arXiv_CV arXiv_CV  Transformer  Salient  Pose  Detection  Object_Detection  Attention  Prediction  PDF
• 2021-10-15 Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation    Yao Qin, Chiyuan Zhang, Ting Chen, Balaji Lakshminarayanan, Alex Beutel, Xuezhi Wang arXiv_CV arXiv_CV  Transformer  PDF
• 2021-10-15 Cascaded Fast and Slow Models for Efficient Semantic Code Search    Akhilesh Deepak Gotmare, Junnan Li, Shafiq Joty, Steven C.H. Hoi arXiv_CL arXiv_CL  Transformer  Pose  Classification  PDF
• 2021-10-14 'Knights': First Place Submission for VIPriors21 Action Recognition Challenge at ICCV 2021    Ishan Dave, Naman Biyani, Brandon Clark, Rohit Gupta, Yogesh Rawat, Mubarak Shah arXiv_CV arXiv_CV  Transformer  Recognition  Self-Supervised  Pose  Action_Recognition  Action  Optical_Flow  PDF
• 2021-10-14 Attention-Free Keyword Spotting    Mashrur M. Morshed, Ahmad Omar Ahsan arXiv_SD arXiv_SD  Transformer  Speech  Deep_Learning  Attention  PDF
• 2021-10-14 The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization    Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber arXiv_AI arXiv_AI  Transformer  Pose  Attention  PDF
• 2021-10-14 Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision    Chenyang Huang, Hao Zhou, Osmar R. Zaïane, Lili Mou, Lei Li arXiv_CL arXiv_CL  Transformer  Pose  Inference  Prediction  PDF
• 2021-10-14 Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning    Benno Weck, Xavier Favory, Konstantinos Drossos, Xavier Serra arXiv_CL arXiv_CL  Transformer  Embedding  Bert  Attention  Caption  Language_Model  PDF
• 2021-10-14 Transferring Semantic Knowledge Into Language Encoders    Mohammad Umair, Francis Ferraro arXiv_CL arXiv_CL  Transformer  Embedding  Knowledge  Pose  Classification  Inference  Language_Model  PDF
• 2021-10-14 View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums    Conghao Wong, Beihao Xia, Ziming Hong, Qinmu Peng, Xinge You arXiv_CV arXiv_CV  Transformer  Pose  Action  Quantitative  Autonomous  Prediction  PDF
• 2021-10-14 Causal Transformers Perform Below Chance on Recursive Nested Constructions, Unlike Humans    Yair Lakretz, Théo Desbordes, Dieuwke Hupkes, Stanislas Dehaene arXiv_CL arXiv_CL  Transformer  RNN  Language_Model  PDF
• 2021-10-14 SpeechT5: Unified-Modal Encoder-Decoder Pre-training for Spoken Language Processing    Junyi Ao, Rui Wang, Long Zhou, Shujie Liu, Shuo Ren, Yu Wu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, Furu Wei arXiv_CL arXiv_CL  Transformer  Quantization  Recognition  Represenation_Learning  Speech  Self-Supervised  Pose  Speech_Recognition  PDF
• 2021-10-14 Relation-aware Heterogeneous Graph for User Profiling    Qilong Yan, Yufeng Zhang, Qiang Liu, Shu Wu, Liang Wang arXiv_AI arXiv_AI  Transformer  Pose  Action  Classification  Relation  Prediction  PDF
• 2021-10-14 Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence    Kelvin Lo, Yuan Jin, Weicong Tan, Ming Liu, Lan Du, Wray Buntine arXiv_CL arXiv_CL  Transformer  Segmentation  Embedding  Knowledge  Pose  PDF
• 2021-10-14 bert2BERT: Towards Reusable Pretrained Language Models    Cheng Chen, Yichun Yin, Lifeng Shang, Xin Jiang, Yujia Qin, Fengyu Wang, Zhi Wang, Xiao Chen, Zhiyuan Liu, Qun Liu arXiv_CL arXiv_CL  Transformer  Bert  Knowledge  Pose  Language_Model  PDF
• 2021-10-14 Auxiliary Loss of Transformer with Residual Connection for End-to-End Speaker Diarization    Yechan Yu, Dongkeon Park, Hong Kook Kim arXiv_SD arXiv_SD  Transformer  Speech  Pose  Attention  PDF
• 2021-10-14 Identifying Introductions in Podcast Episodes from Automatically Generated Transcripts    Elise Jing, Kristiana Schneck, Dennis Egan, Scott A. Waterman arXiv_CL arXiv_CL  Transformer  Segmentation  Embedding  Recognition  Bert  Speech  Pose  GAN  Speech_Recognition  PDF
• 2021-10-13 Study of positional encoding approaches for Audio Spectrogram Transformers    Leonardo Pepino, Pablo Riera, Luciana Ferrer arXiv_SD arXiv_SD  Transformer  Pose  Classification  Deep_Learning  PDF
• 2021-10-13 Language Modelling via Learning to Rank    Arvid Frydenlund, Gagandeep Singh, Frank Rudzicz arXiv_CL arXiv_CL  Transformer  Bert  Knowledge  Language_Model  Prediction  PDF
• 2021-10-13 Semantics-aware Attention Improves Neural Machine Translation    Aviv Slobodkin, Leshem Choshen, Omri Abend arXiv_CL arXiv_CL  Transformer  Knowledge  Pose  Attention  PDF
• 2021-10-13 Object-Region Video Transformers    Roei Herzig, Elad Ben-Avraham, Karttikeya Mangalam, Amir Bar, Gal Chechik, Anna Rohrbach, Trevor Darrell, Amir Globerson arXiv_CV arXiv_CV  Transformer  Recognition  Video_Caption  Action_Recognition  Action  Detection  Attention  PDF
• 2021-10-13 Audio-Visual Scene-Aware Dialog and Reasoning using Audio-Visual Transformers with Joint Student-Teacher Learning    Ankit P. Shah, Shijie Geng, Peng Gao, Anoop Cherian, Takaaki Hori, Tim K. Marks, Jonathan Le Roux, Chiori Hori arXiv_CL arXiv_CL  Transformer  Pose  Attention  Inference  PDF
• 2021-10-13 Automated Essay Scoring Using Transformer Models    Sabrina Ludwig, Christian Mayer, Christopher Hansen, Kerstin Eilers, Steffen Brandt arXiv_CL arXiv_CL  Transformer  Text_Classification  Pose  Classification  Attention  PDF
• 2021-10-13 Morphosyntactic Tagging with Pre-trained Language Models for Arabic and its Dialects    Go Inoue, Salam Khalifa, Nizar Habash arXiv_CL arXiv_CL  Transformer  Language_Model  PDF
• 2021-10-13 Leveraging redundancy in attention with Reuse Transformers    Srinadh Bhojanapalli, Ayan Chakrabarti, Andreas Veit, Michal Lukasik, Himanshu Jain, Frederick Liu, Yin-Wen Chang, Sanjiv Kumar arXiv_CV arXiv_CV  Transformer  Pose  Attention  PDF
• 2021-10-13 Transform and Bitstream Domain Image Classification    P.R. Hill, D.R. Bull arXiv_CV arXiv_CV  Transformer  Pose  Classification  Image_Classification  PDF
• 2021-10-13 CLIP4Caption: CLIP for Video Caption    Mingkang Tang, Zhanyu Wang, Zhenhua Liu, Fengyun Rao, Dian Li, Xiu Li arXiv_CV arXiv_CV  Transformer  Video_Caption  RNN  Pose  Text_Generation  Caption  Matching  PDF
• 2021-10-13 Transformers for EEG Emotion Recognition    Jiyao Liu, Li Zhang, Hao Wu, Huan Zhao arXiv_RO arXiv_RO  Transformer  Recognition  Pose  Emotion  Relation  Attention  PDF
• 2021-10-13 Benchmarking the Robustness of Spatial-Temporal Models Against Corruptions    Chenyu Yi, SIYUAN YANG, Haoliang Li, Yap-peng Tan, Alex Kot arXiv_CV arXiv_CV  Image_Caption  Transformer  Video_Caption  PDF
• 2021-10-13 The Dawn of Quantum Natural Language Processing    Riccardo Di Sipio, Jia-Hong Huang, Samuel Yen-Chi Chen, Stefano Mangini, Marcel Worring arXiv_CV arXiv_CV  Transformer  Speech  Pose  Sentiment  PDF
• 2021-10-13 Efficient domain adaptation of language models in ASR systems using Prompt-tuning    Saket Dingliwal, Ashish Shenoy, Sravan Bodapati, Ankur Gandhe, Ravi Teja Gadde, Katrin Kirchhoff arXiv_CL arXiv_CL  Transformer  Embedding  Recognition  Speech  Speech_Recognition  Language_Model  PDF
• 2021-10-13 Understanding of Emotion Perception from Art    Digbalay Bose, Krishna Somandepalli, Souvik Kundu, Rimita Lahiri, Jonathan Gratch, Shrikanth Narayanan arXiv_CV arXiv_CV  Transformer  Bert  Emotion  Classification  Caption  PDF
• 2021-10-13 Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement    Guochen Yu, Andong Li, Yutian Wang, Yinuo Guo, Hui Wang, Chengshi Zheng arXiv_SD arXiv_SD  Transformer  Enhancement  RNN  Speech  Pose  Attention  CNN  PDF
• 2021-10-13 MMIU: Dataset for Visual Intent Understanding in Multimodal Assistants    Alkesh Patel, Joel Ruben Antony Moniz, Roman Nguyen, Nick Tzou, Hadas Kotek, Vincent Renkens arXiv_CV arXiv_CV  Transformer  Knowledge  Classification  VQA  QA  PDF
• 2021-10-12 CyTran: Cycle-Consistent Transformers for Non-Contrast to Contrast CT Translation    Nicolae-Catalin Ristea, Andreea-Iuliana Miron, Olivian Savencu, Mariana-Iuliana Georgescu, Nicolae Verga, Fahad Shahbaz Khan, Radu Tudor Ionescu arXiv_CV arXiv_CV  Transformer  Style_Transfer  3D  Adversarial  Pose  Attention  Medical  CNN  PDF
• 2021-10-12 Dynamic Inference with Neural Interpreters    Nasim Rahaman, Muhammad Waleed Gondal, Shruti Joshi, Peter Gehler, Yoshua Bengio, Francesco Locatello, Bernhard Schölkopf arXiv_CV arXiv_CV  Transformer  Knowledge  Pose  Classification  Attention  Image_Classification  Inference  PDF
• 2021-10-12 Attention-guided Generative Models for Extractive Question Answering    Peng Xu, Davis Liang, Zhiheng Huang, Bing Xiang arXiv_CL arXiv_CL  Transformer  Pose  Attention  Inference  QA  PDF
• 2021-10-12 HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization    Ye Liu, Jian-Guo Zhang, Yao Wan, Congying Xia, Lifang He, Philip S. Yu arXiv_CL arXiv_CL  Transformer  Sparse  Pose  Relation  Attention  Summarization  PDF
• 2021-10-12 Fine-grained style control in Transformer-based Text-to-speech Synthesis    Li-Wei Chen, Alexander Rudnicky arXiv_CL arXiv_CL  Transformer  Embedding  Style_Transfer  Speech  Attention  PDF
• 2021-10-12 Sm{aa}prat: DialoGPT for Natural Language Generation of Swedish Dialogue by Transfer Learning    Tosin Adewumi, Nosheen Abid, Maryam Pahlavan, Rickard Brännvall, Sana Sabah Sabry, Foteini Liwicki, Marcus Liwicki arXiv_CL arXiv_CL  Transformer  Transfer_Learning  Face  Survey  Language_Model  QA  PDF
• 2021-10-12 Speech Summarization using Restricted Self-Attention    Roshan Sharma, Shruti Palaskar, Alan W Black, Florian Metze arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Pose  Attention  Summarization  Speech_Recognition  PDF
• 2021-10-12 StARformer: Transformer with State-Action-Reward Representations    Jinghuan Shang, Michael S. Ryoo arXiv_AI arXiv_AI  Transformer  Reinforcement_Learning  Pose  Action  Relation  Prediction  PDF
• 2021-10-12 Mention Memory: incorporating textual knowledge into Transformers through entity mention attention    Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald, Fei Sha, William Cohen arXiv_AI arXiv_AI  Transformer  Knowledge  Pose  Attention  QA  PDF
• 2021-10-12 DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer    Haozhe Ji, Minlie Huang arXiv_CL arXiv_CL  Transformer  Pose  Relation  Language_Model  PDF
• 2021-10-12 Trivial or impossible -- dichotomous data difficulty masks model differences    Kristof Meding, Luca M. Schulze Buschoff, Robert Geirhos, Felix A. Wichmann arXiv_AI arXiv_AI  Transformer  Self-Supervised  PDF
• 2021-10-12 Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes    Christoph Wick, Jochen Zöllner, Tobias Grüning arXiv_CV arXiv_CV  Transformer  Recognition  RNN  Pose  Classification  Attention  CNN  Language_Model  PDF
• 2021-10-12 LaoPLM: Pre-trained Language Models for Lao    Nankai Lin, Yingwen Fu, Ziyu Yang, Shengyi Jiang arXiv_CL arXiv_CL  Transformer  Bert  Text_Classification  Speech  Classification  Language_Model  PDF
• 2021-10-12 Relative Molecule Self-Attention Transformer    Łukasz Maziarka, Dawid Majchrowski, Tomasz Danel, Piotr Gaiński, Jacek Tabor, Igor Podolak, Paweł Morkisz, Stanisław Jastrzębski arXiv_AI arXiv_AI  Transformer  Self-Supervised  Relation  Attention  Prediction  PDF
• 2021-10-12 Satellite Image Semantic Segmentation    Eric Guérin, Killian Oechslin, Christian Wolf, Benoît Martinez arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  Sparse  Pose  Quantitative  PDF
• 2021-10-12 Learning Efficient Multi-Agent Cooperative Visual Exploration    Chao Yu, Xinyi Yang, Jiaxuan Gao, Huazhong Yang, Yu Wang, Yi Wu arXiv_CV arXiv_CV  Transformer  Enhancement  Reinforcement_Learning  SLAM  Action  Relation  Inference  PDF
• 2021-10-12 LightSeq: Accelerated Training for Transformer-based Models on GPUs    Xiaohui Wang, Ying Xiong, Xian Qian, Yang Wei, Lei Li, Mingxuan Wang arXiv_CL arXiv_CL  Transformer  Recognition  Bert  Optimization  Speech  Pose  Speech_Recognition  Inference  PDF
• 2021-10-12 Large Language Models Can Be Strong Differentially Private Learners    Xuechen Li, Florian Tramèr, Percy Liang, Tatsunori Hashimoto arXiv_CL arXiv_CL  Transformer  Gradient_Descent  Optimization  Pose  Deep_Learning  Language_Model  PDF
• 2021-10-11 SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition    Jing Pan, Tao Lei, Kwangyoun Kim, Kyu Han, Shinji Watanabe arXiv_CL arXiv_CL  Transformer  Recognition  RNN  Speech  Pose  Attention  Speech_Recognition  Language_Model  PDF
• 2021-10-11 Development and testing of an image transformer for explainable autonomous driving systems    Jiqian Dong, Sikai Chen, Shuya Zong, Tiantian Chen, Mohammad Miralinaghi, Samuel Labi arXiv_CV arXiv_CV  Transformer  Pose  Action  Deep_Learning  Attention  Autonomous  Prediction  PDF
• 2021-10-11 Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generation    Sashank Santhanam, Behnam Hedayatnia, Spandana Gella, Aishwarya Padmakumar, Seokhwan Kim, Yang Liu, Dilek Hakkani-Tur arXiv_AI arXiv_AI  Transformer  Knowledge  Detection  Object_Detection  PDF
• 2021-10-11 Certified Patch Robustness via Smoothed Vision Transformers    Hadi Salman, Saachi Jain, Eric Wong, Aleksander Mądry arXiv_AI arXiv_AI  Transformer  Inference  PDF
• 2021-10-11 Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning    Chongjian Ge, Youwei Liang, Yibing Song, Jianbo Jiao, Jue Wang, Ping Luo arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  Enhancement  Recognition  Represenation_Learning  Self-Supervised  Pose  Classification  Detection  Object_Detection  Attention  Image_Classification  PDF
• 2021-10-11 Investigating Transfer Learning Capabilities of Vision Transformers and CNNs by Fine-Tuning a Single Trainable Block    Durvesh Malpure, Onkar Litake, Rajesh Ingle arXiv_AI arXiv_AI  Transformer  Transfer_Learning  Classification  CNN  PDF
• 2021-10-11 CLIP4Caption ++: Multi-CLIP for Video Caption    Mingkang Tang, Zhanyu Wang, Zhaoyang Zeng, Fengyun Rao, Dian Li arXiv_CV arXiv_CV  Transformer  Enhancement  Video_Caption  Pose  Caption  PDF
• 2021-10-11 WeTS: A Benchmark for Translation Suggestion    Zhen Yang, Yingxue Zhang, Ernan Li, Fandong Meng, Jie Zhou arXiv_CL arXiv_CL  Transformer  Pose  PDF
• 2021-10-11 Offensive Language Detection with BERT-based models, By Customizing Attention Probabilities    Peyman Alavi, Pouria Nikvand, Mehrnoush Shamsfard arXiv_AI arXiv_AI  Transformer  Embedding  Bert  RNN  Detection  Attention  PDF
• 2021-10-11 The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation    Guillem Brasó, Nikita Kister, Laura Leal-Taixé arXiv_CV arXiv_CV  Transformer  Embedding  Pose_Estimation  Pose  Detection  Object_Detection  Attention  Inference  Prediction  PDF
