Transformer

Transformer

• 2021-05-17 Pay Attention to MLPs    Hanxiao Liu, Zihang Dai, David R. So, Quoc V. Le arXiv_CV arXiv_CV  Transformer  Bert  Pose  Deep_Learning  Attention  PDF
• 2021-05-17 Supporting Context Monotonicity Abstractions in Neural NLI Models    Julia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan, Marco Valentino, André Freitas arXiv_CL arXiv_CL  Transformer  Action  Classification  Relation  PDF
• 2021-05-17 TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning    Lu Wang, Xiaofu Chang, Shuang Li, Yunfei Chu, Hui Li, Wei Zhang, Xiaofeng He, Le Song, Jingren Zhou, Hongxia Yang arXiv_AI arXiv_AI  Transformer  Represenation_Learning  Knowledge  Pose  Contrastive_Learning  Action  Attention  Prediction  Recommendation  PDF
• 2021-05-17 Rethinking the Design Principles of Robust Vision Transformer    Xiaofeng Mao, Gege Qi, Yuefeng Chen, Xiaodan Li, Shaokai Ye, Yuan He, Hui Xue arXiv_CV arXiv_CV  Transformer  Sketch  Pose  Attention  CNN  PDF
• 2021-05-17 SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising    Kuan Xuan, Yongbo Wang, Yongliang Wang, Zujie Wen, Yang Dong arXiv_CL arXiv_CL  Transformer  Pose  Denoising  PDF
• 2021-05-17 A Fine-Grained Visual Attention Approach for Fingerspelling Recognition in the Wild    Kamala Gajurel, Cuncong Zhong, Guanghui Wang arXiv_CV arXiv_CV  Transformer  Recognition  Gesture  Pose  Classification  Attention  Optical_Flow  Prediction  PDF
• 2021-05-17 Vision Transformers are Robust Learners    Sayak Paul, Pin-Yu Chen arXiv_CV arXiv_CV  Transformer  Adversarial  Pose  Quantitative  Classification  Attention  CNN  PDF
• 2021-05-17 Exploring Self-Supervised Representation Ensembles for COVID-19 Cough Classification    Hao Xue, Flora D. Salim arXiv_SD arXiv_SD  Transformer  Self-Supervised  Pose  Classification  Deep_Learning  Medical  PDF
• 2021-05-16 Doc2Dict: Information Extraction as Text Generation    Benjamin Townsend, Eamon Ito-Fisher, Lily Zhang, Madison May arXiv_AI arXiv_AI  Transformer  Action  Text_Generation  Language_Model  PDF
• 2021-05-16 How is BERT surprised? Layerwise detection of linguistic anomalies    Bai Li, Zining Zhu, Guillaume Thomas, Yang Xu, Frank Rudzicz arXiv_CL arXiv_CL  Transformer  Bert  Detection  Relation  Language_Model  PDF
• 2021-05-16 Is Image Size Important? A Robustness Comparison of Deep Learning Methods for Multi-scale Cell Image Classification Tasks: from Convolutional Neural Networks to Visual Transformers    Wanli Liu, Chen Li, Hongzan Sun, Weiming Hu, Haoyuan Chen, Changhao Sun, Marcin Grzegorzek arXiv_CV arXiv_CV  Transformer  Classification  Deep_Learning  Medical  CNN  Image_Classification  PDF
• 2021-05-15 Rethinking Skip Connection with Layer Normalization in Transformers and ResNets    Fenglin Liu, Xuancheng Ren, Zhiyuan Zhang, Xu Sun, Yuexian Zou arXiv_CV arXiv_CV  Transformer  Optimization  Pose  Classification  Image_Classification  PDF
• 2021-05-15 Are Convolutional Neural Networks or Transformers more like human vision?    Shikhar Tuli, Ishita Dasgupta, Erin Grant, Thomas L. Griffiths arXiv_CV arXiv_CV  Transformer  Recognition  Pose  Attention  CNN  PDF
• 2021-05-14 BERT Busters: Outlier LayerNorm Dimensions that Disrupt BERT    Olga Kovaleva, Saurabh Kulshreshtha, Anna Rogers, Anna Rumshisky arXiv_CL arXiv_CL  Transformer  Bert  PDF