• 2021-10-11 Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^circ$ Videos    Heeseung Yun, Youngjae Yu, Wonsuk Yang, Kangil Lee, Gunhee Kim arXiv_CV arXiv_CV  Transformer  Embedding  Pose  Relation  VQA  Visual_Relation  QA  PDF
• 2021-10-11 Adaptively Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation    Hui Shuai, Lele Wu, Qingshan Liu arXiv_CV arXiv_CV  Transformer  Embedding  3D  Pose_Estimation  Pose  Quantitative  Relation  Attention  Inference  PDF
• 2021-10-11 Efficient Training of Audio Transformers with Patchout    Khaled Koutini, Jan Schlüter, Hamid Eghbal-zadeh, Gerhard Widmer arXiv_SD arXiv_SD  Transformer  Pose  CNN  PDF
• 2021-10-11 Multi-View Self-Attention Based Transformer for Speaker Recognition    Rui Wang, Junyi Ao, Long Zhou, Shujie Liu, Zhihua Wei, Tom Ko, Qing Li, Yu Zhang arXiv_AI arXiv_AI  Transformer  Embedding  Recognition  Speech  Pose  Attention  PDF
• 2021-10-11 MELONS: generating melody with long-term structure using transformers and structure graph    Yi Zou, Pei Zou, Yi Zhao, Kaixiang Zhang, Ran Zhang, Xiaorui Wang arXiv_SD arXiv_SD  Transformer  Pose  Relation  PDF
• 2021-10-10 On Automatic Text Extractive Summarization Based on Graph and pre-trained Language Model Attention    Yuan-Ching Lin, Jinwen Ma arXiv_CL arXiv_CL  Transformer  Relation  Attention  Summarization  CNN  Language_Model  PDF
• 2021-10-10 NViT: Vision Transformer Compression and Parameter Redistribution    Huanrui Yang, Hongxu Yin, Pavlo Molchanov, Hai Li, Jan Kautz arXiv_CV arXiv_CV  Transformer  Regularization  Pose  Inference  PDF
• 2021-10-10 DCT: Dynamic Compressive Transformer for Modeling Unbounded Sequence    Kai-Po Chang, Wei-Yun Ma arXiv_CL arXiv_CL  Transformer  Pose  PDF
• 2021-10-10 6D-ViT: Category-Level 6D Object Pose Estimation via Transformer-based Instance Representation Learning    Lu Zou, Zhangjin Huang arXiv_CV arXiv_CV  Transformer  Point_Cloud  3D  Represenation_Learning  Pose_Estimation  Pose  PDF
• 2021-10-10 Transformer-based Dual Relation Graph for Multi-label Image Recognition    Jiawei Zhao, Ke Yan, Yifan Zhao, Jia Li, arXiv_CV arXiv_CV  Transformer  Embedding  Recognition  Pose  Relation  PDF
• 2021-10-10 SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions    Vinod Ganesan, Gowtham Ramesh, Pratyush Kumar arXiv_CL arXiv_CL  Transformer  NAS  Bert  Pose  Language_Model  PDF
• 2021-10-10 Multi-Channel End-to-End Neural Diarization with Distributed Microphones    Shota Horiguchi, Yuki Takashima, Paola Garcia, Shinji Watanabe, Yohei Kawaguchi arXiv_CL arXiv_CL  Transformer  Pose  Attention  PDF
• 2021-10-10 Poformer: A simple pooling transformer for speaker verification    Yufeng Ma, Yiwei Ding, Miao Zhao, Yu Zheng, Min Liu, Minqiang Xu arXiv_SD arXiv_SD  Transformer  Embedding  Pose  Attention  PDF
• 2021-10-09 Vector-quantized Image Modeling with Improved VQGAN    Jiahui Yu, Xin Li, Jing Yu Koh, Han Zhang, Ruoming Pang, James Qin, Alexander Ku, Yuanzhong Xu, Jason Baldridge, Yonghui Wu arXiv_CV arXiv_CV  Transformer  Reconstruction  Unsupervised  Transfer_Learning  Zero-Shot  Represenation_Learning  Pose  Few-Shot  GAN  Language_Model  Prediction  PDF
• 2021-10-09 Google Landmark Retrieval 2021 Competition Third Place Solution    Qishen Ha, Bo Liu, Hongwei Zhang arXiv_CV arXiv_CV  Transformer  Recognition  Face  PDF
• 2021-10-09 Improving Multi-Party Dialogue Discourse Parsing via Domain Integration    Zhengyuan Liu, Nancy F. Chen arXiv_CL arXiv_CL  Transformer  Pose  Relation  GAN  Language_Model  PDF
• 2021-10-09 Leveraging recent advances in Pre-Trained Language Models forEye-Tracking Prediction    Varun Madhavan, Aditya Girish Pawate, Shraman Pal, Abhranil Chandra arXiv_CL arXiv_CL  Transformer  Tracking  Bert  Language_Model  Prediction  PDF
• 2021-10-09 Vision Transformer based COVID-19 Detection using Chest X-rays    Koushik Sivarama Krishnan, Karthik Sivarama Krishnan arXiv_CV arXiv_CV  Transformer  Knowledge  Pose  Detection  Medical  PDF
• 2021-10-09 Using multiple reference audios and style embedding constraints for speech synthesis    Cheng Gong, Longbiao Wang, Zhenhua Ling, Ju Zhang, Jianwu Dang arXiv_AI arXiv_AI  Transformer  Embedding  Bert  Speech  Pose  Inference  PDF
• 2021-10-09 EfficientPhys: Enabling Simple, Fast and Accurate Camera-Based Vitals Measurement    Xin Liu, Brian L. Hill, Ziheng Jiang, Shwetak Patel, Daniel McDuff arXiv_AI arXiv_AI  Transformer  Segmentation  Face_Detection  Pose  Face  Detection  CNN  PDF
• 2021-10-08 Robustness Evaluation of Transformer-based Form Field Extractors via Form Attacks    Le Xue, Mingfei Gao, Zeyuan Chen, Caiming Xiong, Ran Xu arXiv_AI arXiv_AI  Transformer  OCR  Pose  Action  Recommendation  PDF
• 2021-10-08 Adversarial Token Attacks on Vision Transformers    Ameya Joshi, Gauri Jagatap, Chinmay Hegde arXiv_CV arXiv_CV  Transformer  Adversarial  Attention  CNN  PDF
• 2021-10-08 Local and Global Context-Based Pairwise Models for Sentence Ordering    Ruskin Raj Manku, Aditya Jyoti Paul arXiv_CL arXiv_CL  Transformer  Bert  Pose  Prediction  PDF
• 2021-10-08 Field Extraction from Forms with Unlabeled Data    Mingfei Gao, Zeyuan Chen, Nikhil Naik, Kazuma Hashimoto, Caiming Xiong, Ran Xu arXiv_AI arXiv_AI  Transformer  Pose  Action  PDF
• 2021-10-08 Exploring Heterogeneous Characteristics of Layers in ASR Models for More Efficient Training    Lillian Zhou, Dhruv Guliani, Andreas Kabel, Giovanni Motta, Françoise Beaufays arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Pose  Relation  Speech_Recognition  PDF
• 2021-10-08 Taming Sparsely Activated Transformer with Stochastic Experts    Simiao Zuo, Xiaodong Liu, Jian Jiao, Young Jin Kim, Hany Hassan, Ruofei Zhang, Tuo Zhao, Jianfeng Gao arXiv_CL arXiv_CL  Transformer  Sparse  Pose  Inference  Prediction  PDF
• 2021-10-08 VieSum: How Robust Are Transformer-based Models on Vietnamese Summarization?    Hieu Nguyen, Long Phan, James Anibal, Alec Peltekian, Hieu Tran arXiv_CL arXiv_CL  Transformer  Transfer_Learning  Self-Supervised  Summarization  Text_Generation  PDF
• 2021-10-08 Inferring Offensiveness In Images From Natural Language Supervision    Patrick Schramowski, Kristian Kersting arXiv_AI arXiv_AI  Transformer  Knowledge  PDF
• 2021-10-08 Iterative Decoding for Compositional Generalization in Transformers    Luana Ruiz, Joshua Ainslie, Santiago Ontañón arXiv_CL arXiv_CL  Transformer  Deep_Learning  Inference  PDF
• 2021-10-08 Text analysis and deep learning: A network approach    Ingo Marquart arXiv_CL arXiv_CL  Transformer  Unsupervised  Bert  Knowledge  Review  Pose  Deep_Learning  Relation  Language_Model  PDF
• 2021-10-08 The Layout Generation Algorithm of Graphic Design Based on Transformer-CVAE    Mengxi Guo, Dangqing Huang, Xiaodong Xie arXiv_CV arXiv_CV  Transformer  Pose  Face  PDF
• 2021-10-08 TRUNet: Transformer-Recurrent-U Network for Multi-channel Reverberant Sound Source Separation    Ali Aroudi, Stefan Uhlich, Marc Ferras Font arXiv_SD arXiv_SD  Transformer  Pose  Deep_Learning  Attention  CNN  PDF
• 2021-10-08 Context-LGM: Leveraging Object-Context Relation for Context-Aware Object Recognition    Mingzhou Liu, Xinwei Sun, Fandong Zhang, Yizhou Yu, Yizhou Wang arXiv_CV arXiv_CV  Transformer  Recognition  Pose  Emotion  Relation  Attention  Prediction  PDF
• 2021-10-08 UniNet: Unified Architecture Search with Convolution, Transformer, and MLP    Jihao Liu, Hongsheng Li, Guanglu Song, Xin Huang, Yu Liu arXiv_CV arXiv_CV  Transformer  NAS  Segmentation  Semantic_Segmentation  Pose  Classification  Detection  Object_Detection  PDF
• 2021-10-08 An End-to-End Trainable Video Panoptic Segmentation Method usingTransformers    Jeongwon Ryu, Kwangjin Yoon arXiv_CV arXiv_CV  Transformer  Segmentation  Tracking  Object_Tracking  Pose  PDF
• 2021-10-08 Multiplex Behavioral Relation Learning for Recommendation via Memory Augmented Transformer Network    Lianghao Xia, Chao Huang, Yong Xu, Peng Dai, Bo Zhang, Liefeng Bo arXiv_AI arXiv_AI  Transformer  Embedding  Pose  Action  Relation  Attention  Recommendation  PDF
• 2021-10-08 Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation    Lianghao Xia, Chao Huang, Yong Xu, Peng Dai, Xiyue Zhang, Hongsheng Yang, Jian Pei, Liefeng Bo arXiv_AI arXiv_AI  Transformer  Embedding  Knowledge  Pose  Action  Relation  Attention  Recommendation  PDF
• 2021-10-08 Maximize the Exploration of Congeneric Semantics for Weakly Supervised Semantic Segmentation    Ke Zhang, Sihong Chen, Qi Ju, Yong Jiang, Yucong Li, Xin He arXiv_AI arXiv_AI  Transformer  Segmentation  Embedding  Semantic_Segmentation  Weakly_Supervised  Pose  Attention  PDF
• 2021-10-08 ViDT: An Efficient and Effective Fully Transformer-based Object Detector    Hwanjun Song, Deqing Sun, Sanghyuk Chun, Varun Jampani, Dongyoon Han, Byeongho Heo, Wonjae Kim, Ming-Hsuan Yang arXiv_CV arXiv_CV  Transformer  Recognition  Classification  Detection  Object_Detection  Attention  Image_Classification  PDF
• 2021-10-08 M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining    Junyang Lin, An Yang, Jinze Bai, Chang Zhou, Le Jiang, Xianyan Jia, Ang Wang, Jie Zhang, Yong Li, Wei Lin, Jingren Zhou, Hongxia Yang arXiv_CL arXiv_CL  Transformer  Pose  Deep_Learning  PDF
• 2021-10-08 Contrastive Learning for Source Code with Structural and Functional Properties    Yangruibo Ding, Luca Buratti, Saurabh Pujar, Alessandro Morari, Baishakhi Ray, Saikat Chakraborty arXiv_AI arXiv_AI  Transformer  Knowledge  Self-Supervised  Contrastive_Learning  Language_Model  PDF
• 2021-10-08 Boundary-aware Transformers for Skin Lesion Segmentation    Jiacheng Wang, Lan Wei, Liansheng Wang, Qichao Zhou, Lei Zhu, Jing Qin arXiv_CV arXiv_CV  Transformer  Segmentation  Embedding  Knowledge  Pose  Quantitative  Attention  CNN  PDF
• 2021-10-08 Token Pooling in Visual Transformers    Dmitrii Marin, Jen-Hao Rick Chang, Anurag Ranjan, Anish Prabhu, Mohammad Rastegari, Oncel Tuzel arXiv_CV arXiv_CV  Transformer  Reconstruction  Optimization  Pose  Attention  PDF
• 2021-10-08 Speeding up Deep Model Training by Sharing Weights and Then Unsharing    Shuo Yang, Le Hou, Xiaodan Song, Qiang Liu, Denny Zhou arXiv_CL arXiv_CL  Transformer  Bert  Pose  PDF
• 2021-10-07 Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution    Yangyang Shi, Chunyang Wu, Dilin Wang, Alex Xiao, Jay Mahadeokar, Xiaohui Zhang, Chunxi Liu, Ke Li, Yuan Shangguan, Varun Nagaraja, Ozlem Kalinli, Mike Seltzer arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Pose  Attention  Speech_Recognition  PDF
• 2021-10-07 Efficient large-scale image retrieval with deep feature orthogonality and Hybrid-Swin-Transformers    Christof Henkel arXiv_CV arXiv_CV  Transformer  Recognition  Image_Retrieval  Face  PDF
• 2021-10-07 SVG-Net: An SVG-based Trajectory Prediction Model    Mohammadhossein Bahari, Vahid Zehtab, Sadegh Khorasani, Sana Ayramlou, Saeed Saadatnejad, Alexandre Alahi arXiv_CV arXiv_CV  Transformer  Pose  Relation  Attention  Autonomous  Prediction  PDF
• 2021-10-07 ATISS: Autoregressive Transformers for Indoor Scene Synthesis    Despoina Paschalidou, Amlan Kar, Maria Shugrina, Karsten Kreis, Andreas Geiger, Sanja Fidler arXiv_CV arXiv_CV  Transformer  3D  Pose  PDF
• 2021-10-07 TranSalNet: Visual saliency prediction using transformers    Jianxun Lou, Hanhe Lin, David Marshall, Dietmar Saupe, Hantao Liu arXiv_CV arXiv_CV  Transformer  Salient  Pose  Attention  CNN  Prediction  PDF
• 2021-10-07 A transformer-based deep learning approach for classifying brain metastases into primary organ sites using clinical whole brain MRI images    Qing Lyu, Sanjeev V. Namjoshi, Emory McTyre, Umit Topaloglu, Richard Barcus, Michael D. Chan, Christina K. Cramer, Waldemar Debinski, Metin N. Gurcan, Glenn J. Lesser, Hui-Kuan Lin, Reginald F. Munden, Boris C. Pasche, Kiran Kumar Solingapuram Sai, Roy E. Strowd, Stephen B. Tatter, Kounosuke Watabe, Wei Zhang, Ge Wang, Christopher T. Whitlow arXiv_CV arXiv_CV  Transformer  Segmentation  Knowledge  Pose  Classification  Deep_Learning  GAN  PDF
• 2021-10-07 mRAT-SQL+GAP:A Portuguese Text-to-SQL Transformer    Marcelo Archanjo José, Fabio Gagliardi Cozman arXiv_AI arXiv_AI  Transformer  Pose  Attention  Inference  Language_Model  PDF
• 2021-10-07 Pretrained Language Models are Symbolic Mathematics Solvers too!    Kimia Noorbakhsh, Modar Sulaiman, Mahdi Sharifi, Kallol Roy, Pooyan Jamshidi arXiv_CL arXiv_CL  Transformer  Deep_Learning  Language_Model  PDF
• 2021-10-07 Sparse MoEs meet Efficient Ensembles    James Urquhart Allingham, Florian Wenzel, Zelda E Mariet, Basil Mustafa, Joan Puigcerver, Neil Houlsby, Ghassen Jerfel, Vincent Fortuin, Balaji Lakshminarayanan, Jasper Snoek, Dustin Tran, Carlos Riquelme Ruiz, Rodolphe Jenatton arXiv_CV arXiv_CV  Transformer  Sparse  Few-Shot  Prediction  PDF
• 2021-10-07 Noisy Text Data: Achilles' Heel of popular transformer based NLP models    Kartikay Bagla, Ankit Kumar, Shivam Gupta, Anuj Gupta arXiv_AI arXiv_AI  Transformer  Text_Classification  Classification  Summarization  PDF
• 2021-10-07 Cross-Language Learning for Entity Matching    Ralph Peeters, Christian Bizer arXiv_CL arXiv_CL  Transformer  Matching  PDF
• 2021-10-07 Universal Approximation Under Constraints is Possible with Transformers    Anastasis Kratsios, Behnoosh Zamanlooy, Tianlin Liu, Ivan Dokmanić arXiv_AI arXiv_AI  Transformer  Action  Quantitative  PDF
• 2021-10-07 End-to-End Supermask Pruning: Learning to Prune Image Captioning Models    Jia Huei Tan, Chee Seng Chan, Joon Huang Chuah arXiv_CV arXiv_CV  Image_Caption  Transformer  Sparse  Pose  Relation  Attention  Caption  PDF
• 2021-10-07 Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling    Kyuhong Shim, Iksoo Choi, Wonyong Sung, Jungwook Choi arXiv_CL arXiv_CL  Transformer  Pose  Attention  Language_Model  PDF
• 2021-10-07 Attention is All You Need? Good Embeddings with Statistics are enough: Audio Understanding WITHOUT Convolutions/Transformers/BERTs/Mixers/Attention/RNNs or    Prateek Verma arXiv_AI arXiv_AI  Transformer  Embedding  Bert  Represenation_Learning  RNN  Classification  Deep_Learning  Attention  CNN  PDF
• 2021-10-07 A Comparative Study of Transformer-Based Language Models on Extractive Question Answering    Kate Pearce, Tiffany Zhan, Aneesh Komanduri, Justin Zhan arXiv_CL arXiv_CL  Transformer  Bert  RNN  Pose  Language_Model  QA  PDF
• 2021-10-06 Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition    Zhong Meng, Yashesh Gaur, Naoyuki Kanda, Jinyu Li, Xie Chen, Yu Wu, Yifan Gong arXiv_AI arXiv_AI  Transformer  Recognition  Speech  Pose  Speech_Recognition  Inference  Language_Model  PDF
• 2021-10-06 On Neurons Invariant to Sentence Structural Changes in Neural Machine Translation    Gal Patel, Leshem Choshen, Omri Abend arXiv_CL arXiv_CL  Transformer  Relation  PDF
• 2021-10-06 Dynamically Decoding Source Domain Knowledge For Unseen Domain Generalization    Cuicui Kang, Karthik Nandakumar arXiv_CV arXiv_CV  Transformer  Knowledge  Pose  Attention  Inference  PDF
• 2021-10-06 Tensor-to-Image: Image-to-Image Translation with Vision Transformers    Yiğit Gündüç arXiv_AI arXiv_AI  Transformer  Deep_Learning  Attention  PDF
• 2021-10-06 Self-Supervised Knowledge Assimilation for Expert-Layman Text Style Transfer    Wenda Xu, Michael Saxon, Misha Sra, William Yang Wang arXiv_CL arXiv_CL  Transformer  Style_Transfer  Knowledge  Self-Supervised  Pose  Medical  Language_Model  PDF
• 2021-10-06 SAIC_Cambridge-HuPBA-FBK Submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021    Swathikiran Sudhakaran, Adrian Bulat, Juan-Manuel Perez-Rua, Alex Falcon, Sergio Escalera, Oswald Lanz, Brais Martinez, Georgios Tzimiropoulos arXiv_CV arXiv_CV  Transformer  Recognition  Action_Recognition  Action  Prediction  PDF
• 2021-10-06 Sequence-to-Sequence Lexical Normalization with Multilingual Transformers    Ana-Maria Bucur, Adrian Cosma, Liviu P. Dinu arXiv_CL arXiv_CL  Transformer  Pose  PDF
• 2021-10-06 PSG HASOC-Dravidian CodeMixFIRE2021: Pretrained Transformers for Offensive Language Identification in Tanglish    Sean Benhur, Kanchana Sivanraju arXiv_CL arXiv_CL  Transformer  Bert  Speech  PDF
• 2021-10-06 Semantic Prediction: Which One Should Come First, Recognition or Prediction?    Hafez Farazi, Jan Nogga, and Sven Behnke arXiv_CV arXiv_CV  Transformer  Recognition  Video_Prediction  Self-Supervised  Action  Prediction  PDF
• 2021-10-06 Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs    Philipp Benz, Soomin Ham, Chaoning Zhang, Adil Karjauv, In So Kweon arXiv_CV arXiv_CV  Transformer  Adversarial  Pose  Attention  CNN  PDF
• 2021-10-06 3rd Place Solution to Google Landmark Recognition Competition 2021    Cheng Xu, Weimin Wang, Shuai Liu, Yong Wang, Yuxiang Tang, Tianling Bian, Yanyu Yan, Qi She, Cheng Yang arXiv_CV arXiv_CV  Transformer  Embedding  Recognition  Face  Classification  Prediction  PDF
• 2021-10-06 How BPE Affects Memorization in Transformers    Eugene Kharitonov, Marco Baroni, Dieuwke Hupkes arXiv_CL arXiv_CL  Transformer  Knowledge  Action  Inference  Language_Model  QA  PDF
• 2021-10-06 2nd Place Solution to Google Landmark Recognition Competition 2021    Shubin Dai arXiv_CV arXiv_CV  Transformer  Recognition  Action  PDF
• 2021-10-06 Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer    Yining Ma, Jingwen Li, Zhiguang Cao, Wen Song, Le Zhang, Zhenghua Chen, Jing Tang arXiv_AI arXiv_AI  Transformer  Embedding  Optimization  Relation  PDF
• 2021-10-06 ABC: Attention with Bounded-memory Control    Hao Peng, Jungo Kasai, Nikolaos Pappas, Dani Yogatama, Zhaofeng Wu, Lingpeng Kong, Roy Schwartz, Noah A. Smith arXiv_CL arXiv_CL  Transformer  Action  Attention  GAN  Inference  Language_Model  PDF
• 2021-10-06 Ripple Attention for Visual Perception with Sub-quadratic Complexity    Lin Zheng, Huijie Pan, Lingpeng Kong arXiv_CV arXiv_CV  Transformer  Pose  Relation  Attention  PDF
• 2021-10-06 PoNet: Pooling Network for Efficient Token Mixing in Long Sequences    Chao-Hong Tan, Qian Chen, Wen Wang, Qinglin Zhang, Siqi Zheng, Zhen-Hua Ling arXiv_AI arXiv_AI  Transformer  Transfer_Learning  Bert  Sparse  Speech  Pose  Action  Attention  PDF
• 2021-10-05 Word Acquisition in Neural Language Models    Tyler A. Chang, Benjamin K. Bergen arXiv_CL arXiv_CL  Transformer  Bert  RNN  Action  Language_Model  Prediction  PDF
• 2021-10-05 Language Modeling using LMUs: 10x Better Data Efficiency or Improved Scaling Compared to Transformers    Narsimha Chilkuri, Eric Hunsberger, Aaron Voelker, Gurshaant Malik, Chris Eliasmith arXiv_CL arXiv_CL  Transformer  RNN  Relation  Attention  Language_Model  PDF
• 2021-10-05 Transformer Assisted Convolutional Network for Cell Instance Segmentation    Deepanshu Pandey, Pradyumna Gupta, Sumit Bhattacharya, Aman Sinha, Rohit Agarwal arXiv_AI arXiv_AI  Transformer  Segmentation  Embedding  Detection  Object_Detection  Attention  CNN  PDF
• 2021-10-05 MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer    Sachin Mehta, Mohammad Rastegari arXiv_AI arXiv_AI  Transformer  Pose  Detection  Object_Detection  Attention  CNN  PDF
• 2021-10-05 Exploring the Limits of Large Scale Pre-training    Samira Abnar, Mostafa Dehghani, Behnam Neyshabur, Hanie Sedghi arXiv_AI arXiv_AI  Transformer  Recognition  Pose  Relation  PDF
• 2021-10-05 Exploiting Twitter as Source of Large Corpora of Weakly Similar Pairs for Semantic Sentence Embeddings    Marco Di Giovanni, Marco Brambilla arXiv_CL arXiv_CL  Transformer  Embedding  Unsupervised  Pose  PDF
• 2021-10-05 FoodChem: A food-chemical relation extraction model    Gjorgjina Cenikj, Barbara Koroušić Seljak, Tome Eftimov arXiv_CL arXiv_CL  Transformer  Bert  Review  Pose  Action  Classification  Relation  Relation_Extraction  Medical  PDF
• 2021-10-05 Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection    Zhirong Ye, Xiangdong Wang, Hong Liu, Yueliang Qian, Rui Tao, Long Yan, Kazushige Ouchi arXiv_SD arXiv_SD  Transformer  Surveillance  Video_Indexing  Boundary_Detection  Classification  Detection  Attention  Prediction  Matching  PDF
• 2021-10-05 Sicilian Translator: A Recipe for Low-Resource NMT    Eryk Wdowiak arXiv_CL arXiv_CL  Transformer  NMT  PDF
• 2021-10-05 Attention Augmented Convolutional Transformer for Tabular Time-series    Sharath M Shankaranarayana, Davor Runje arXiv_AI arXiv_AI  Transformer  Embedding  Quantization  Bert  Represenation_Learning  Pose  Classification  Attention  CNN  Language_Model  PDF
• 2021-10-05 MoEfication: Conditional Computation of Transformer Models for Efficient Inference    Zhengyan Zhang, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou arXiv_CL arXiv_CL  Transformer  Text_Classification  Sparse  Pose  Classification  Inference  Language_Model  PDF
• 2021-10-04 VTAMIQ: Transformers for Attention Modulated Image Quality Assessment    Andrei Chubarau, James Clark arXiv_CV arXiv_CV  Transformer  Salient  Pose  Action  Classification  Attention  QA  PDF
• 2021-10-04 Privacy enabled Financial Text Classification using Differential Privacy and Federated Learning    Priyam Basu, Tiasa Singha Roy, Rakshit Naidu, Zumrut Muftuoglu arXiv_CL arXiv_CL  Transformer  Bert  Text_Classification  Pose  Classification  Detection  Sentiment  PDF
• 2021-10-04 Generalization in NLI: Ways To Go Beyond Simple Heuristics    Prajjwal Bhargava, Aleksandr Drozd, Anna Rogers arXiv_CL arXiv_CL  Transformer  Bert  Adversarial  PDF
• 2021-10-04 A free lunch from ViT: Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition    Yuan Zhang, Jian Cao, Ling Zhang, Xiangcheng Liu, Zhiyi Wang, Feng Ling, Weiqian Chen arXiv_CV arXiv_CV  Transformer  Recognition  Pose  Attention  PDF
• 2021-10-03 Multi-task Voice-Activated Framework using Self-supervised Learning    Shehzeen Hussain, Van Nguyen, Shuhua Zhang, Erik Visser arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Self-Supervised  Pose  Emotion  Classification  Speech_Recognition  PDF
• 2021-10-03 Multimodal Fusion Based Attentive Networks for Sequential Music Recommendation    Kunal Vaswani, Yudhik Agrawal, Vinoo Alluri arXiv_SD arXiv_SD  Transformer  Pose  Emotion  Deep_Learning  Prediction  Recommendation  PDF
• 2021-10-03 Translating Images into Maps    Avishkar Saha, Oscar Mendez Maldonado, Chris Russell, Richard Bowden arXiv_CV arXiv_CV  Transformer  CNN  PDF
• 2021-10-03 Music Playlist Title Generation: A Machine-Translation Approach    SeungHeon Doh, Junwon Lee, Juhan Nam arXiv_CL arXiv_CL  Transformer  RNN  Pose  GAN  PDF
• 2021-10-02 Implicit and Explicit Attention for Zero-Shot Learning    Faisal Alamri, Anjan Dutta arXiv_CV arXiv_CV  Image_Caption  Transformer  Zero-Shot  Self-Supervised  Pose  Attention  PDF
• 2021-10-02 SurvTRACE: Transformers for Survival Analysis with Competing Events    Zifeng Wang, Jimeng Sun arXiv_AI arXiv_AI  Transformer  Pose  Attention  PDF
• 2021-10-02 ProTo: Program-Guided Transformer for Program-Guided Tasks    Zelin Zhao, Karan Samel, Binghong Chen, Le Song arXiv_AI arXiv_AI  Transformer  Pose  Attention  QA  PDF
• 2021-10-01 Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification    Jiong Zhang, Wei-cheng Chang, Hsiang-fu Yu, Inderjit S. Dhillon arXiv_AI arXiv_AI  Transformer  Text_Classification  Pose  Classification  Recommendation  PDF
• 2021-10-01 Geometry Attention Transformer with Position-aware LSTMs for Image Captioning    Chi Wang, Yulin Shen, Luping Ji arXiv_CV arXiv_CV  Image_Caption  Transformer  RNN  Pose  Relation  Attention  Caption  PDF
• 2021-10-01 Lightweight Transformer in Federated Setting for Human Activity Recognition    Ali Raza, Kim Phuc Tran, Ludovic Koehl, Shujun Li, Xianyi Zeng, Khaled Benzaidi arXiv_AI arXiv_AI  Transformer  Recognition  RNN  Pose  Activity  CNN  PDF
• 2021-10-01 Data-Efficient Instance Segmentation with a Single GPU    Pengyu Chen, Wanhua Li, Jiwen Lu arXiv_CV arXiv_CV  Transformer  Segmentation  Detection  Inference  PDF
• 2021-10-01 Predicting COVID-19 Patient Shielding: A Comprehensive Study    Vithya Yogarajan, Jacob Montiel, Tony Smith, Bernhard Pfahringer arXiv_AI arXiv_AI  Transformer  Knowledge  Classification  GAN  Medical  Prediction  PDF
• 2021-09-30 Learning to Predict Trustworthiness with Steep Slope Loss    Yan Luo, Yongkang Wong, Mohan S. Kankanhalli, Qi Zhao arXiv_CV arXiv_CV  Transformer  Pose  Deep_Learning  Prediction  PDF
• 2021-09-30 Multi-granular Legal Topic Classification on Greek Legislation    Christos Papaloukas, Ilias Chalkidis, Konstantinos Athinaios, Despina-Athanasia Pantazi, Manolis Koubarakis arXiv_CL arXiv_CL  Transformer  Embedding  Transfer_Learning  Text_Classification  RNN  Knowledge  Classification  PDF
• 2021-09-30 MatSciBERT: A Materials Domain Language Model for Text Mining and Information Extraction    Tanishq Gupta, Mohd Zaki, N. M. Anoop Krishnan, Mausam arXiv_CL arXiv_CL  Transformer  Recognition  Bert  Optimization  Knowledge  Review  Action  Classification  Relation  Relation_Extraction  Language_Model  PDF
• 2021-09-30 Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks    Yichen Jiang, Mohit Bansal arXiv_AI arXiv_AI  Transformer  Pose  Action  Attention  Inference  Prediction  PDF
• 2021-09-30 SlovakBERT: Slovak Masked Language Model    Matúš Pikuliak, Štefan Grivalský, Martin Konôpka, Miroslav Blšták, Martin Tamajka, Viktor Bachratý, Marián Šimko, Pavol Balážik, Michal Trnka, Filip Uhlárik arXiv_CL arXiv_CL  Transformer  Bert  Speech  Sentiment  Language_Model  PDF
• 2021-09-30 CoSeg: Cognitively Inspired Unsupervised Generic Event Segmentation    Xiao Wang, Jingen Liu, Tao Mei, Jiebo Luo arXiv_CV arXiv_CV  Transformer  Reconstruction  Segmentation  Embedding  Unsupervised  Self-Supervised  Pose  Boundary_Detection  Detection  Prediction  PDF
• 2021-09-30 Compositional generalization in semantic parsing with pretrained transformers    A. Emin Orhan arXiv_CL arXiv_CL  Transformer  Knowledge  Language_Model  Prediction  PDF
• 2021-09-30 Self-conditioning pre-trained language models    Xavier Suau, Luca Zappella, Nicholas Apostoloff arXiv_CL arXiv_CL  Transformer  Knowledge  Text_Generation  Inference  Language_Model  PDF
• 2021-09-30 Deep Neural Compression Via Concurrent Pruning and Self-Distillation    James O' Neill, Sourav Dutta, Haytham Assem arXiv_CL arXiv_CL  Transformer  Sparse  Knowledge  Pose  Relation  Language_Model  PDF
• 2021-09-30 Syntactic Persistence in Language Models: Priming as a Window into Abstract Language Representations    Arabella Sinclair, Jaap Jumelet, Willem Zuidema, Raquel Fernández arXiv_CL arXiv_CL  Transformer  Knowledge  Language_Model  PDF
• 2021-09-30 MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction    Hao Xue, Flora D.Salim, Yongli Ren, Nuria Oliver arXiv_AI arXiv_AI  Transformer  Pose  Relation  Attention  Prediction  PDF
• 2021-09-30 Prose2Poem: The blessing of Transformer-based Language Models in translating Prose to Persian Poetry    Reza Khanmohammadi, Mitra Sadat Mirshafiee, Yazdan Rezaee Jouryabi, Seyed Abolghasem Mirroshandel arXiv_CL arXiv_CL  Transformer  Bert  Speech  NMT  Language_Model  PDF
• 2021-09-30 BERT got a Date: Introducing Transformers to Temporal Tagging    Satya Almasian, Dennis Aumiller, Michael Gertz arXiv_CL arXiv_CL  Transformer  Bert  Classification  Language_Model  PDF
• 2021-09-30 COVID-19 Fake News Detection Using Bidirectiona lEncoder Representations from Transformers Based Models    Yuxiang Wang, Yongheng Zhang, Xuebo Li, Xinyao Yu arXiv_CL arXiv_CL  Transformer  Bert  RNN  Classification  Detection  PDF
• 2021-09-30 GT U-Net: A U-Net Like Group Transformer Network for Tooth Root Segmentation    Yunxiang Li, Shuai Wang, Jun Wang, Guodong Zeng, Wenjun Liu, Qianni Zhang, Qun Jin, Yaqi Wang arXiv_CV arXiv_CV  Transformer  Segmentation  Optimization  Knowledge  Pose  PDF
• 2021-09-29 Subdimensional Expansion Using Attention-Based Learning For Multi-Agent Path Finding    Lakshay Virmani, Zhongqiang Ren, Sivakumar Rathinam, Howie Choset arXiv_AI arXiv_AI  Transformer  Attention  PDF
• 2021-09-29 CCTrans: Simplifying and Improving Crowd Counting with Transformer    Ye Tian, Xiangxiang Chu, Hongpeng Wang arXiv_CV arXiv_CV  Transformer  Pose  CNN  PDF
• 2021-09-29 UFO-ViT: High Performance Linear Vision Transformer without Softmax    Jeong-geun Song arXiv_CV arXiv_CV  Transformer  Pose  Classification  Attention  CNN  Image_Classification  Prediction  PDF
• 2021-09-29 Infrared Small-Dim Target Detection with Transformer under Complex Backgrounds    Fangcen Liu, Chenqiang Gao, Fang Chen, Deyu Meng, Wangmeng Zuo, Xinbo Gao arXiv_CV arXiv_CV  Transformer  Tracking  Enhancement  Pose  Action  Deep_Learning  Detection  Attention  CNN  PDF
• 2021-09-29 Localizing Objects with Self-Supervised Transformers and no Labels    Oriane Siméoni, Gilles Puy, Huy V. Vo, Simon Roburin, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Renaud Marlet, Jean Ponce arXiv_CV arXiv_CV  Transformer  Unsupervised  Self-Supervised  Pose  Detection  Object_Detection  PDF