• 2021-05-14 A Frequency Domain Constraint for Synthetic X-ray Image Super Resolution    Qing Ma, Jae Chul Koh, WonSook Lee arXiv_CV arXiv_CV  Transformer  Super_Resolution  Knowledge  Pose  PDF
• 2021-05-14 Classifying Long Clinical Documents with Pre-trained Transformers    Xin Su, Timothy Miller, Xiyu Ding, Majid Afshar, Dmitriy Dligach arXiv_CL arXiv_CL  Transformer  Bert  Language_Model  PDF
• 2021-05-14 Dynamic Multi-Branch Layers for On-Device Neural Machine Translation    Zhixing Tan, Maosong Sun, Yang Liu arXiv_CL arXiv_CL  Transformer  Pose  NMT  Inference  PDF
• 2021-05-14 Streaming Transformer for Hardware Efficient Voice Trigger Detection and False Trigger Mitigation    Vineet Garg, Wonil Chang, Siddharth Sigtia, Saurabh Adya, Pramod Simha, Pranay Dighe, Chandra Dhir arXiv_SD arXiv_SD  Transformer  Recognition  Speech  Pose  Detection  Speech_Recognition  Inference  PDF
• 2021-05-13 Not All Memories are Created Equal: Learning to Forget by Expiring    Sainbayar Sukhbaatar, Da Ju, Spencer Poff, Stephen Roller, Arthur Szlam, Jason Weston, Angela Fan arXiv_AI arXiv_AI  Transformer  Reinforcement_Learning  Pose  Attention  Language_Model  PDF
• 2021-05-13 High-Resolution Complex Scene Synthesis with Transformers    Manuel Jahn, Robin Rombach, Björn Ommer arXiv_CV arXiv_CV  Image_Caption  Transformer  Adversarial  PDF
• 2021-05-13 Episodic Transformer for Vision-and-Language Navigation    Alexander Pashevich, Cordelia Schmid, Chen Sun arXiv_AI arXiv_AI  Transformer  Pose  Action  PDF
• 2021-05-12 Spelling Correction with Denoising Transformer    Alex Kuznetsov, Hector Urdiales arXiv_AI arXiv_AI  Transformer  Denoising  PDF
• 2021-05-12 Building a Question and Answer System for News Domain    Sandipan Basu, Aravind Gaddala, Pooja Chetan, Garima Tiwari, Narayana Darapaneni, Sadwik Parvathaneni, Anwesh Reddy Paduri arXiv_AI arXiv_AI  Transformer  Embedding  Transfer_Learning  Bert  RNN  Attention  PDF
• 2021-05-12 Segmenter: Transformer for Semantic Segmentation    Robin Strudel, Ricardo Garcia, Ivan Laptev, Cordelia Schmid arXiv_AI arXiv_AI  Transformer  Segmentation  Embedding  Semantic_Segmentation  Classification  Image_Classification  PDF
• 2021-05-12 Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation    Hu Cao, Yueyue Wang, Joy Chen, Dongsheng Jiang, Xiaopeng Zhang, Qi Tian, Manning Wang arXiv_CV arXiv_CV  Transformer  Segmentation  Pose  Action  GAN  Medical  CNN  PDF
• 2021-05-12 OCHADAI-KYODAI at SemEval-2021 Task 1: Enhancing ModelGeneralization and Robustness for Lexical Complexity Prediction    Yuki Taya, Lis Kanashiro Pereira, Fei Cheng, Ichiro Kobayashi arXiv_CL arXiv_CL  Transformer  Bert  Adversarial  Pose  Prediction  PDF
• 2021-05-12 A Large-Scale Benchmark for Food Image Segmentation    Xiongwei Wu, Xin Fu, Ying Liu, Ee-Peng Lim, Steven C.H. Hoi, Qianru Sun arXiv_CV arXiv_CV  Image_Caption  Transformer  Segmentation  Semantic_Segmentation  Knowledge  Pose  PDF
• 2021-05-12 News Headline Grouping as a Challenging NLU Task    Philippe Laban, Lucas Bandarkar, Marti A. Hearst arXiv_CL arXiv_CL  Transformer  Unsupervised  Pose  Prediction  PDF