• 2021-09-29 Hierarchical Character Tagger for Short Text Spelling Error Correction    Mengyi Gao, Canran Xu, Peng Shi arXiv_CL arXiv_CL  Transformer  Bert  Pose  Inference  Language_Model  PDF
• 2021-09-29 Road Network Guided Fine-Grained Urban Traffic Flow Inference    Lingbo Liu, Mengmeng Liu, Guanbin Li, Ziyi Wu, Liang Lin arXiv_AI arXiv_AI  Transformer  Knowledge  Pose  Relation  CNN  Inference  PDF
• 2021-09-29 Geometry-Entangled Visual Semantic Transformer for Image Captioning    Ling Cheng, Wei Wei, Feida Zhu, Yong Liu, Chunyan Miao arXiv_CV arXiv_CV  Image_Caption  Transformer  Pose  Attention  Caption  PDF
• 2021-09-28 VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding    Hu Xu, Gargi Ghosh, Po-Yao Huang, Dmytro Okhonko, Armen Aghajanyan, Florian Metze Luke Zettlemoyer Christoph Feichtenhofer arXiv_CV arXiv_CV  Transformer  Segmentation  Zero-Shot  Action_Localization  Action  QA  Video_Retrieval  PDF
• 2021-09-28 Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations    Ekaterina Taktasheva, Vladislav Mikhailov, Ekaterina Artemova arXiv_CL arXiv_CL  Transformer  Embedding  Bert  Pose  Attention  GAN  Language_Model  PDF
• 2021-09-28 How Different Text-preprocessing Techniques Using The BERT Model Affect The Gender Profiling of Authors    Esam Alzahrani, Leon Jololian arXiv_CL arXiv_CL  Transformer  Transfer_Learning  Bert  Review  Pose  Face  PDF
• 2021-09-28 Single-dataset Experts for Multi-dataset Question Answering    Dan Friedman, Ben Dodge, Danqi Chen arXiv_CL arXiv_CL  Transformer  Zero-Shot  Few-Shot  PDF
• 2021-09-28 One to rule them all: Towards Joint Indic Language Hate Speech Detection    Mehar Bhatia, Tenzin Singhay Bhotia, Akshat Agarwal, Prakash Ramesh, Shubham Gupta, Kumar Shridhar, Felix Laumann, Ayushman Dash arXiv_CL arXiv_CL  Transformer  Speech  Classification  Detection  Language_Model  PDF
• 2021-09-28 Nana-HDR: A Non-attentive Non-autoregressive Hybrid Model for TTS    Shilun Lin, Wenchao Su, Li Meng, Fenglong Xie, Xinhui Li, Li Lu arXiv_CL arXiv_CL  Transformer  RNN  Attention  PDF
• 2021-09-28 Generating texts under constraint through discriminator-guided MCTS    Antoine Chaffin, Vincent Claveau, Ewa Kijak arXiv_CL arXiv_CL  Transformer  Review  Pose  Emotion  Language_Model  PDF
• 2021-09-28 Exploring Teacher-Student Learning Approach for Multi-lingual Speech-to-Intent Classification    Bidisha Sharma, Maulik Madhavi, Xuehao Zhou, Haizhou Li arXiv_AI arXiv_AI  Transformer  Bert  Knowledge  Speech  Classification  PDF
• 2021-09-28 Fine-tuning Vision Transformers for the Prediction of State Variables in Ising Models    Onur Kara, Arijit Sehanobish, Hector H Corzo arXiv_CV arXiv_CV  Transformer  Pose  Deep_Learning  Attention  CNN  Prediction  PDF
• 2021-09-27 On Isotropy Calibration of Transformers    Yue Ding, Karolis Martinkus, Damian Pascual, Simon Clematide, Roger Wattenhofer arXiv_CL arXiv_CL  Transformer  Embedding  Language_Model  PDF
• 2021-09-27 TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation    Adaku Uchendu, Zeyu Ma, Thai Le, Rui Zhang, Dongwon Lee arXiv_CL arXiv_CL  Transformer  Knowledge  Detection  Text_Generation  Language_Model  PDF
• 2021-09-27 Discovering Drug-Target Interaction Knowledge from Biomedical Literature    Yutai Hou, Yingce Xia, Lijun Wu, Shufang Xie, Yang Fan, Jinhua Zhu, Wanxiang Che, Tao Qin, Tie-Yan Liu arXiv_AI arXiv_AI  Transformer  Knowledge  Pose  Action  Relation  Medical  PDF
• 2021-09-27 Multimodal Integration of Human-Like Attention in Visual Question Answering    Ekta Sood, Fabian Kögel, Philipp Müller, Dominike Thomas, Mihai Bace, Andreas Bulling arXiv_CV arXiv_CV  Transformer  Salient  VQA  Attention  Prediction  QA  PDF
• 2021-09-27 Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer    Evgeniia Tokarchuk, Jan Rosendahl, Weiyue Wang, Pavel Petrushkov, Tomer Lancewicki, Shahram Khadivi, Hermann Ney arXiv_CL arXiv_CL  Transformer  Reinforcement_Learning  Pose  NMT  Text_Generation  PDF
• 2021-09-27 Improving Stack Overflow question title generation with copying enhanced CodeBERT model and bi-modal information    Fengji Zhang, Jacky Keung, Xiao Yu, Zhiwen Xie, Zhen Yang, Caoyuan Ma, Zhimin Zhang arXiv_AI arXiv_AI  Transformer  Bert  RNN  Pose  Deep_Learning  Attention  PDF
• 2021-09-27 Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer    Evgeniia Tokarchuk, Jan Rosendahl, Weiyue Wang, Pavel Petrushkov, Tomer Lancewicki, Shahram Khadivi, Hermann Ney arXiv_CL arXiv_CL  Transformer  Speech  Pose  PDF
• 2021-09-27 Understanding and Overcoming the Challenges of Efficient Transformer Quantization    Yelysei Bondarenko, Markus Nagel, Tijmen Blankevoort arXiv_AI arXiv_AI  Transformer  Embedding  Quantization  Bert  Attention  Inference  PDF
• 2021-09-27 Sparse Spatial Transformers for Few-Shot Learning    Haoxing Chen, Huaxiong Li, Yaohui Li, Chunlin Chen arXiv_CV arXiv_CV  Transformer  Embedding  Sparse  Pose  Few-Shot  Matching  PDF
• 2021-09-27 Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates    Hirofumi Inaguma, Siddharth Dalmia, Brian Yan, Shinji Watanabe arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Pose  Classification  Speech_Recognition  Inference  Language_Model  PDF
• 2021-09-27 Multiplicative Position-aware Transformer Models for Language Understanding    Zhiheng Huang, Davis Liang, Peng Xu, Bing Xiang arXiv_AI arXiv_AI  Transformer  Embedding  Bert  Review  Pose  Attention  PDF
• 2021-09-27 Joint Multimedia Event Extraction from Video and Article    Brian Chen, Xudong Lin, Christopher Thomas, Manling Li, Shoya Yoshida, Lovish Chum, Heng Ji, Shih-Fu Chang arXiv_CV arXiv_CV  Transformer  Self-Supervised  Pose  Action  PDF
• 2021-09-27 Abstraction, Reasoning and Deep Learning: A Study of the 'Look and Say' Sequence    Wlodek W. Zadrozny arXiv_AI arXiv_AI  Transformer  RNN  Action  Deep_Learning  Attention  PDF
• 2021-09-26 Improving Question Answering Performance Using Knowledge Distillation and Active Learning    Yasaman Boreshban, Seyed Morteza Mirbostani, Gholamreza Ghassem-Sani, Seyed Abolghasem Mirroshandel, Shahin Amiriparian arXiv_CL arXiv_CL  Transformer  Bert  Knowledge  Pose  QA  PDF
• 2021-09-26 Vision Transformer Hashing for Image Retrieval    Shiv Ram Dubey, Satish Kumar Singh, Wei-Ta Chu arXiv_CV arXiv_CV  Transformer  Quantization  Recognition  Image_Retrieval  Pose  Deep_Learning  Attention  PDF
• 2021-09-26 PETA: Photo Albums Event Recognition using Transformers Attention    Tamar Glaser, Emanuel Ben-Baruch, Gilad Sharir, Nadav Zamir, Asaf Noy, Lihi Zelnik-Manor arXiv_CV arXiv_CV  Image_Caption  Transformer  Recognition  RNN  Pose  Classification  Attention  PDF
• 2021-09-26 ViT Cane: Visual Assistant for the Visually Impaired    Bhavesh Kumar arXiv_AI arXiv_AI  Transformer  Pose  Face  Detection  PDF
• 2021-09-25 Language Model Priming for Cross-Lingual Event Extraction    Steven Fincke, Shantanu Agarwal, Scott Miller, Elizabeth Boschee arXiv_CL arXiv_CL  Transformer  Zero-Shot  Sparse  Action  Classification  Detection  Language_Model  PDF
• 2021-09-25 DziriBERT: a Pre-trained Language Model for the Algerian Dialect    Amine Abdaoui, Mohamed Berrimi, Mourad Oussalah, Abdelouahab Moussaoui arXiv_CL arXiv_CL  Transformer  Bert  Attention  Language_Model  PDF
• 2021-09-25 Finetuning Transformer Models to Build ASAG System    Mithun Thakkar arXiv_AI arXiv_AI  Transformer  Bert  Face  Relation  PDF
• 2021-09-25 BiTr-Unet: a CNN-Transformer Combined Network for MRI Brain Tumor Segmentation    Qiran Jia, Hai Shu arXiv_AI arXiv_AI  Transformer  Segmentation  3D  Pose  Classification  Attention  GAN  Medical  CNN  Image_Classification  PDF
• 2021-09-25 Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features    Bruce W. Lee, Yoo Sung Jang, Jason Hyung-Jong Lee arXiv_AI arXiv_AI  Transformer  Bert  Action  Classification  PDF
• 2021-09-25 Systematic Generalization on gSCAN: What is Nearly Solved and What is Next?    Linlu Qiu, Hexiang Hu, Bowen Zhang, Peter Shaw, Fei Sha arXiv_CL arXiv_CL  Transformer  Pose  Relation  Attention  PDF
• 2021-09-24 Predicting Attention Sparsity in Transformers    Marcos Treviso, António Góis, Patrick Fernandes, Erick Fonseca, André F. T. Martins arXiv_CL arXiv_CL  Transformer  Quantization  Sparse  Pose  Attention  Language_Model  PDF
• 2021-09-24 MLIM: Vision-and-Language Model Pre-training with Masked Language and Image Modeling    Tarik Arici, Mehmet Saygin Seyfioglu, Tal Neiman, Yi Xu, Son Train, Trishul Chilimbi, Belinda Zeng, Ismail Tutar arXiv_AI arXiv_AI  Transformer  Reconstruction  Pose  Action  Classification  Detection  Object_Detection  Language_Model  PDF
• 2021-09-24 Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations    Longxiang Zhang, Renato Negrinho, Arindam Ghosh, Vasudevan Jagannathan, Hamid Reza Hassanzadeh, Thomas Schaaf, Matthew R. Gormley arXiv_CL arXiv_CL  Transformer  Summarization  Medical  PDF
• 2021-09-24 Monolingual and Cross-Lingual Acceptability Judgments with the Italian CoLA corpus    Daniela Trotta, Raffaele Guarasci, Elisa Leonardelli, Sara Tonelli arXiv_CL arXiv_CL  Transformer  Classification  PDF
• 2021-09-24 Transformers Generalize Linearly    Jackson Petty, Robert Frank arXiv_CL arXiv_CL  Transformer  Face  Relation  Language_Model  PDF
• 2021-09-24 Unsupervised Translation of German--Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language    Lukas Edman, Ahmet Üstün, Antonio Toral, Gertjan van Noord arXiv_CL arXiv_CL  Transformer  Unsupervised  PDF
• 2021-09-24 Localizing Infinity-shaped fishes: Sketch-guided object localization in the wild    Pau Riba, Sounak Dey, Ali Furkan Biten, Josep Llados arXiv_CV arXiv_CV  Transformer  Segmentation  Sketch  Classification  Detection  Object_Detection  PDF
• 2021-09-24 A Diversity-Enhanced and Constraints-Relaxed Augmentation for Low-Resource Classification    Guang Liu, Hailong Huang, Yuzhao Mao, Weiguo Gao, Xuan Li, Jianping Shen arXiv_CL arXiv_CL  Transformer  Regularization  Pose  Classification  Language_Model  PDF
• 2021-09-24 DACT-BERT: Differentiable Adaptive Computation Time for an Efficient BERT Inference    Cristóbal Eyzaguirre, Felipe del Río, Vladimir Araujo, Álvaro Soto arXiv_AI arXiv_AI  Transformer  Bert  Pose  Inference  Language_Model  PDF
• 2021-09-23 Turn-to-Diarize: Online Speaker Diarization Constrained by Transformer Transducer Speaker Turn Detection    Wei Xia, Han Lu, Quan Wang, Anshuman Tripathi, Ignacio Lopez Moreno, Hasim Sak arXiv_SD arXiv_SD  Transformer  Embedding  Detection  PDF
• 2021-09-23 End-to-End Dense Video Grounding via Parallel Regression    Fengyuan Shi, Limin Wang, Weilin Huang arXiv_CV arXiv_CV  Transformer  Sparse  Detection  Attention  Caption  Activity  Inference  PDF
• 2021-09-23 The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21    Lihua Qian, Yi Zhou, Zaixiang Zheng, Yaoming Zhu, Zehui Lin, Jiangtao Feng, Shanbo Cheng, Lei Li, Mingxuan Wang, Hao Zhou arXiv_CL arXiv_CL  Transformer  Knowledge  PDF
• 2021-09-23 Incorporating Linguistic Knowledge for Abstractive Multi-document Summarization    Congbo Ma, Wei Emma Zhang, Hu Wang, Shubham Gupta, Mingyu Guo arXiv_CL arXiv_CL  Transformer  Knowledge  Pose  Relation  Attention  Summarization  PDF
• 2021-09-23 Findings of the NLP4IF-2021 Shared Tasks on Fighting the COVID-19 Infodemic and Censorship Detection    Shaden Shaar, Firoj Alam, Giovanni Da San Martino, Alex Nikolov, Wajdi Zaghouani, Preslav Nakov, Anna Feldman arXiv_CL arXiv_CL  Transformer  Detection  Attention  PDF
• 2021-09-23 OH-Former: Omni-Relational High-Order Transformer for Person Re-Identification    Xianing Chen, Jialang Xu, Jiale Xu, Shenghua Gao arXiv_CV arXiv_CV  Transformer  Person_Re-identification  Pose  Relation  Attention  Re-identification  PDF
• 2021-09-22 Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models    Yiwen Wang, Jennifer Hu, Roger Levy, Peng Qian arXiv_CL arXiv_CL  Transformer  Sparse  RNN  Knowledge  Relation  Language_Model  PDF
• 2021-09-22 T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regression    Arash Amini, Arul Selvam Periyasamy, Sven Behnke arXiv_CV arXiv_CV  Transformer  Pose_Estimation  Pose  Detection  Object_Detection  Attention  Inference  Prediction  PDF
• 2021-09-22 Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers    Yi Tay, Mostafa Dehghani, Jinfeng Rao, William Fedus, Samira Abnar, Hyung Won Chung, Sharan Narang, Dani Yogatama, Ashish Vaswani, Donald Metzler arXiv_AI arXiv_AI  Transformer  Language_Model  PDF
• 2021-09-22 Enriching and Controlling Global Semantics for Text Summarization    Thong Nguyen, Anh Tuan Luu, Truc Lu, Tho Quan arXiv_CL arXiv_CL  Transformer  Summarization  Text_Generation  PDF
• 2021-09-22 Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning    IlWi Yun, Hyuk-Jae Lee, Chae Eun Rhee arXiv_CV arXiv_CV  Transformer  Knowledge  Self-Supervised  Pose  Prediction  PDF
• 2021-09-22 Hierarchical Multimodal Transformer to Summarize Videos    Bin Zhao, Maoguo Gong, Xuelong Li arXiv_AI arXiv_AI  Transformer  Video_Caption  RNN  Pose  Relation  Attention  Summarization  Caption  PDF
• 2021-09-22 KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation    Yongfei Liu, Chenfei Wu, Shao-yen Tseng, Vasudev Lal, Xuming He, Nan Duan arXiv_CV arXiv_CV  Transformer  Represenation_Learning  Knowledge  Self-Supervised  Pose  Detection  Object_Detection  PDF
• 2021-09-22 The NiuTrans Machine Translation Systems for WMT21    Shuhan Zhou, Tao Zhou, Binghao Wei, Yingfeng Luo, Yongyu Mu, Zefan Zhou, Chenglong Wang, Xuanjun Zhou, Chuanhao Lv, Yi Jing, Laohu Wang, Jingnan Zhang, Canan Huang, Zhongxiang Yan, Chi Hu, Bei Li, Tong Xiao, Jingbo Zhu arXiv_CL arXiv_CL  Transformer  Knowledge  PDF
• 2021-09-21 Extracting Fine-Grained Knowledge Graphs of Scientific Claims: Dataset and Transformer-Based Results    Ian H. Magnusson, Scott E. Friedman arXiv_CL arXiv_CL  Transformer  Knowledge  Knowledge_Graph  Action  Relation  Relation_Extraction  PDF
• 2021-09-21 From English to Signal Temporal Logic    Jie He, Ezio Bartocci, Dejan Ničković, Haris Isakovic, Radu Grosu arXiv_CL arXiv_CL  Transformer  Pose  Attention  PDF
• 2021-09-21 TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models    Minghao Li, Tengchao Lv, Lei Cui, Yijuan Lu, Dinei Florencio, Cha Zhang, Zhoujun Li, Furu Wei arXiv_CV arXiv_CV  Image_Caption  Transformer  Recognition  OCR  RNN  Optical_Character  Pose  Text_Generation  Language_Model  PDF
• 2021-09-21 Audiomer: A Convolutional Transformer for Keyword Spotting    Surya Kant Sahu, Sai Mitheran, Juhi Kamdar, Meet Gandhi arXiv_CL arXiv_CL  Transformer  Action  Attention  CNN  PDF
• 2021-09-21 BERTweetFR : Domain Adaptation of Pre-Trained Language Models for French Tweets    Yanzhu Guo, Virgile Rennard, Christos Xypolopoulos, Michalis Vazirgiannis arXiv_CL arXiv_CL  Transformer  Recognition  Bert  Detection  Language_Model  PDF
• 2021-09-21 Are Transformers a Modern Version of ELIZA? Observations on French Object Verb Agreement    Bingzhi Li, Guillaume Wisniewski, Benoit Crabbé arXiv_CL arXiv_CL  Transformer  Unsupervised  RNN  Face  Language_Model  PDF
• 2021-09-21 ConvFiT: Conversational Fine-Tuning of Pretrained Language Models    Ivan Vulić, Pei-Hao Su, Sam Coope, Daniela Gerz, Paweł Budzianowski, Iñigo Casanueva, Nikola Mrkšić, Tsung-Hsien Wen arXiv_CL arXiv_CL  Transformer  Knowledge  Pose  Detection  Few-Shot  Inference  Language_Model  PDF
• 2021-09-21 InvBERT: Text Reconstruction from Contextualized Embeddings used for Derived Text Formats of Literary Works    Johannes Höhmann, Achim Rettinger, Kai Kugler arXiv_CL arXiv_CL  Transformer  Reconstruction  Embedding  Bert  Pose  Quantitative  PDF
• 2021-09-21 DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers    Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang arXiv_CV arXiv_CV  Transformer  Optimization  Sparse  Pose  Inference  PDF
• 2021-09-21 LOTR: Face Landmark Localization Using Localization Transformer    Ukrit Watchareeruetai, Benjaphan Sommanna, Sanjana Jain, Pavit Noinongyao, Ankush Ganguly, Aubin Samacoits, Samuel W.F. Earp, Nakarin Sritrakool arXiv_AI arXiv_AI  Transformer  Facial_Landmark  Pose  Face  Prediction  PDF
• 2021-09-21 Something Old, Something New: Grammar-based CCG Parsing with Transformer Models    Stephen Clark arXiv_CL arXiv_CL  Transformer  PDF
• 2021-09-21 Multi-Domain Few-Shot Learning and Dataset for Agricultural Applications    Sai Vidyaranya Nuthalapati, Anirudh Tunga arXiv_CV arXiv_CV  Transformer  Embedding  Pose  Classification  Deep_Learning  Few-Shot  CNN  Image_Classification  PDF
• 2021-09-21 Survey: Transformer based Video-Language Pre-training    Ludan Ruan, Qin Jin arXiv_CV arXiv_CV  Transformer  Knowledge  Survey  Attention  PDF
• 2021-09-20 Well Googled is Half Done: Multimodal Forecasting of New Fashion Product Sales with Image-based Google Trends    Geri Skenderi, Christian Joppi, Matteo Denitto, Marco Cristani arXiv_CV arXiv_CV  Transformer  Knowledge  Pose  PDF
• 2021-09-20 Transforming Fake News: Robust Generalisable News Classification Using Transformers    Ciara Blackledge, Amir Atapour-Abarghouei arXiv_CL arXiv_CL  Transformer  Knowledge  Pose  Classification  Attention  Inference  PDF
• 2021-09-20 DisCoDisCo at the DISRPT2021 Shared Task: A System for Discourse Segmentation, Classification, and Connective Detection    Luke Gessler, Shabnam Behzad, Yang Janet Liu, Siyao Peng, Yilun Zhu, Amir Zeldes arXiv_CL arXiv_CL  Transformer  Segmentation  Embedding  Classification  Detection  Relation  Language_Model  Prediction  PDF
• 2021-09-20 MFEViT: A Robust Lightweight Transformer-based Network for Multimodal 2D+3D Facial Expression Recognition    Hanting Li, Mingzhe Sui, Zhaoqing Zhu, Feng Zhao arXiv_AI arXiv_AI  Transformer  Recognition  3D  Knowledge  Pose  Attention  PDF
• 2021-09-20 Audio-Visual Speech Recognition is Worth 32$times$32$times$8 Voxels    Dmitriy Serdyuk, Otavio Braga, Olivier Siohan arXiv_CV arXiv_CV  Transformer  Recognition  3D  Speech  Pose  Classification  Speech_Recognition  CNN  Image_Classification  PDF
• 2021-09-20 PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation    Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Zhihua Wu, Zhen Guo, Hua Lu, Xinxian Huang, Xin Tian, Xinchao Xu, Yingzhan Lin, Zhengyu Niu arXiv_CL arXiv_CL  Transformer  Knowledge  PDF
• 2021-09-20 Dyadformer: A Multi-modal Transformer for Long-Range Modeling of Dyadic Interactions    David Curto, Albert Clapés, Javier Selva, Sorina Smeureanu, Julio C. S. Jacques Junior, David Gallardo-Pujol, Georgina Guilera, David Leiva, Thomas B. Moeslund, Sergio Escalera, Cristina Palmero arXiv_AI arXiv_AI  Transformer  Pose  Action  Attention  Inference  PDF
• 2021-09-19 Unified and Multilingual Author Profiling for Detecting Haters    Ipek Baris Schlicht, Angel Felipe Magnossão de Paula arXiv_AI arXiv_AI  Transformer  Speech  Pose  Attention  PDF
• 2021-09-19 Automated and Explainable Ontology Extension Based on Deep Learning: A Case Study in the Chemical Domain    Adel Memariani, Martin Glauer, Fabian Neuhaus, Till Mossakowski, Janna Hastings arXiv_AI arXiv_AI  Transformer  Knowledge  Pose  Ontology  Deep_Learning  Attention  PDF
• 2021-09-19 Do Long-Range Language Models Actually Use Long-Range Context?    Simeng Sun, Kalpesh Krishna, Andrew Mattarella-Micke, Mohit Iyyer arXiv_CL arXiv_CL  Transformer  Pose  Attention  Language_Model  Prediction  PDF
• 2021-09-18 Augmenting semantic lexicons using word embeddings and transfer learning    Thayer Alshaabi, Colin Van Oort, Mikaela Fudolig, Michael V. Arnold, Christopher M. Danforth, Peter Sheridan Dodds arXiv_CL arXiv_CL  Transformer  Embedding  Transfer_Learning  Review  Pose  Action  Sentiment  Language_Model  Recommendation  PDF
• 2021-09-18 SDTP: Semantic-aware Decoupled Transformer Pyramid for Dense Image Prediction    Zekun Li, Yufan Liu, Bing Li, Weiming Hu, Kebin Wu, Pei Wang arXiv_CV arXiv_CV  Transformer  Pose  Action  Attention  Prediction  PDF
• 2021-09-18 Efficient Hybrid Transformer: Learning Global-local Context for Urban Sence Segmentation    Libo Wang, Shenghui Fang, Ce Zhang, Rui Li, Chenxi Duan arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  Pose  Action  Classification  Deep_Learning  Detection  Object_Detection  CNN  Image_Classification  PDF
• 2021-09-18 Towards High-Quality Temporal Action Detection with Sparse Proposals    Jiannan Wu, Peize Sun, Shoufa Chen, Jiewen Yang, Zihao Qi, Lan Ma, Ping Luo arXiv_CV arXiv_CV  Transformer  Video_Caption  Sparse  Action  Detection  Attention  Activity  PDF
• 2021-09-18 MM-Deacon: Multimodal molecular domain embedding analysis via contrastive learning    Zhihui Guo, Pramod Kumar Sharma, Liang Du, Robin Abraham arXiv_CL arXiv_CL  Transformer  Embedding  Represenation_Learning  Pose  Contrastive_Learning  Action  Language_Model  PDF
• 2021-09-17 The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task    Shuoyang Ding, Marcin Junczys-Dowmunt, Matt Post, Christian Federmann, Philipp Koehn arXiv_CL arXiv_CL  Transformer  PDF
• 2021-09-17 Primer: Searching for Efficient Transformers for Language Modeling    David R. So, Wojciech Mańke, Hanxiao Liu, Zihang Dai, Noam Shazeer, Quoc V. Le arXiv_AI arXiv_AI  Transformer  Attention  Inference  Language_Model  PDF
• 2021-09-17 Towards Handling Unconstrained User Preferences in Dialogue    Suraj Pandey, Svetlana Stoyanchev, Rama Doddipatla arXiv_CL arXiv_CL  Transformer  Unsupervised  Knowledge  Review  Pose  Face  Recommendation  PDF
• 2021-09-17 Grounding Natural Language Instructions: Can Large Language Models Capture Spatial Information?    Julia Rozanova, Deborah Ferreira, Krishna Dubba, Weiwei Cheng, Dell Zhang, Andre Freitas arXiv_AI arXiv_AI  Transformer  Bert  Pose  Face  Language_Model  PDF
• 2021-09-17 The futility of STILTs for the classification of lexical borrowings in Spanish    Javier de la Rosa arXiv_CL arXiv_CL  Transformer  Recognition  Bert  Speech  Classification  Detection  Language_Model  PDF
• 2021-09-17 Boosting Transformers for Job Expression Extraction and Classification in a Low-Resource Setting    Lukas Lange, Heike Adel, Jannik Strötgen arXiv_CL arXiv_CL  Transformer  Transfer_Learning  Action  Classification  PDF
• 2021-09-17 Slot Filling for Biomedical Information Extraction    Yannis Papanikolaou, Francine Bennett arXiv_CL arXiv_CL  Transformer  Recognition  Zero-Shot  Knowledge  Pose  Action  Relation  Relation_Extraction  Medical  PDF
• 2021-09-17 Continuous Streaming Multi-Talker ASR with Dual-path Transducers    Desh Raj, Liang Lu, Zhuo Chen, Yashesh Gaur, Jinyu Li arXiv_SD arXiv_SD  Transformer  Recognition  RNN  Speech  Pose  PDF
• 2021-09-17 Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules    Forough Arabshahi, Jennifer Lee, Antoine Bosselut, Yejin Choi, Tom Mitchell arXiv_AI arXiv_AI  Transformer  Zero-Shot  Knowledge  Pose  Face  Action  PDF
• 2021-09-17 Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation    Feilong Chen, Fandong Meng, Xiuyi Chen, Peng Li, Jie Zhou arXiv_CV arXiv_CV  Transformer  Pose  Attention  PDF
• 2021-09-17 Neural Unification for Logic Reasoning over Natural Language    Gabriele Picco, Hoang Thanh Lam, Marco Luca Sbodio, Vanessa Lopez Garcia arXiv_CL arXiv_CL  Transformer  Pose  Inference  PDF
• 2021-09-17 Transformer-Unet: Raw Image Processing with Unet    Youyang Sha, Yonghong Zhang, Xuquan Ji, Lei Hu arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  Pose  Classification  Detection  Object_Detection  Attention  Medical  Image_Classification  PDF
• 2021-09-17 Expression Snippet Transformer for Robust Video-based Facial Expression Recognition    Yuanyuan Liu, Wenbin Wang, Chuanxu Feng, Haoyu Zhang, Zhe Chen, Yibing Zhan arXiv_CV arXiv_CV  Transformer  Recognition  3D  Salient  Pose  Relation  Attention  Visual_Relation  Prediction  PDF
• 2021-09-17 Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers    Jason Phang, Haokun Liu, Samuel R. Bowman arXiv_CL arXiv_CL  Transformer  Bert  PDF
• 2021-09-17 GraFormer: Graph Convolution Transformer for 3D Pose Estimation    Weixi Zhao, Yunjie Tian, Qixiang Ye, Jianbin Jiao, Weiqiang Wang arXiv_CV arXiv_CV  Transformer  3D  Pose_Estimation  Pose  Relation  Attention  PDF
• 2021-09-16 Regularized Training of Nearest Neighbor Language Models    Jean-Francois Ton, Walter Talbott, Shuangfei Zhai, Josh Susskind arXiv_CL arXiv_CL  Transformer  Regularization  Knowledge  Classification  Inference  Language_Model  PDF
• 2021-09-16 Fast-Slow Transformer for Visually Grounding Speech    Puyuan Peng, David Harwath arXiv_CL arXiv_CL  Transformer  Image_Retrieval  Speech  Attention  PDF
• 2021-09-16 TANet: A new Paradigm for Global Face Super-resolution via Transformer-CNN Aggregation Network    Yuanzhi Wang, Tao Lu, Yanduo Zhang, Junjun Jiang, Jiaming Wang, Zhongyuan Wang, Jiayi Ma arXiv_CV arXiv_CV  Transformer  Reconstruction  Facial_Landmark  Recognition  Super_Resolution  Restoration  Pose  Face  Relation  Attention  Visual_Relation  CNN  PDF
• 2021-09-16 An End-to-End Transformer Model for 3D Object Detection    Ishan Misra, Rohit Girdhar, Armand Joulin arXiv_AI arXiv_AI  Transformer  Embedding  Point_Cloud  3D  Knowledge  Pose  Detection  Object_Detection  PDF
• 2021-09-16 MeLT: Message-Level Transformer with Masked Document Representations as Pre-Training for Stance Detection    Matthew Matero, Nikita Soni, Niranjan Balasubramanian, H. Andrew Schwartz arXiv_CL arXiv_CL  Transformer  Reconstruction  Detection  Language_Model  Prediction  PDF
• 2021-09-16 Eformer: Edge Enhancement based Transformer for Medical Image Denoising    Achleshwar Luthra, Harsh Sulakhe, Tanish Mittal, Abhishek Iyer, Santosh Yadav arXiv_CV arXiv_CV  Transformer  Enhancement  Pose  Denoising  Attention  Medical  PDF
• 2021-09-16 The NiuTrans System for WNGT 2020 Efficiency Task    Chi Hu, Bei Li, Ye Lin, Yinqiao Li, Yanyang Li, Chenglong Wang, Tong Xiao, Jingbo Zhu arXiv_CL arXiv_CL  Transformer  Knowledge  NMT  Attention  Inference  PDF
• 2021-09-16 The NiuTrans System for the WMT21 Efficiency Task    Chenglong Wang, Chi Hu, Yongyu Mu, Zhongxiang Yan, Siming Wu, Minyi Hu, Hang Cao, Bei Li, Ye Lin, Tong Xiao, Jingbo Zhu arXiv_CL arXiv_CL  Transformer  Optimization  Knowledge  NMT  PDF
• 2021-09-16 KnowMAN: Weakly Supervised Multinomial Adversarial Networks    Luisa März, Ehsaneddin Asgari, Fabienne Braune, Franziska Zimmermann, Benjamin Roth arXiv_CL arXiv_CL  Transformer  Weakly_Supervised  Knowledge  Adversarial  Pose  Language_Model  PDF
• 2021-09-16 Translation Transformers Rediscover Inherent Data Domains    Maksym Del, Elizaveta Korotkova, Mark Fishel arXiv_CL arXiv_CL  Transformer  Unsupervised  Pose  NMT  Language_Model  PDF
• 2021-09-16 Label-Attention Transformer with Geometrically Coherent Objects for Image Captioning    Shikha Dubey, Farrukh Olimov, Muhammad Aasim Rafique, Joonmo Kim, Moongu Jeon arXiv_AI arXiv_AI  Image_Caption  Transformer  Pose  Quantitative  Relation  Attention  Caption  PDF
• 2021-09-16 Utterance-level neural confidence measure for end-to-end children speech recognition    Wei Liu, Tan Lee arXiv_SD arXiv_SD  Transformer  Recognition  Speech  Classification  Attention  Speech_Recognition  Prediction  PDF
• 2021-09-16 Scaling Laws for Neural Machine Translation    Behrooz Ghorbani, Orhan Firat, Markus Freitag, Ankur Bapna, Maxim Krikun, Xavier Garcia, Ciprian Chelba, Colin Cherry arXiv_AI arXiv_AI  Transformer  Pose  NMT  Relation  Prediction  Recommendation  PDF
• 2021-09-15 Pose Transformers : Human Motion Prediction with Non-Autoregressive Transformers    Angel Martínez-González, Michael Villamizar, Jean-Marc Odobez arXiv_CV arXiv_CV  Transformer  3D  RNN  Pose  Classification  Activity  Prediction  PDF
• 2021-09-15 Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering    Youngjoong Kwon, Dahun Kim, Duygu Ceylan, Henry Fuchs arXiv_CV arXiv_CV  Transformer  Sparse  Pose  Attention  PDF
• 2021-09-15 Discriminative and Generative Transformer-based Models For Situation Entity Classification    Mehdi Rezaee, Kasra Darvish, Gaoussou Youssouf Kebe, Francis Ferraro arXiv_AI arXiv_AI  Transformer  RNN  Pose  Face  Classification  Prediction  PDF
• 2021-09-15 SupCL-Seq: Supervised Contrastive Learning for Downstream Optimized Sequence Representations    Hooman Sedghamiz, Shivam Raval, Enrico Santus, Tuka Alhanai, Mohammad Ghassemi arXiv_CL arXiv_CL  Transformer  Bert  Optimization  Self-Supervised  Contrastive_Learning  Classification  Language_Model  PDF
• 2021-09-15 Matching with Transformers in MELT    Sven Hertling, Jan Portisch, Heiko Paulheim arXiv_AI arXiv_AI  Transformer  Knowledge  Knowledge_Graph  Ontology  Classification  Language_Model  Matching  PDF
• 2021-09-15 Topic Transferable Table Question Answering    Saneem Ahmed Chemmengath, Vishwajeet Kumar, Samarth Bharadwaj, Jaydeep Sen, Mustafa Canim, Soumen Chakrabarti, Alfio Gliozzo, Karthik Sankaranarayanan arXiv_AI arXiv_AI  Transformer  Bert  Pose  QA  PDF
• 2021-09-15 Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLU    Patrick Kahardipraja, Brielen Madureira, David Schlangen arXiv_CL arXiv_CL  Transformer  Inference  PDF