• 2021-05-11 BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?    Asahi Ushio, Luis Espinosa-Anke, Steven Schockaert, Jose Camacho-Collados arXiv_CL arXiv_CL  Transformer  Embedding  Unsupervised  Bert  Knowledge  Relation  Attention  Language_Model  PDF
• 2021-05-11 Role of Artificial Intelligence in Detection of Hateful Speech for Hinglish Data on Social Media    Ananya Srivastava, Mohammed Hasan, Bhargav Yagnik, Rahee Walambe, Ketan Kotecha arXiv_CL arXiv_CL  Transformer  Embedding  Bert  Speech  Pose  Detection  Language_Model  PDF
• 2021-05-11 Benchmarking down-scaled pre-trained language models    M. Aßenmacher, P. Schulze, C. Heumann arXiv_CL arXiv_CL  Transformer  Bert  Language_Model  PDF
• 2021-05-11 Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation    Shun-Po Chuang, Yung-Sung Chuang, Chih-Chiang Chang, Hung-yi Lee arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Quantitative  Classification  Speech_Recognition  PDF
• 2021-05-11 EL-Attention: Memory Efficient Lossless Attention for Generation    Yu Yan, Jiusheng Chen, Weizhen Qi, Nikhil Bhendawade, Yeyun Gong, Nan Duan, Ruofei Zhang arXiv_CL arXiv_CL  Transformer  Pose  Attention  Summarization  Inference  PDF
• 2021-05-10 Assessing the Syntactic Capabilities of Transformer-based Multilingual Language Models    Laura Pérez-Mayos, Alba Táboas García, Simon Mille, Leo Wanner arXiv_CL arXiv_CL  Transformer  Bert  Optimization  Language_Model  PDF
• 2021-05-10 R2D2: Relational Text Decoding with Transformers    Aryan Arbabi, Mingqiu Wang, Laurent El Shafey, Nan Du, Izhak Shafran arXiv_CL arXiv_CL  Transformer  Bert  Pose  Action  Relation  Attention  Text_Generation  Medical  PDF
• 2021-05-10 Local Frequency Domain Transformer Networks for Video Prediction    Hafez Farazi, Jan Nogga, Sven Behnke arXiv_CV arXiv_CV  Transformer  Segmentation  Unsupervised  RNN  Video_Prediction  Pose  Deep_Learning  Prediction  PDF
• 2021-05-10 Language Acquisition is Embodied, Interactive, Emotive: a Research Proposal    Casey Kennington arXiv_CL arXiv_CL  Transformer  Sketch  Review  Emotion  Language_Model  PDF
• 2021-05-10 Self-Supervised Learning with Swin Transformers    Zhenda Xie, Yutong Lin, Zhuliang Yao, Zheng Zhang, Qi Dai, Yue Cao, Han Hu arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  Self-Supervised  Pose  Detection  Object_Detection  Prediction  PDF
• 2021-05-10 Self-Guided Curriculum Learning for Neural Machine Translation    Lei Zhou, Liang Ding, Kevin Duh, Ryohei Sasano, Koichi Takeda arXiv_AI arXiv_AI  Transformer  Knowledge  Pose  NMT  Language_Model  PDF
• 2021-05-10 Learning Robust Latent Representations for Controllable Speech Synthesis    Shakti Kumar, Jithin Pradeep, Hussain Zaidi arXiv_CL arXiv_CL  Transformer  RNN  Speech  Pose  PDF
• 2021-05-10 SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation    Bing Li, Cheng Zheng, Silvio Giancola, Bernard Ghanem arXiv_AI arXiv_AI  Transformer  Point_Cloud  3D  Sparse  Pose  Relation  Matching  PDF
• 2021-05-10 RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation    En Yu, Zhuoling Li, Shoudong Han, Hongwei Wang arXiv_CV arXiv_CV  Transformer  Embedding  Tracking  Optimization  Object_Tracking  Pose  Detection  Relation  Attention  Re-identification  Inference  PDF