• 2021-09-15 Mi{dh}eind's WMT 2021 submission    Haukur Barri Símonarson, Vésteinn Snæbjarnarson, Pétur Orri Ragnarsson, Haukur Páll Jónsson, Vilhjálmur Þorsteinsson arXiv_CL arXiv_CL  Transformer  PDF
• 2021-09-15 Improving Streaming Transformer Based ASR Under a Framework of Self-supervised Learning    Songjun Cao, Yueteng Kang, Yanzhe Fu, Xiaoshuo Xu, Sining Sun, Yike Zhang, Long Ma arXiv_SD arXiv_SD  Transformer  Recognition  Knowledge  Speech  Self-Supervised  Pose  Speech_Recognition  PDF
• 2021-09-15 Sequence Length is a Domain: Length-based Overfitting in Transformer Models    Dušan Variš, Ondřej Bojar arXiv_CL arXiv_CL  Transformer  Regularization  PDF
• 2021-09-15 Enhancing Clinical Information Extraction with Transferred Contextual Embeddings    Zimin Wan, Chenchen Xu, Hanna Suominen arXiv_CL arXiv_CL  Transformer  Embedding  Transfer_Learning  Bert  Action  Deep_Learning  Medical  PDF
• 2021-09-15 Transformer-based Language Models for Factoid Question Answering at BioASQ9b    Urvashi Khanna, Diego Mollá arXiv_CL arXiv_CL  Transformer  Bert  Medical  Language_Model  PDF
• 2021-09-15 MISSFormer: An Effective Medical Image Segmentation Transformer    Xiaohong Huang, Zhifang Deng, Dandan Li, Xueguang Yuan arXiv_CV arXiv_CV  Transformer  Segmentation  Pose  GAN  Medical  CNN  PDF
• 2021-09-15 Learning to Match Job Candidates Using Multilingual Bi-Encoder BERT    Dor Lavi arXiv_CL arXiv_CL  Transformer  Bert  PDF
• 2021-09-15 Incorporating Residual and Normalization Layers into Analysis of Masked Language Models    Goro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, Kentaro Inui arXiv_CL arXiv_CL  Transformer  Pose  Action  Attention  Language_Model  PDF
• 2021-09-15 Anchor DETR: Query Design for Transformer-Based Detector    Yingming Wang, Xiangyu Zhang, Tong Yang, Jian Sun arXiv_CV arXiv_CV  Transformer  Embedding  Pose  Detection  Object_Detection  Attention  Prediction  PDF
• 2021-09-15 Hybrid Local-Global Transformer for Image Dehazing    Dong Zhao, Jia Li, Hongyu Li, Long Xu arXiv_CV arXiv_CV  Transformer  Pose  Prediction  PDF
• 2021-09-15 Transformer-based Lexically Constrained Headline Generation    Kosuke Yamada, Yuta Hitomi, Hideaki Tamori, Ryohei Sasano, Naoaki Okazaki, Kentaro Inui, Koichi Takeda arXiv_CL arXiv_CL  Transformer  RNN  Pose  PDF
• 2021-09-15 PnP-DETR: Towards Efficient Visual Analysis with Transformers    Tao Wang, Li Yuan, Yunpeng Chen, Jiashi Feng, Shuicheng Yan arXiv_CV arXiv_CV  Transformer  Segmentation  Recognition  Action  Detection  Object_Detection  PDF
• 2021-09-15 Seeking an Optimal Approach for Computer-Aided Pulmonary Embolism Detection    Nahid Ul Islam, Shiv Gehlot, Zongwei Zhou, Michael B Gotway, Jianming Liang arXiv_CV arXiv_CV  Transformer  Transfer_Learning  Self-Supervised  Classification  Deep_Learning  Detection  CNN  PDF
• 2021-09-14 Frequency Effects on Syntactic Rule Learning in Transformers    Jason Wei, Dan Garrette, Tal Linzen, Ellie Pavlick arXiv_CL arXiv_CL  Transformer  Bert  Inference  Language_Model  Prediction  PDF
• 2021-09-14 Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering    Siddhant Garg, Alessandro Moschitti arXiv_CL arXiv_CL  Transformer  Pose  QA  PDF
• 2021-09-14 A Three Step Training Approach with Data Augmentation for Morphological Inflection    Gabor Szolnok, Botond Barta, Dorina Lakatos, Judit Acs arXiv_AI arXiv_AI  Transformer  RNN  GAN  PDF
• 2021-09-14 NOPE: A Corpus of Naturally-Occurring Presuppositions in English    Alicia Parrish, Sebastian Schuster, Alex Warstadt, Omar Agha, Soo-Hwan Lee, Zhuoye Zhao, Samuel R. Bowman, Tal Linzen arXiv_CL arXiv_CL  Transformer  Action  Inference  PDF
• 2021-09-14 Explainable Identification of Dementia from Transcripts using Transformer Networks    Loukas Ilias, Dimitris Askounis arXiv_CL arXiv_CL  Transformer  Bert  Pose  Face  Classification  Detection  Relation  Prediction  PDF
• 2021-09-14 The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders    Han He, Jinho D. Choi arXiv_AI arXiv_AI  Transformer  Embedding  Pose  Attention  PDF
• 2021-09-14 Legal Transformer Models May Not Always Help    Sakbo Geng, Rémi Lebret, Karl Aberer arXiv_CL arXiv_CL  Transformer  Bert  Deep_Learning  Language_Model  PDF
• 2021-09-14 Evaluating Biomedical BERT Models for Vocabulary Alignment at Scale in the UMLS Metathesaurus    Goonmeet Bajaj, Vinh Nguyen, Thilini Wijesiriwardene, Hong Yung Yip, Vishesh Javangula, Srinivasan Parthasarathy, Amit Sheth, Olivier Bodenreider arXiv_CL arXiv_CL  Transformer  Embedding  Bert  RNN  Action  Medical  Prediction  PDF
• 2021-09-14 Semantic Answer Type Prediction using BERT: IAI at the ISWC SMART Task 2020    Vinay Setty, Krisztian Balog arXiv_AI arXiv_AI  Transformer  Bert  Text_Classification  Classification  Detection  Prediction  PDF
• 2021-09-14 Non-autoregressive Transformer with Unified Bidirectional Decoder for Automatic Speech Recognition    Chuan-Fei Zhang, Yan Liu, Tian-Hao Zhang, Song-Lu Chen, Feng Chen, Xu-Cheng Yin arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Pose  Attention  Speech_Recognition  PDF
• 2021-09-14 Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer    Fushun Zhu, Shan Zhao, Peng Wang, Hao Wang, Hua Yan, Shuaicheng Liu arXiv_CV arXiv_CV  Transformer  Pose  Face  Deep_Learning  PDF
• 2021-09-14 Vision Transformer for Learning Driving Policies in Complex Multi-Agent Environments    Eshagh Kargar, Ville Kyrki arXiv_AI arXiv_AI  Transformer  Reinforcement_Learning  Pose  Attention  CNN  PDF
• 2021-09-14 Space Time Recurrent Memory Network    Hung Nguyen, Fuxin Li arXiv_AI arXiv_AI  Transformer  Segmentation  Video_Prediction  Pose  Inference  Prediction  PDF
• 2021-09-14 Multi-modal Motion Prediction with Transformer-based Neural Network for Autonomous Driving    Zhiyu Huang, Xiaoyu Mo, Chen Lv arXiv_RO arXiv_RO  Transformer  Pose  Action  Relation  Attention  GAN  Autonomous  Prediction  PDF
• 2021-09-14 Structure-Enhanced Pop Music Generation via Harmony-Aware Learning    Xueyao Zhang, Jinchao Zhang, Yao Qiu, Li Wang, Jie Zhou arXiv_SD arXiv_SD  Transformer  Pose  PDF
• 2021-09-13 Evaluating Transferability of BERT Models on Uralic Languages    Judit Ács, Dániel Lévai, András Kornai arXiv_CL arXiv_CL  Transformer  Bert  Optimization  Language_Model  PDF
• 2021-09-13 KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation    Marzieh S. Tahaei, Ella Charlaix, Vahid Partovi Nia, Ali Ghodsi, Mehdi Rezagholizadeh arXiv_AI arXiv_AI  Transformer  Embedding  Bert  Knowledge  Pose  Attention  Language_Model  PDF
• 2021-09-13 CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation    Tongkun Xu, Weihua Chen, Pichao Wang, Fan Wang, Hao Li, Rong Jin arXiv_CV arXiv_CV  Transformer  Unsupervised  Knowledge  Pose  Attention  CNN  PDF
• 2021-09-13 Beyond Isolated Utterances: Conversational Emotion Recognition    Raghavendra Pappagari, Piotr Żelasko, Jesús Villalba, Laureano Moro-Velazquez, Najim Dehak arXiv_CL arXiv_CL  Transformer  Embedding  Recognition  RNN  Speech  Pose  Emotion  Attention  PDF
• 2021-09-13 On Pursuit of Designing Multi-modal Transformer for Video Grounding    Meng Cao, Long Chen, Mike Zheng Shou, Can Zhang, Yuexian Zou arXiv_CV arXiv_CV  Transformer  Embedding  Pose  Classification  Attention  Inference  Prediction  Matching  PDF
• 2021-09-13 xGQA: Cross-Lingual Visual Question Answering    Jonas Pfeiffer, Gregor Geigle, Aishwarya Kamath, Jan-Martin O. Steitz, Stefan Roth, Ivan Vulić, Iryna Gurevych arXiv_CL arXiv_CL  Transformer  Zero-Shot  Pose  VQA  Language_Model  QA  PDF
• 2021-09-13 Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions    Javier Ferrando, Marta R. Costa-jussà arXiv_AI arXiv_AI  Transformer  Pose  NMT  Attention  Prediction  PDF
• 2021-09-13 Exploring a Unified Sequence-To-Sequence Transformer for Medical Product Safety Monitoring in Social Media    Shivam Raval, Hooman Sedghamiz, Enrico Santus, Tuka Alhanai, Mohammad Ghassemi, Emmanuele Chersoni arXiv_CL arXiv_CL  Transformer  Bert  Zero-Shot  Pose  Action  Detection  Medical  PDF
• 2021-09-13 GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks    Weicheng Ma, Renze Lou, Kai Zhang, Lili Wang, Soroush Vosoughi arXiv_CL arXiv_CL  Transformer  Bert  Classification  PDF
• 2021-09-13 CPT: A Pre-Trained Unbalanced Transformerfor Both Chinese Language Understanding and Generation    Yunfan Shao, Zhichao Geng, Yitao Liu, Junqi Dai, Fei Yang, Li Zhe, Hujun Bao, Xipeng Qiu arXiv_CL arXiv_CL  Transformer  Knowledge  Pose  Denoising  Text_Generation  Inference  Language_Model  PDF
• 2021-09-13 SHAPE: Shifted Absolute Position Embedding for Transformers    Shun Kiyono, Sosuke Kobayashi, Jun Suzuki, Kentaro Inui arXiv_CL arXiv_CL  Transformer  Embedding  PDF
• 2021-09-12 Levenshtein Training for Word-level Quality Estimation    Shuoyang Ding, Marcin Junczys-Dowmunt, Matt Post, Philipp Koehn arXiv_CL arXiv_CL  Transformer  Transfer_Learning  Pose  Inference  PDF
• 2021-09-12 PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds    Xiaoxue Chen, Hao Zhao, Guyue Zhou, Ya-Qin Zhang arXiv_CV arXiv_CV  Transformer  Point_Cloud  3D  Optimization  Pose  Quantitative  Detection  Object_Detection  PDF
• 2021-09-12 Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval    Zhihao Fan, Zhongyu Wei, Zejun Li, Siyuan Wang, Haijun Shan, Xuanjing Huang, Jianqing Fan arXiv_CV arXiv_CV  Transformer  Represenation_Learning  Pose  Action  Attention  Matching  PDF
• 2021-09-12 TEASEL: A Transformer-Based Speech-Prefixed Language Model    Mehdi Arjmand, Mohammad Javad Dousti, Hadi Moradi arXiv_AI arXiv_AI  Transformer  Speech  Self-Supervised  Pose  Sentiment  Language_Model  PDF
• 2021-09-12 ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis    Kailin Li, Lixin Yang, Xinyu Zhan, Jun Lv, Wenqiang Xu, Jiefeng Li, Cewu Lu arXiv_AI arXiv_AI  Transformer  3D  Pose_Estimation  Pose  PDF
• 2021-09-12 Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration    Chuanxin Tang, Chong Luo, Zhiyuan Zhao, Dacheng Yin, Yucheng Zhao, Wenjun Zeng arXiv_AI arXiv_AI  Transformer  Embedding  Zero-Shot  Speech  Pose  Prediction  PDF
• 2021-09-12 Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?    Chuanxin Tang, Yucheng Zhao, Guangting Wang, Chong Luo, Wenxuan Xie, Wenjun Zeng arXiv_CV arXiv_CV  Transformer  Recognition  Sparse  Pose  Attention  PDF
• 2021-09-12 Guiding Topic Flows in the Generative Chatbot by Enhancing the ConceptNet with the Conversation Corpora    Pengda Si, Yao Qiu, Jinchao Zhang, Yujiu Yang arXiv_AI arXiv_AI  Transformer  Knowledge  Knowledge_Graph  Pose  Relation  QA  PDF
• 2021-09-11 The Impact of Positional Encodings on Multilingual Compression    Vinit Ravishankar, Anders Søgaard arXiv_CL arXiv_CL  Transformer  Embedding  Bert  Knowledge  Pose  Attention  Language_Model  PDF
• 2021-09-11 HYDRA -- Hyper Dependency Representation Attentions    Ha-Thanh Nguyen, Vu Tran, Tran-Binh Dang, Minh-Quan Bui, Minh-Phuong Nguyen, Le-Minh Nguyen arXiv_CL arXiv_CL  Transformer  Unsupervised  Knowledge  Pose  Attention  PDF
• 2021-09-11 BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation    Naina Dhingra, Florian Ritter, Andreas Kunz arXiv_AI arXiv_AI  Transformer  Pose  Detection  Relation  Visual_Relation  Prediction  PDF
• 2021-09-11 Multilingual Translation via Grafting Pre-trained Language Models    Zewei Sun, Mingxuan Wang, Lei Li arXiv_CL arXiv_CL  Transformer  Bert  Self-Supervised  Pose  Attention  Language_Model  PDF
• 2021-09-11 Bornon: Bengali Image Captioning with Transformer-based Deep learning approach    Faisal Muhammad Shah, Mayeesha Humaira, Md Abidur Rahman Khan Jim, Amit Saha Ami, Shimul Paul arXiv_CV arXiv_CV  Image_Caption  Transformer  RNN  Deep_Learning  Attention  Caption  PDF
• 2021-09-11 Empirical Analysis of Training Strategies of Transformer-based Japanese Chit-chat Systems    Hiroaki Sugiyama, Masahiro Mizukami, Tsunehiro Arimoto, Hiromi Narimatsu, Yuya Chiba, Hideharu Nakajima, Toyomi Meguro arXiv_AI arXiv_AI  Transformer  Pose  PDF
• 2021-09-11 RobustART: Benchmarking Robustness on Architecture Design and Training Techniques    Shiyu Tang, Ruihao Gong, Yan Wang, Aishan Liu, Jiakai Wang, Xinyun Chen, Fengwei Yu, Xianglong Liu, Dawn Song, Alan Yuille, Philip H.S. Torr, Dacheng Tao arXiv_CV arXiv_CV  Transformer  NAS  Adversarial  Pose  Relation  PDF
• 2021-09-11 College Student Retention Risk Analysis From Educational Database using Multi-Task Multi-Modal Neural Fusion    Mohammad Arif Ul Alam arXiv_CL arXiv_CL  Transformer  Embedding  Bert  RNN  Pose  PDF
• 2021-09-10 Remember the context! ASR slot error correction through memorization    Dhanush Bekal, Ashish Shenoy, Monica Sunkara, Sravan Bodapati, Katrin Kirchhoff arXiv_SD arXiv_SD  Transformer  Recognition  Speech  Pose  Speech_Recognition  Inference  PDF
• 2021-09-10 FBERT: A Neural Transformer for Identifying Offensive Content    Diptanu Sarkar, Marcos Zampieri, Tharindu Ranasinghe, Alexander Ororbia arXiv_AI arXiv_AI  Transformer  Bert  Speech  PDF
• 2021-09-10 PlaTe: Visually-Grounded Planning with Transformers in Procedural Tasks    Jiankai Sun, De-An Huang, Bo Lu, Yun-Hui Liu, Bolei Zhou, Animesh Garg arXiv_RO arXiv_RO  Transformer  Action  Prediction  PDF
• 2021-09-10 Block Pruning For Faster Transformers    François Lagunas, Ella Charlaix, Victor Sanh, Alexander M. Rush arXiv_CL arXiv_CL  Transformer  Bert  Classification  Attention  Inference  PDF
• 2021-09-10 RoR: Read-over-Read for Long Document Machine Reading Comprehension    Jing Zhao, Junwei Bao, Yifan Wang, Yongwei Zhou, Youzheng Wu, Xiaodong He, Bowen Zhou arXiv_CL arXiv_CL  Transformer  Bert  Pose  Prediction  QA  PDF
• 2021-09-10 Real-time multimodal image registration with partial intraoperative point-set data    Zachary M C Baum, Yipeng Hu, Dean C Barratt arXiv_CV arXiv_CV  Transformer  Unsupervised  Sparse  Action  Inference  PDF
• 2021-09-10 Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localization    Sungho Yoon, Ayoung Kim arXiv_CV arXiv_CV  Transformer  Pose  CNN  Matching  PDF
• 2021-09-10 Temporal Pyramid Transformer with Multimodal Interaction for Video Question Answering    Min Peng, Chongyang Wang, Yuan Gao, Yu Shi, Xiang-Dong Zhou arXiv_CV arXiv_CV  Transformer  Pose  Action  Attention  Inference  QA  PDF
• 2021-09-10 Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model    Kuntal Kumar Pal, Chitta Baral arXiv_AI arXiv_AI  Transformer  Transfer_Learning  Language_Model  Prediction  PDF