• 2021-05-10 Visual Grounding with Transformers    Ye Du, Zehua Fu, Qingjie Liu, Yunhong Wang arXiv_CV arXiv_CV  Transformer  Embedding  Pose  Detection  Object_Detection  Inference  PDF
• 2021-05-10 ReadTwice: Reading Very Large Documents with Memories    Yury Zemlyanskiy, Joshua Ainslie, Michiel de Jong, Philip Pham, Ilya Eckstein, Fei Sha arXiv_CL arXiv_CL  Transformer  Knowledge  Pose  QA  PDF
• 2021-05-10 Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning    Dandan Guo, Ruiying Lu, Bo Chen, Zequn Zeng, Mingyuan Zhou arXiv_CV arXiv_CV  Transformer  RNN  Pose  Action  Relation  Caption  Inference  Language_Model  Matching  PDF
• 2021-05-10 MuseMorphose: Full-Song and Fine-Grained Music Style Transfer with Just One Transformer VAE    Shih-Lun Wu, Yi-Hsuan Yang arXiv_SD arXiv_SD  Transformer  Style_Transfer  RNN  Attention  PDF
• 2021-05-09 Improving Patent Mining and Relevance Classification using Transformers    Théo Ding, Walter Vermeiren, Sylvie Ranwez, Binbin Xu arXiv_CL arXiv_CL  Transformer  Pose  Face  Classification  PDF
• 2021-05-09 Which transformer architecture fits my data? A vocabulary bottleneck in self-attention    Noam Wies, Yoav Levine, Daniel Jannai, Amnon Shashua arXiv_CL arXiv_CL  Transformer  Embedding  Bert  Attention  PDF
• 2021-05-09 Conformer: Local Features Coupling Global Representations for Visual Recognition    Zhiliang Peng, Wei Huang, Shanzhi Gu, Lingxi Xie, Yaowei Wang, Jianbin Jiao, Qixiang Ye arXiv_CV arXiv_CV  Transformer  Segmentation  Recognition  Represenation_Learning  Pose  Detection  Object_Detection  Attention  CNN  PDF
• 2021-05-09 Trajectory Prediction for Autonomous Driving with Topometric Map    Jiaolong Xu, Liang Xiao, Dawei Zhao, Yiming Nie, Bin Dai arXiv_CV arXiv_CV  Transformer  Pose  Autonomous  Prediction  PDF
• 2021-05-09 FNet: Mixing Tokens with Fourier Transforms    James Lee-Thorp, Joshua Ainslie, Ilya Eckstein, Santiago Ontanon arXiv_CL arXiv_CL  Transformer  Bert  Text_Classification  Classification  Relation  Attention  Matching  PDF
• 2021-05-09 TrTr: Visual Tracking with Transformer    Moju Zhao, Kei Okada, Masayuki Inaba arXiv_CV arXiv_CV  Transformer  Tracking  Pose  Classification  Relation  Attention  PDF
• 2021-05-08 Long-Span Dependencies in Transformer-based Summarization Systems    Potsawee Manakul, Mark J. F. Gales arXiv_CL arXiv_CL  Transformer  Attention  Summarization  PDF
• 2021-05-08 Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning    Benjamin Minixhofer, Milan Gritta, Ignacio Iacobacci arXiv_CL arXiv_CL  Transformer  Transfer_Learning  Bert  Classification  Inference  Language_Model  PDF
• 2021-05-08 NLP-IIS@UT at SemEval-2021 Task 4: Machine Reading Comprehension using the Long Document Transformer    Hossein Basafa, Sajad Movahedi, Ali Ebrahimi, Azadeh Shakery, Heshaam Faili arXiv_CL arXiv_CL  Transformer  Bert  Pose  Language_Model  PDF
• 2021-05-08 Falling Through the Gaps: Neural Architectures as Models of Morphological Rule Learning    Deniz Beser arXiv_CL arXiv_CL  Transformer  RNN  PDF
• 2021-05-07 Empirical Evaluation of Pre-trained Transformers for Human-Level NLP: The Role of Sample Size and Dimensionality    Adithya V Ganesan, Matthew Matero, Aravind Reddy Ravula, Huy Vu, H. Andrew Schwartz arXiv_CL arXiv_CL  Transformer  Embedding  Bert  Pose  Language_Model  PDF