• 2021-09-10 Zero-Shot Dialogue State Tracking via Cross-Task Transfer    Zhaojiang Lin, Bing Liu, Andrea Madotto, Seungwhan Moon, Paul Crook, Zhenpeng Zhou, Zhiguang Wang, Zhou Yu, Eunjoon Cho, Rajen Subba, Pascale Fung arXiv_CL arXiv_CL  Transformer  Tracking  Transfer_Learning  Zero-Shot  Knowledge  Pose  Few-Shot  QA  PDF
• 2021-09-10 What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers    Boseop Kim, HyoungSeok Kim, Sang-Woo Lee, Gichang Lee, Donghyun Kwak, Dong Hyeon Jeon, Sunghyun Park, Sungju Kim, Seonhoon Kim, Dongpil Seo, Heungsub Lee, Minyoung Jeong, Sungjae Lee, Minsub Kim, Suk Hyun Ko, Seokhun Kim, Taeyong Park, Jinuk Kim, Soyoung Kang, Na-Hyeon Ryu, Kang Min Yoo, Minsuk Chang, Soobin Suh, Sookyo In, Jinseong Park, Kyungduk Kim, Hiun Kim, Jisu Jeong, Yong Goo Yeo, Donghoon Ham, Dongju Park, Min Young Lee, Jaewook Kang, Inho Kang, Jung-Woo Ha, Woomyoung Park, Nako Sung arXiv_CL arXiv_CL  Transformer  Zero-Shot  Optimization  Face  Few-Shot  Language_Model  PDF
• 2021-09-10 Query-driven Segment Selection for Ranking Long Documents    Youngwoo Kim, Razieh Rahimi, Hamed Bonab, James Allan arXiv_CL arXiv_CL  Transformer  Bert  Pose  Attention  PDF
• 2021-09-10 An Exploratory Study on Long Dialogue Summarization: What Works and What's Next    Yusen Zhang, Ansong Ni, Tao Yu, Rui Zhang, Chenguang Zhu, Budhaditya Deb, Asli Celikyilmaz, Ahmed Hassan Awadallah, Dragomir Radev arXiv_CL arXiv_CL  Transformer  Sparse  Salient  Pose  Summarization  PDF
• 2021-09-09 Graph-Based Decoding for Task Oriented Semantic Parsing    Jeremy R. Cole, Nanjiang Jiang, Panupong Pasupat, Luheng He, Peter Shaw arXiv_CL arXiv_CL  Transformer  Prediction  PDF
• 2021-09-09 Speechformer: Reducing Information Loss in Direct Speech Translation    Sara Papi, Marco Gaido, Matteo Negri, Marco Turchi arXiv_CL arXiv_CL  Transformer  Speech  Pose  Attention  PDF
• 2021-09-09 ConvMLP: Hierarchical Convolutional MLPs for Vision    Jiachen Li, Ali Hassani, Steven Walton, Humphrey Shi arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  Recognition  Pose  Detection  Object_Detection  CNN  PDF
• 2021-09-09 Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers    Stella Frank, Emanuele Bugliarello, Desmond Elliott arXiv_CV arXiv_CV  Transformer  Bert  Pose  Language_Model  Prediction  PDF
• 2021-09-09 TxT: Crossmodal End-to-End Learning with Transformers    Jan-Martin O. Steitz, Jonas Pfeiffer, Iryna Gurevych, Stefan Roth arXiv_CV arXiv_CV  Transformer  Detection  VQA  Object_Detection  QA  PDF
• 2021-09-09 All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality    William Timkey, Marten van Schijndel arXiv_CL arXiv_CL  Transformer  Embedding  Bert  Language_Model  PDF
• 2021-09-09 ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding    Xing Wu, Chaochen Gao, Liangjun Zang, Jizhong Han, Zhongyuan Wang, Songlin Hu arXiv_AI arXiv_AI  Transformer  Embedding  Unsupervised  Bert  Pose  Contrastive_Learning  Relation  Attention  PDF
• 2021-09-09 UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer    Haonan Wang, Peng Cao, Jiaqi Wang, Osmar R.Zaiane arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  Pose  Attention  Medical  PDF
• 2021-09-09 MATE: Multi-view Attention for Table Transformer Efficiency    Julian Martin Eisenschlos, Maharshi Gor, Thomas Müller, William W. Cohen arXiv_AI arXiv_AI  Transformer  Sparse  Pose  Relation  Attention  QA  PDF
• 2021-09-09 DAN: Decentralized Attention-based Neural Network to Solve the MinMax Multiple Traveling Salesman Problem    Yuhong Cao, Zhanhong Sun, Guillaume Sartoretti arXiv_AI arXiv_AI  Transformer  Reinforcement_Learning  Optimization  Attention  PDF
• 2021-09-09 Towards Transferable Adversarial Attacks on Vision Transformers    Zhipeng Wei, Jingjing Chen, Micah Goldblum, Zuxuan Wu, Tom Goldstein, Yu-Gang Jiang arXiv_AI arXiv_AI  Transformer  Adversarial  Pose  Attention  PDF
• 2021-09-09 Lexico-semantic and affective modelling of Spanish poetry: A semi-supervised learning approach    Alberto Barbado, María Dolores González, Débora Carrera arXiv_AI arXiv_AI  Transformer  Embedding  Text_Classification  Pose  Classification  Attention  PDF
• 2021-09-09 ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization    Alireza Salemi, Emad Kebriaei, Ghazal Neisi Minaei, Azadeh Shakery arXiv_CL arXiv_CL  Transformer  Bert  Salient  Pose  Attention  Summarization  Language_Model  PDF
• 2021-09-09 A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation    Shilei Liu, Xiaofeng Zhao, Bochao Li, Feiliang Ren, Longhui Zhang, Shujuan Yin arXiv_AI arXiv_AI  Transformer  Weakly_Supervised  Knowledge  Pose  PDF
• 2021-09-09 Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems    Yicheng Zou, Zhihua Liu, Xingwu Hu, Qi Zhang arXiv_CL arXiv_CL  Transformer  Pose  Inference  PDF
• 2021-09-09 BeamTransformer: Microphone Array-based Overlapping Speech Detection    Siqi Zheng, Shiliang Zhang, Weilong Huang, Qian Chen, Hongbin Suo, Ming Lei, Jinwei Feng, Zhijie Yan arXiv_AI arXiv_AI  Transformer  Optimization  Speech  Pose  Detection  Relation  Prediction  PDF
• 2021-09-09 Graphine: A Dataset for Graph-aware Terminology Definition Generation    Zequn Liu, Shukai Wang, Yiyang Gu, Ruiyi Zhang, Ming Zhang, Sheng Wang arXiv_CL arXiv_CL  Transformer  Represenation_Learning  Pose  Text_Generation  Medical  Language_Model  PDF
• 2021-09-08 TrAISformer-A generative transformer for AIS trajectory prediction    Duong Nguyen, Ronan Fablet arXiv_AI arXiv_AI  Transformer  Embedding  Classification  Deep_Learning  Relation  Prediction  PDF
• 2021-09-08 What's Hidden in a One-layer Randomly Weighted Transformer?    Sheng Shen, Zhewei Yao, Douwe Kiela, Kurt Keutzer, Michael W. Mahoney arXiv_AI arXiv_AI  Transformer  Embedding  PDF
• 2021-09-08 Transformers in the loop: Polarity in neural models of language    Lisa Bylinina, Alexey Tikhonov arXiv_CL arXiv_CL  Transformer  Bert  Pose  Language_Model  Prediction  PDF
• 2021-09-08 ELIT: Emory Language and Information Toolkit    Han He, Liyan Xu, Jinho D. Choi arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Inference  PDF
• 2021-09-08 Retrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Models    Steven Y. Feng, Kevin Lu, Zhuofu Tao, Malihe Alikhani, Teruko Mitamura, Eduard Hovy, Varun Gangal arXiv_AI arXiv_AI  Transformer  Text_Generation  Caption  PDF
• 2021-09-08 Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems    Potsawee Manakul, Mark J. F. Gales arXiv_CL arXiv_CL  Transformer  Sparse  Pose  Attention  Summarization  Inference  PDF
• 2021-09-08 Panoptic SegFormer    Zhiqi Li, Wenhai Wang, Enze Xie, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, Tong Lu, Ping Luo arXiv_CV arXiv_CV  Transformer  Segmentation  Pose  Prediction  PDF
• 2021-09-08 Scaled ReLU Matters for Training Vision Transformers    Pichao Wang, Xue Wang, Hao Luo, Jingkai Zhou, Zhipeng Zhou, Fan Wang, Hao Li, Rong Jin arXiv_CV arXiv_CV  Transformer  Pose  CNN  PDF
• 2021-09-08 Axial multi-layer perceptron architecture for automatic segmentation of choroid plexus in multiple sclerosis    Marius Schmidt-Mengin, Vito A.G. Ricigliano, Benedetta Bodini, Emanuele Morena, Annalisa Colombi, Mariem Hamzaoui, Arya Yazdan Panah, Bruno Stankoff, Olivier Colliot arXiv_CV arXiv_CV  Transformer  Segmentation  3D  Knowledge  Pose  Deep_Learning  Attention  CNN  PDF
• 2021-09-08 Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories    David Wilmot, Frank Keller arXiv_AI arXiv_AI  Transformer  Unsupervised  Knowledge  Detection  Language_Model  PDF
• 2021-09-08 Biomedical and Clinical Language Models for Spanish: On the Benefits of Domain-Specific Pretraining in a Mid-Resource Scenario    Casimiro Pio Carrino, Jordi Armengol-Estapé, Asier Gutiérrez-Fandiño, Joan Llop-Palao, Marc Pàmies, Aitor Gonzalez-Agirre, Marta Villegas arXiv_CL arXiv_CL  Transformer  Recognition  Bert  Knowledge  Medical  Language_Model  PDF
• 2021-09-08 Cross-lingual Offensive Language Identification for Low Resource Languages: The Case of Marathi    Saurabh Gaikwad, Tharindu Ranasinghe, Marcos Zampieri, Christopher M. Homan arXiv_AI arXiv_AI  Transformer  Transfer_Learning  PDF
• 2021-09-08 Pose-guided Inter- and Intra-part Relational Transformer for Occluded Person Re-Identification    Zhongxing Ma, Yifan Zhao, Jia Li arXiv_CV arXiv_CV  Transformer  Surveillance  Person_Re-identification  Pose  Action  Relation  Re-identification  Matching  PDF
• 2021-09-07 Text-Free Prosody-Aware Generative Spoken Language Modeling    Eugene Kharitonov, Ann Lee, Adam Polyak, Yossi Adi, Jade Copet, Kushal Lakhotia, Tu-Anh Nguyen, Morgane Rivière, Abdelrahman Mohamed, Emmanuel Dupoux, Wei-Ning Hsu arXiv_CL arXiv_CL  Transformer  Speech  Pose  Classification  GAN  Language_Model  PDF
• 2021-09-07 Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos    Chinedu Innocent Nwoye, Tong Yu, Cristians Gonzalez, Barbara Seeliger, Pietro Mascagni, Didier Mutter, Jacques Marescaux, Nicolas Padoy arXiv_CV arXiv_CV  Transformer  Recognition  Pose  Action  Relation  Attention  Prediction  PDF
• 2021-09-07 nnFormer: Interleaved Transformer for Volumetric Segmentation    Hong-Yu Zhou, Jiansen Guo, Yinghao Zhang, Lequan Yu, Liansheng Wang, Yizhou Yu arXiv_CV arXiv_CV  Transformer  Segmentation  3D  Pose  Attention  Medical  CNN  PDF
• 2021-09-07 How much pretraining data do language models need to learn syntax?    Laura Pérez-Mayos, Miguel Ballesteros, Leo Wanner arXiv_CL arXiv_CL  Transformer  Bert  Knowledge  Speech  Language_Model  PDF
• 2021-09-07 Sequential Diagnosis Prediction with Transformer and Ontological Representation    Xueping Peng, Guodong Long, Tao Shen, Sen Wang, Jing Jiang arXiv_AI arXiv_AI  Transformer  Embedding  Pose  Ontology  Action  Medical  Prediction  PDF
• 2021-09-07 Revisiting Context Choices for Context-aware Machine Translation    Matīss Rikters, Toshiaki Nakazawa arXiv_CL arXiv_CL  Transformer  PDF
• 2021-09-07 FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting    Rui Liu, Hanming Deng, Yangyi Huang, Xiaoyu Shi, Lewei Lu, Wenxiu Sun, Xiaogang Wang, Jifeng Dai, Hongsheng Li arXiv_CV arXiv_CV  Transformer  Inpainting  Pose  Action  Quantitative  Relation  PDF
• 2021-09-07 FH-SWF SG at GermEval 2021: Using Transformer-Based Language Models to Identify Toxic, Engaging, & Fact-Claiming Comments    Christian Gawron, Sebastian Schmidt arXiv_CL arXiv_CL  Transformer  Face  Language_Model  Prediction  PDF
• 2021-09-07 GCsT: Graph Convolutional Skeleton Transformer for Action Recognition    Ruwen Bai, Min Li, Bo Meng, Fengfa Li, Junxing Ren, Miao Jiang, Degang Sun arXiv_AI arXiv_AI  Transformer  Recognition  Pose  Action_Recognition  Action  Relation  Attention  CNN  PDF
• 2021-09-07 A Scalable AI Approach for Clinical Trial Cohort Optimization    Xiong Liu, Cheng Shi, Uday Deore, Yingbo Wang, Myah Tran, Iya Khalil, Murthy Devarakonda arXiv_AI arXiv_AI  Transformer  Optimization  Pose  PDF
• 2021-09-07 Puzzle Solving without Search or Human Knowledge: An Unnatural Language Approach    David Noever, Ryerson Burdick arXiv_AI arXiv_AI  Transformer  Sparse  Knowledge  PDF
• 2021-09-07 Mixed Attention Transformer for LeveragingWord-Level Knowledge to Neural Cross-Lingual Information Retrieval    Zhiqi Huang, Hamed Bonab, Sheikh Muhammad Sarwar, Razieh Rahimi, James Allan arXiv_CL arXiv_CL  Transformer  Knowledge  Pose  Attention  PDF
• 2021-09-06 Training Deep Networks from Zero to Hero: avoiding pitfalls and going beyond    Moacir Antonelli Ponti, Fernando Pereira dos Santos, Leo Sampaio Ferraz Ribeiro, Gabriel Biscaro Cavallari arXiv_CV arXiv_CV  Transformer  Transfer_Learning  Optimization  Self-Supervised  CNN  PDF
• 2021-09-06 Vision Transformers For Weeds and Crops Classification Of High Resolution UAV Images    Reenul Reedha, Eric Dericquebourg, Raphael Canals, Adel Hafiane arXiv_CV arXiv_CV  Transformer  Recognition  Face  Classification  Deep_Learning  Attention  CNN  Image_Classification  PDF
• 2021-09-06 The Animation Transformer: Visual Correspondence via Segment Matching    Evan Casey, Víctor Pérez, Zhuoru Li, Harry Teitelman, Nick Boyajian, Tim Pulver, Mike Manh, William Grisaitis arXiv_AI arXiv_AI  Transformer  Pose  Relation  Visual_Relation  Matching  PDF
• 2021-09-06 Enhancing Language Models with Plug-and-Play Large-Scale Commonsense    Wanyun Cui, Xingran Chen arXiv_CL arXiv_CL  Transformer  Embedding  Bert  Represenation_Learning  Knowledge  Knowledge_Graph  Pose  Language_Model  PDF
• 2021-09-06 3D Human Texture Estimation from a Single Image with Transformers    Xiangyu Xu, Chen Change Loy arXiv_AI arXiv_AI  Transformer  3D  Pose  Quantitative  CNN  PDF
• 2021-09-06 GPT-3 Models are Poor Few-Shot Learners in the Biomedical Domain    Milad Moradi, Kathrin Blagec, Florian Haberl, Matthias Samwald arXiv_AI arXiv_AI  Transformer  Transfer_Learning  Bert  Knowledge  Few-Shot  Medical  Language_Model  PDF
• 2021-09-06 Voxel Transformer for 3D Object Detection    Jiageng Mao, Yujing Xue, Minzhe Niu, Haoyue Bai, Jiashi Feng, Xiaodan Liang, Hang Xu, Chunjing Xu arXiv_CV arXiv_CV  Transformer  Recognition  Point_Cloud  3D  Sparse  Pose  Detection  Relation  Object_Detection  Attention  CNN  PDF
• 2021-09-06 Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction    Bo Wang, Tao Shen, Guodong Long, Tianyi Zhou, Yi Chang arXiv_CL arXiv_CL  Transformer  Embedding  Unsupervised  Sentiment_Classification  Represenation_Learning  Adversarial  Pose  Action  Classification  Sentiment  PDF
• 2021-09-06 PermuteFormer: Efficient Relative Position Encoding for Long Sequences    Peng Chen arXiv_CL arXiv_CL  Transformer  Pose  Attention  Language_Model  PDF
• 2021-09-06 Improved RAMEN: Towards Domain Generalization for Visual Question Answering    Bhanuka Manesha Samarasekara Vitharana Gamage, Lim Chern Hong arXiv_CV arXiv_CV  Transformer  VQA  QA  PDF
• 2021-09-06 CTRL-C: Camera calibration TRansformer with Line-Classification    Jinwoo Lee, Hyunsung Go, Hyunjoon Lee, Sunghyun Cho, Minhyuk Sung, Junho Kim arXiv_CV arXiv_CV  Transformer  Pose  Classification  PDF
• 2021-09-06 Learning to Generate Scene Graph from Natural Language Supervision    Yiwu Zhong, Jing Shi, Jianwei Yang, Chenliang Xu, Yin Li arXiv_CV arXiv_CV  Transformer  Recognition  Pose  Detection  Relation  Object_Detection  Caption  Prediction  PDF
• 2021-09-05 Transformer Models for Text Coherence Assessment    Tushar Abhishek, Daksh Rawat, Manish Gupta, Vasudeva Varma arXiv_CL arXiv_CL  Transformer  Pose  Deep_Learning  Relation  Summarization  Text_Generation  PDF
• 2021-09-05 Teaching Autoregressive Language Models Complex Tasks By Demonstration    Gabriel Recchia arXiv_AI arXiv_AI  Transformer  Language_Model  PDF
• 2021-09-05 Fusformer: A Transformer-based Fusion Approach for Hyperspectral Image Super-resolution    Jin-Fan Hu, Ting-Zhu Huang, Liang-Jian Deng arXiv_CV arXiv_CV  Transformer  Super_Resolution  Pose  Relation  CNN  PDF
• 2021-09-05 SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks    Wanyu Du, Yangfeng Ji arXiv_CL arXiv_CL  Transformer  Pose  Language_Model  PDF
• 2021-09-04 LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation    Mohammad Abuzar Shaikh, Zhanghexuan Ji, Dana Moukheiber, Sargur Srihari, Mingchen Gao arXiv_AI arXiv_AI  Image_Caption  Transformer  Embedding  Represenation_Learning  Self-Supervised  Pose  Attention  GAN  Caption  PDF
• 2021-09-04 Weakly Supervised Relative Spatial Reasoning for Visual Question Answering    Pratyay Banerjee, Tejas Gokhale, Yezhou Yang, Chitta Baral arXiv_CV arXiv_CV  Transformer  3D  Weakly_Supervised  Action  Classification  VQA  Few-Shot  Prediction  QA  PDF
• 2021-09-04 Audio-Visual Transformer Based Crowd Counting    Usman Sajid, Xiangyu Chen, Hasan Sajid, Taejoon Kim, Guanghui Wang arXiv_CV arXiv_CV  Transformer  Pose  Action  Attention  PDF
• 2021-09-04 Transformer Networks for Data Augmentation of Human Physical Activity Recognition    Sandeep Ramachandra, Alexander Hoelzemann, Kristof Van Laerhoven arXiv_CV arXiv_CV  Transformer  Recognition  Adversarial  Classification  Attention  GAN  Activity  PDF
• 2021-09-04 Error Detection in Large-Scale Natural Language Understanding Systems Using Transformer Models    Rakesh Chada, Pradeep Natarajan, Darshan Fofadiya, Prathap Ramachandra arXiv_AI arXiv_AI  Transformer  Recognition  Bert  RNN  Classification  Detection  PDF
• 2021-09-03 IMG2SMI: Translating Molecular Structure Images to Simplified Molecular-input Line-entry System    Daniel Campos, Heng Ji arXiv_CV arXiv_CV  Image_Caption  Transformer  Unsupervised  Recognition  Action  Caption  Prediction  PDF
• 2021-09-03 Contextualized Embeddings based Convolutional Neural Networks for Duplicate Question Identification    Harsh Sakhrani (1), Saloni Parekh (1), Pratik Ratadiya (2) ((1) Pune Institute of Computer Technology, Maharashtra, India, (2) vCreaTek Consulting Services Pvt. Ltd., Maharashtra, India) arXiv_CL arXiv_CL  Transformer  Embedding  Pose  CNN  Inference  Prediction  PDF
• 2021-09-03 Biomedical Data-to-Text Generation via Fine-Tuning Transformers    Ruslan Yermakov, Nicholas Drago, Angelo Ziletti arXiv_CL arXiv_CL  Transformer  Text_Generation  Medical  PDF
• 2021-09-03 LG4AV: Combining Language Models and Graph Neural Networks for Author Verification    Maximilian Stubbemann, Gerd Stumme arXiv_AI arXiv_AI  Transformer  Knowledge  Knowledge_Graph  Relation  Language_Model  PDF
• 2021-09-03 Semantic Segmentation on VSPW Dataset through Aggregation of Transformer Models    Zixuan Chen, Junhong Zou, Xiaotao Wang arXiv_CV arXiv_CV  Transformer  Segmentation  Scene_Parsing  Semantic_Segmentation  Autonomous  PDF
• 2021-09-02 Multimodal Conditionality for Natural Language Generation    Michael Sollami, Aashish Jain arXiv_CL arXiv_CL  Transformer  Pose  Language_Model  PDF
• 2021-09-02 Skim-Attention: Learning to Focus via Document Layout    Laura Nguyen, Thomas Scialom, Jacopo Staiano, Benjamin Piwowarski arXiv_CL arXiv_CL  Transformer  Attention  Language_Model  PDF
• 2021-09-02 LegaLMFiT: Efficient Short Legal Text Classification with LSTM Language Model Pre-Training    Benjamin Clavié, Akshita Gheewala, Paul Briton, Marc Alphonsus, Rym Labiyaad, Francesco Piccoli arXiv_CL arXiv_CL  Transformer  Bert  Text_Classification  RNN  Classification  Language_Model  PDF
• 2021-09-02 CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation    Yue Wang, Weishi Wang, Shafiq Joty, Steven C.H. Hoi arXiv_CL arXiv_CL  Transformer  Bert  Pose  Detection  PDF
• 2021-09-02 Interactively Generating Explanations for Transformer-based Language Models    Patrick Schramowski, Felix Friedrich, Christopher Tauchmann, Kristian Kersting arXiv_AI arXiv_AI  Transformer  Knowledge  Action  Relation  Language_Model  PDF
• 2021-09-02 MemBERT: Injecting Unstructured Knowledge into BERT    Federico Ruggeri, Marco Lippi, Paolo Torroni arXiv_AI arXiv_AI  Transformer  Enhancement  Bert  Knowledge  Pose  PDF
• 2021-09-02 Multi-Modal Zero-Shot Sign Language Recognition    Razieh Rastgoo, Kourosh Kiani, Sergio Escalera, Mohammad Sabokrou arXiv_CV arXiv_CV  Transformer  Embedding  Recognition  3D  Bert  Zero-Shot  RNN  Pose  Action  Detection  PDF
• 2021-09-02 Controllable deep melody generation via hierarchical music structure representation    Shuqi Dai, Zeyu Jin, Celso Gomes, Roger B. Dannenberg arXiv_AI arXiv_AI  Transformer  Knowledge  Pose  Deep_Learning  Contour  GAN  PDF
• 2021-09-01 Searching for Efficient Multi-Stage Vision Transformers    Yi-Lun Liao, Sertac Karaman, Vivienne Sze arXiv_CV arXiv_CV  Transformer  NAS  Pose  CNN  PDF
• 2021-09-01 WebQA: Multihop and Multimodal QA    Yingshan Chang, Mridu Narang, Hisami Suzuki, Guihong Cao, Jianfeng Gao, Yonatan Bisk arXiv_AI arXiv_AI  Transformer  Pose  QA  PDF
• 2021-09-01 Pulmonary Disease Classification Using Globally Correlated Maximum Likelihood: an Auxiliary Attention mechanism for Convolutional Neural Networks    Edward Verenich, Tobias Martin, Alvaro Velasquez, Nazar Khan, Faraz Hussain arXiv_CV arXiv_CV  Transformer  Salient  Classification  Relation  Attention  CNN  PDF
• 2021-09-01 Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction    Jeremy Reizenstein, Roman Shapovalov, Philipp Henzler, Luca Sbordone, Patrick Labatut, David Novotny arXiv_CV arXiv_CV  Transformer  Reconstruction  Point_Cloud  3D  Pose  PDF
• 2021-09-01 Stochastic Transformer Networks with Linear Competing Units: Application to end-to-end SL Translation    Andreas Voskou, Konstantinos P. Panousis, Dimitrios Kosmopoulos, Dimitris N. Metaxas, Sotirios Chatzis arXiv_CL arXiv_CL  Transformer  Inference  PDF
• 2021-09-01 TransforMesh: A Transformer Network for Longitudinal modeling of Anatomical Meshes    Ignacio Sarasua, Sebastian Polsterl, Christian Wachinger arXiv_CV arXiv_CV  Transformer  3D  Knowledge  Medical  PDF
• 2021-09-01 Boosting Search Engines with Interactive Agents    Leonard Adolphs, Benjamin Boerschinger, Christian Buck, Michelle Chen Huebscher, Massimiliano Ciaramita, Lasse Espeholt, Thomas Hofmann, Yannic Kilcher arXiv_AI arXiv_AI  Transformer  Reinforcement_Learning  Knowledge  Action  Language_Model  PDF
• 2021-09-01 Exploring deep learning methods for recognizing rare diseases and their clinical manifestations from texts    Isabel Segura-Bedmar, David Camino-Perdonas, Sara Guerrero-Aspizua arXiv_CL arXiv_CL  Transformer  Bert  RNN  Knowledge  Deep_Learning  Medical  PDF
• 2021-09-01 $infty$-former: Infinite Memory Transformer    Pedro Henrique Martins, Zita Marinho, André F. T. Martins arXiv_CL arXiv_CL  Transformer  Pose  Attention  Language_Model  PDF
• 2021-09-01 Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs    Pierre Marion, Paweł Krzysztof Nowak, Francesco Piccinno arXiv_CL arXiv_CL  Transformer  Embedding  Knowledge  Knowledge_Graph  Attention  QA  PDF
• 2021-09-01 CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations    Hang Li, Yu Kang, Tianqiao Liu, Wenbiao Ding, Zitao Liu arXiv_AI arXiv_AI  Transformer  Pose  Emotion  Classification  Sentiment  Language_Model  PDF
• 2021-08-31 MergeBERT: Program Merge Conflict Resolution via Neural Transformers    Alexey Svyatkovskiy, Todd Mytcowicz, Negar Ghorbani, Sarah Fakhoury, Elizabeth Dinella, Christian Bird, Neel Sundaresan, Shuvendu Lahiri arXiv_CL arXiv_CL  Transformer  Bert  Zero-Shot  Classification  PDF
• 2021-08-31 Sentence Bottleneck Autoencoders from Transformer Language Models    Ivan Montero, Nikolaos Pappas, Noah A. Smith arXiv_CL arXiv_CL  Transformer  Reconstruction  Style_Transfer  Represenation_Learning  Classification  Denoising  Language_Model  PDF
• 2021-08-31 Deep DNA Storage: Scalable and Robust DNA Storage via Coding Theory and Deep Learning    Daniella Bar-Lev, Itai Orr, Omer Sabary, Tuvi Etzion, Eitan Yaakobi arXiv_AI arXiv_AI  Transformer  Reconstruction  Knowledge  Pose  Deep_Learning  PDF
• 2021-08-31 Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience    George Chrysostomou, Nikolaos Aletras arXiv_CL arXiv_CL  Transformer  Bert  Salient  Attention  Prediction  PDF
• 2021-08-31 Automated Mining of Leaderboards for Empirical AI Research    Salomon Kabongo, Jennifer D'Souza, Sören Auer arXiv_AI arXiv_AI  Transformer  Bert  Knowledge  Knowledge_Graph  Face  Action  GAN  PDF
• 2021-08-31 T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP    Raymond Li (1), Wen Xiao (1), Lanjun Wang (2), Hyeju Jang (1), Giuseppe Carenini (1) ((1) University of British Columbia, (2) Huawei Cananda Technologies Co. Ltd.) arXiv_CL arXiv_CL  Transformer  Face  Attention  PDF
• 2021-08-31 AraT5: Text-to-Text Transformers for Arabic Language Understanding and Generation    El Moatez Billah Nagoudi, Muhammad Abdul-Mageed, AbdelRahim Elmadany arXiv_CL arXiv_CL  Transformer  Transfer_Learning  Bert  Pose  PDF
• 2021-08-30 On the Multilingual Capabilities of Very Large-Scale English Language Models    Jordi Armengol-Estapé, Ona de Gibert Bonet, Maite Melero arXiv_AI arXiv_AI  Transformer  Zero-Shot  Pose  Few-Shot  Language_Model  PDF
• 2021-08-30 Hire-MLP: Vision MLP via Hierarchical Rearrangement    Jianyuan Guo, Yehui Tang, Kai Han, Xinghao Chen, Han Wu, Chao Xu, Chang Xu, Yunhe Wang arXiv_CV arXiv_CV  Transformer  Pose  Inference  PDF
• 2021-08-30 The effects of data size on Automated Essay Scoring engines    Christopher Ormerod, Amir Jafari, Susan Lottridge, Milan Patel, Amy Harris, Paul van Wamelen arXiv_AI arXiv_AI  Transformer  Classification  Language_Model  PDF
• 2021-08-30 From General to Specific: Informative Scene Graph Generation via Balance Adjustment    Yuyu Guo, Lianli Gao, Xuanhan Wang, Yuxuan Hu, Xing Xu, Xu Lu, Heng Tao Shen, Jingkuan Song arXiv_CV arXiv_CV  Transformer  Pose  Relation  Visual_Relation  PDF
• 2021-08-30 Shatter: An Efficient Transformer Encoder with Single-Headed Self-Attention and Relative Sequence Partitioning    Ran Tian, Joshua Maynez, Ankur P. Parikh arXiv_CL arXiv_CL  Transformer  Bert  Attention  PDF
• 2021-08-30 Exploring and Improving Mobile Level Vision Transformers    Pengguang Chen, Yixin Chen, Shu Liu, Mingchang Yang, Jiaya Jia arXiv_CV arXiv_CV  Transformer  Embedding  Pose  Attention  PDF
• 2021-08-30 A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP    Yucheng Zhao, Guangting Wang, Chuanxin Tang, Chong Luo, Wenjun Zeng, Zheng-Jun Zha arXiv_CV arXiv_CV  Transformer  Pose  Classification  CNN  PDF
• 2021-08-30 Scheduled Sampling Based on Decoding Steps for Neural Machine Translation    Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu, Jie Zhou arXiv_CL arXiv_CL  Transformer  Pose  Summarization  Inference  PDF
• 2021-08-30 Multi-Channel Transformer Transducer for Speech Recognition    Feng-Ju Chang, Martin Radfar, Athanasios Mouchtaris, Maurizio Omologo arXiv_SD arXiv_SD  Transformer  Recognition  Speech  Pose  Attention  Speech_Recognition  Inference  PDF
• 2021-08-29 Investigations on Speech Recognition Systems for Low-Resource Dialectal Arabic-English Code-Switching Speech    Injy Hamed, Pavel Denisov, Chia-Yu Li, Mohamed Elmahdy, Slim Abdennadher, Ngoc Thang Vu arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Pose  Speech_Recognition  PDF
• 2021-08-29 TCCT: Tightly-Coupled Convolutional Transformer on Time Series Forecasting    Li Shen, Yangzhu Wang arXiv_AI arXiv_AI  Transformer  Pose  Attention  CNN  Prediction  PDF
• 2021-08-28 GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer    Shuaicheng Li, Qianggang Cao, Lingbo Liu, Kunlin Yang, Shinan Liu, Jun Hou, Shuai Yi arXiv_CV arXiv_CV  Transformer  Recognition  Pose  Action  Attention  Activity  PDF
• 2021-08-28 Towards Fine-grained Image Classification with Generative Adversarial Networks and Facial Landmark Detection    Mahdi Darvish, Mahsa Pouramini, Hamid Bahador arXiv_CV arXiv_CV  Transformer  Facial_Landmark  Adversarial  Pose  Classification  Detection  GAN  Image_Classification  PDF
• 2021-08-28 On the Significance of Question Encoder Sequence Model in the Out-of-Distribution Performance in Visual Question Answering    Gouthaman KV, Anurag Mittal arXiv_CV arXiv_CV  Transformer  RNN  Pose  Relation  VQA  Attention  QA  PDF
• 2021-08-28 AMMASurv: Asymmetrical Multi-Modal Attention for Accurate Survival Analysis with Whole Slide Images and Gene Expression Data    Ruoqi Wang, Ziwang Huang, Haitao Wang, Hejun Wu arXiv_AI arXiv_AI  Transformer  Pose  Attention  Prediction  PDF
• 2021-08-27 Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation    Ofir Press, Noah A. Smith, Mike Lewis arXiv_CL arXiv_CL  Transformer  Embedding  Attention  Inference  PDF
• 2021-08-27 A Web Scale Entity Extraction System    Xuanting Cai, Quanbin Ma, Pan Li, Jianyu Liu, Qi Zeng, Zhengkan Yang, Pushkar Tripathi arXiv_AI arXiv_AI  Transformer  Action  PDF
• 2021-08-27 Tree Decomposition Attention for AMR-to-Text Generation    Lisa Jin, Daniel Gildea arXiv_CL arXiv_CL  Transformer  Pose  Attention  Text_Generation  Prediction  PDF
• 2021-08-27 Lyra: A Benchmark for Turducken-Style Code Generation    Qingyuan Liang, Zeyu Sun, Qihao Zhu, Wenjie Zhang, Lian Yu, Yingfei Xiong, Lu Zhang arXiv_AI arXiv_AI  Transformer  Knowledge  Matching  PDF
• 2021-08-27 Automated Generation of Accurate & Fluent Medical X-ray Reports    Hoang T.N. Nguyen, Dong Nie, Taivanbat Badamdorj, Yujie Liu, Yingying Zhu, Jason Truong, Li Cheng arXiv_CL arXiv_CL  Transformer  Embedding  Classification  Medical  PDF
• 2021-08-26 Semantic-based Self-Critical Training For Question Generation    Loïc, Kwate Dassi arXiv_AI arXiv_AI  Transformer  Reinforcement_Learning  Bert  Relation  Text_Generation  Language_Model  PDF
• 2021-08-26 Evaluating Transformer based Semantic Segmentation Networks for Pathological Image Segmentation    Cam Nguyen, Zuhayr Asad, Yuankai Huo arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  Quantitative  Deep_Learning  CNN  PDF
• 2021-08-26 Enhanced Seq2Seq Autoencoder via Contrastive Learning for Abstractive Text Summarization    Chujie Zheng, Kunpeng Zhang, Harry Jiannan Wang, Ling Fan, Zhe Wang arXiv_CL arXiv_CL  Transformer  Self-Supervised  Contrastive_Learning  Denoising  Summarization  PDF