• 2021-05-07 Duplex Sequence-to-Sequence Learning for Reversible Machine Translation    Zaixiang Zheng, Hao Zhou, Shujian Huang, Jiajun Chen, Jingjing Xu, Lei Li arXiv_CL arXiv_CL  Transformer  Pose  PDF
• 2021-05-07 $partial$-Explainer: Abductive Natural Language Inference via Differentiable Convex Optimization    Mokanarangan Thayaparan, Marco Valentino, Deborah Ferreira, Julia Rozanova, André Freitas arXiv_AI arXiv_AI  Transformer  Embedding  Optimization  Inference  QA  PDF
• 2021-05-07 Are Pre-trained Convolutions Better than Pre-trained Transformers?    Yi Tay, Mostafa Dehghani, Jai Gupta, Dara Bahri, Vamsi Aribandi, Zhen Qin, Donald Metzler arXiv_CL arXiv_CL  Transformer  CNN  Language_Model  PDF
• 2021-05-07 MOTR: End-to-End Multiple-Object Tracking with TRansformer    Fangao Zeng, Bin Dong, Tiancai Wang, Cheng Chen, Xiangyu Zhang, Yichen Wei arXiv_CV arXiv_CV  Transformer  Tracking  Object_Tracking  Pose  Detection  Relation  Object_Detection  PDF
• 2021-05-07 A State-of-the-art Survey of Object Detection Techniques in Microorganism Image Analysis: from Traditional Image Processing and Classical Machine Learning to Current Deep Convolutional Neural Networks and Potential Visual Transformers    Chen Li, Pingli Ma, Md Mamunur Rahaman, Yudong Yao, Jiawei Zhang, Shuojia Zou, Xin Zhao, Marcin Grzegorzek arXiv_AI arXiv_AI  Transformer  Review  Survey  Deep_Learning  Detection  Object_Detection  GAN  CNN  PDF
• 2021-05-07 SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts    Zhao You, Shulin Feng, Dan Su, Dong Yu arXiv_CL arXiv_CL  Transformer  Embedding  Recognition  Speech  Pose  Speech_Recognition  Inference  PDF
• 2021-05-07 Efficient Weight factorization for Multilingual Speech Recognition    Ngoc-Quan Pham, Tuan-Nam Nguyen, Sebastian Stueker, Alexander Waibel arXiv_CL arXiv_CL  Transformer  Recognition  RNN  Speech  Pose  Speech_Recognition  PDF
• 2021-05-06 Graph-based Multilingual Product Retrieval in E-commerce Search    Hanqing Lu, Youna Hu, Tong Zhao, Tony Wu, Yiwei Song, Bing Yin arXiv_CL arXiv_CL  Transformer  Pose  Action  Attention  Language_Model  PDF
• 2021-05-06 On the logistical difficulties and findings of Jopara Sentiment Analysis    Marvin M. Agüero-Torales, David Vilares, Antonio G. López-Herrera arXiv_CL arXiv_CL  Transformer  Sentiment  Language_Model  PDF
• 2021-05-06 Aligning Subtitles in Sign Language Videos    Hannah Bull, Triantafyllos Afouras, Gül Varol, Samuel Albanie, Liliane Momeni, Andrew Zisserman arXiv_CV arXiv_CV  Transformer  Embedding  Recognition  Bert  Pose  Attention  Prediction  PDF
• 2021-05-06 Adapting Monolingual Models: Data can be Scarce when Language Similarity is High    Wietse de Vries, Martijn Bartelds, Malvina Nissim, Martijn Wieling arXiv_CL arXiv_CL  Transformer  Transfer_Learning  Bert  Zero-Shot  PDF
• 2021-05-06 Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet    Luke Melas-Kyriazi arXiv_CV arXiv_CV  Transformer  Embedding  Classification  Attention  Image_Classification  PDF
• 2021-05-06 GraphFormers: GNN-nested Language Models for Linked Text Representation    Junhan Yang, Zheng Liu, Shitao Xiao, Chaozhuo Li, Guangzhong Sun, Xing Xie arXiv_AI arXiv_AI  Transformer  Embedding  Enhancement  Pose  Language_Model  Recommendation  PDF
• 2021-05-06 XeroAlign: Zero-Shot Cross-lingual Transformer Alignment    Milan Gritta, Ignacio Iacobacci arXiv_CL arXiv_CL  Transformer  Embedding  Zero-Shot  Text_Classification  Adversarial  Classification  Language_Model  PDF
• 2021-05-06 Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer    Wenqi Zhao, Liangcai Gao, Zuoyu Yan, Shuai Peng, Lin Du, Ziyin Zhang arXiv_CV arXiv_CV  Transformer  Recognition  RNN  Attention  Language_Model  PDF
• 2021-05-06 Exploring Explicit and Implicit Visual Relationships for Image Captioning    Zeliang Song, Xiaofei Zhou arXiv_CV arXiv_CV  Image_Caption  Transformer  Bert  Salient  Pose  Action  Relation  Visual_Relation  Caption  CNN  PDF
• 2021-05-05 Attention for Image Registration : an unsupervised Transformer approach    Zihao Wang, Hervé Delingette arXiv_AI arXiv_AI  Transformer  Unsupervised  Optimization  Pose  Deep_Learning  Attention  CNN  PDF
• 2021-05-05 Visual Composite Set Detection Using Part-and-Sum Transformers    Qi Dong, Zhuowen Tu, Haofu Liao, Yuting Zhang, Vijay Mahadevan, Stefano Soatto arXiv_CV arXiv_CV  Transformer  Action  Detection  Relation  Attention  Visual_Relation  Matching  PDF
• 2021-05-05 Proposal-free One-stage Referring Expression via Grid-Word Cross-Attention    Wei Suo, Mengyang Sun, Peng Wang, Qi Wu arXiv_CV arXiv_CV  Transformer  VQA  Attention  PDF
• 2021-05-05 Rare Disease Identification from Clinical Notes with Ontologies and Weak Supervision    Hang Dong, Víctor Suárez-Paniagua, Huayu Zhang, Minhong Wang, Emma Whitfield, Honghan Wu arXiv_CL arXiv_CL  Transformer  Bert  Pose  Ontology  Face  Medical  Matching  PDF
• 2021-05-05 Novelty Detection and Analysis of Traffic Scenario Infrastructures in the Latent Space of a Vision Transformer-Based Triplet Autoencoder    Jonas Wurst, Lakshman Balasubramanian, Michael Botsch, Wolfgang Utschick arXiv_CV arXiv_CV  Transformer  Knowledge  Pose  Detection  Relation  Attention  Autonomous  PDF
• 2021-05-05 TransHash: Transformer-based Hamming Hashing for Efficient Image Retrieval    Yongbiao Chen (1), Sheng Zhang (2), Fangxin Liu (1), Zhigang Chang (1), Mang Ye (3), Zhengwei Qi (1) ((1) Shanghai Jiao Tong University, (2) University of Southern California, (3) Wuhan University) arXiv_CV arXiv_CV  Transformer  Image_Retrieval  Knowledge  Pose  Action  CNN  PDF
• 2021-05-04 Retrieving Complex Tables with Multi-Granular Graph Representation Learning    Fei Wang, Kexuan Sun, Muhao Chen, Jay Pujara, Pedro Szekely arXiv_AI arXiv_AI  Transformer  Represenation_Learning  Self-Supervised  Pose  Matching  PDF
• 2021-05-04 HerBERT: Efficiently Pretrained Transformer-based Language Model for Polish    Robert Mroczkowski, Piotr Rybak, Alina Wróblewska, Ireneusz Gawlik arXiv_CL arXiv_CL  Transformer  Bert  Knowledge  Pose  Language_Model  PDF
• 2021-05-04 MLP-Mixer: An all-MLP Architecture for Vision    Ilya Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Daniel Keysers, Jakob Uszkoreit, Mario Lucic, Alexey Dosovitskiy arXiv_AI arXiv_AI  Transformer  Regularization  Classification  Attention  CNN  Image_Classification  Inference  PDF
• 2021-05-04 PreSizE: Predicting Size in E-Commerce using Transformers    Yotam Eshel, Or Levi, Haggai Roitman, Alexander Nus arXiv_AI arXiv_AI  Transformer  Pose  Deep_Learning  Prediction  Recommendation  PDF
• 2021-05-04 Combining Supervised and Un-supervised Learning for Automatic Citrus Segmentation    Heqing Huang, Tongbin Huang, Zhen Li, Zhiwei Wei, Shilei Lv arXiv_CV arXiv_CV  Transformer  Segmentation  Unsupervised  Prediction  PDF
• 2021-05-04 Moving Towards Centers: Re-ranking with Attention and Memory for Re-identification    Yunhao Zhou, Yi Wang, Lap-Pui Chau arXiv_CV arXiv_CV  Transformer  Embedding  Pose  Relation  Attention  Re-identification  Prediction  PDF
• 2021-05-04 Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoning    Xiangyu Peng, Siyan Li, Sarah Wiegreffe, Mark Riedl arXiv_CL arXiv_CL  Transformer  Action  Inference  Language_Model  PDF
• 2021-05-03 Goldilocks: Just-Right Tuning of BERT for Technology-Assisted Review    Eugene Yang, Sean MacAvaney, David D. Lewis, Ophir Frieder arXiv_CL arXiv_CL  Transformer  Bert  Text_Classification  Review  Classification  Language_Model  PDF
• 2021-05-03 Pseudo Siamese Network for Few-shot Intent Generation    Congying Xia, Caiming Xiong, Philip Yu arXiv_CL arXiv_CL  Transformer  Pose  Action  Detection  Few-Shot  PDF
• 2021-05-03 ISTR: End-to-End Instance Segmentation with Transformers    Jie Hu, Liujuan Cao, Lu Yao, ShengChuan Zhang, Yan Wang, Ke Li, Feiyue Huang, Rongrong Ji, Ling Shao arXiv_CV arXiv_CV  Transformer  Segmentation  Embedding  Recognition  Pose  Quantitative  Detection  Object_Detection  Matching  PDF
• 2021-05-03 AvaTr: One-Shot Speaker Extraction with Transformers    Shell Xu Hu, Md Rifat Arefin, Viet-Nhat Nguyen, Alish Dipani, Xaq Pitkow, Andreas Savas Tolias arXiv_SD arXiv_SD  Transformer  Speech  Pose  Action  Attention  PDF
• 2021-05-02 Larger-Scale Transformers for Multilingual Masked Language Modeling    Naman Goyal, Jingfei Du, Myle Ott, Giri Anantharaman, Alexis Conneau arXiv_CL arXiv_CL  Transformer  Bert  Language_Model  PDF
• 2021-05-02 Augmenting Sequential Recommendation with Pseudo-Prior Items via Reversely Pre-training Transformer    Zhiwei Liu, Ziwei Fan, Yu Wang, Philip S. Yu arXiv_AI arXiv_AI  Transformer  Bert  Pose  Relation  Recommendation  PDF
• 2021-05-02 Event Argument Extraction using Causal Knowledge Structures    Debanjana Kar, Sudeshna Sarkar, Pawan Goyal arXiv_CL arXiv_CL  Transformer  Knowledge  Pose  Action  Quantitative  PDF
• 2021-05-02 Anatomy-Guided Parallel Bottleneck Transformer Network for Automated Evaluation of Root Canal Therapy    Yunxiang Li, Guodong Zeng, Yifan Zhang, Jun Wang, Qianni Zhang, Qun Jin, Lingling Sun, Qisi Lian, Neng Xia, Ruizi Peng, Kai Tang, Yaqi Wang, Shuai Wang arXiv_AI arXiv_AI  Transformer  Segmentation  Knowledge  Pose  Classification  Attention  PDF
• 2021-05-01 Audio Transformers:Transformer Architectures For Large Scale Audio Understanding. Adieu Convolutions    Prateek Verma, Jonathan Berger arXiv_SD arXiv_SD  Image_Caption  Transformer  Embedding  Unsupervised  Pose  Classification  GAN  CNN  PDF
• 2021-05-01 SVT-Net: A Super Light-Weight Network for Large Scale Place Recognition using Sparse Voxel Transformers    Zhaoxin Fan, Zhenbo Song, Hongyan Liu, Jun He, Xiaoyong Du arXiv_CV arXiv_CV  Transformer  Recognition  Point_Cloud  3D  Sparse  Pose  SLAM  PDF
• 2021-04-30 GTN-ED: Event Detection Using Graph Transformer Networks    Sanghamitra Dutta, Liang Ma, Tanay Kumar Saha, Di Lu, Joel Joel Tetreault, Alex Jaimes arXiv_CL arXiv_CL  Transformer  Pose  Detection  Relation  PDF
• 2021-04-30 CAT: Cross-Attention Transformer for One-Shot Object Detection    Weidong Lin, Yuyan Deng, Yang Gao, Ning Wang, Jinghao Zhou, Lingqiao Liu, Lei Zhang, Peng Wang arXiv_CV arXiv_CV  Transformer  Pose  Detection  Object_Detection  Attention  Inference  PDF
• 2021-04-30 Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads    Chenyu Gao, Qi Zhu, Peng Wang, Qi Wu arXiv_CV arXiv_CV  Transformer  Bert  VQA  Attention  QA  PDF
• 2021-04-30 Perceptual Image Quality Assessment with Transformers    Manri Cheon, Sung-Jun Yoon, Byungyeon Kang, Junwoo Lee arXiv_CV arXiv_CV  Transformer  Embedding  Pose  CNN  Prediction  QA  PDF
• 2021-04-30 CoSformer: Detecting Co-Salient Object with Transformers    Lv Tang arXiv_CV arXiv_CV  Transformer  Embedding  Salient  Pose  Deep_Learning  Detection  Relation  Object_Detection  PDF
• 2021-04-30 End-to-End Attention-based Image Captioning    Carola Sundaramoorthy, Lin Ziwen Kelvin, Mahak Sarin, Shubham Gupta arXiv_AI arXiv_AI  Image_Caption  Transformer  RNN  Pose  Attention  Caption  PDF
• 2021-04-29 Pyramid Medical Transformer for Medical Image Segmentation    Zhuangzhuang Zhang, Baozhou Sun, Weixiong Zhang arXiv_CV arXiv_CV  Transformer  Segmentation  Embedding  Pose  Action  Relation  Attention  Medical  CNN  PDF
• 2021-04-29 AMR Parsing with Action-Pointer Transformer    Jiawei Zhou, Tahira Naseem, Ramón Fernandez Astudillo, Radu Florian arXiv_CL arXiv_CL  Transformer  Pose  Action  Attention  Prediction  PDF
• 2021-04-29 Using Transformers to Provide Teachers with Personalized Feedback on their Classroom Discourse: The TalkMoves Application    Abhijit Suresh, Jennifer Jacobs, Vivian Lai, Chenhao Tan, Wayne Ward, James H. Martin, Tamara Sumner arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Face  Speech_Recognition  PDF
• 2021-04-29 HandsFormer: Keypoint Transformer for Monocular 3D Pose Estimation ofHands and Object in Interaction    Shreyas Hampali, Sayan Deb Sarkar, Mahdi Rad, Vincent Lepetit arXiv_CV arXiv_CV  Transformer  Recognition  3D  Pose_Estimation  Pose  Action  Attention  PDF
• 2021-04-29 GasHis-Transformer: A Multi-scale Visual Transformer Approach for Gastric Histopathology Image Classification    Haoyuan Chen, Chen Li, Xiaoyan Li, Ge Wang, Weiming Hu, Yixin Li, Wanli Liu, Changhao Sun, Yudong Yao, Marcin Grzegorzek arXiv_CV arXiv_CV  Transformer  Recognition  Pose  Classification  Deep_Learning  Medical  CNN  Image_Classification  PDF
• 2021-04-29 Emerging Properties in Self-Supervised Vision Transformers    Mathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou, Julien Mairal, Piotr Bojanowski, Armand Joulin arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  Self-Supervised  CNN  PDF
• 2021-04-29 The entire network structure of Crossmodal Transformer    Meng Li, Changyan Lin, Lixia Shu, Xin Pu, Yi Chen, Heng Wu, Jiasong Li, Hongshuai Cao arXiv_CV arXiv_CV  Transformer  3D  Pose  Relation  Medical  Matching  PDF
• 2021-04-29 Using Adaptive Gradient for Texture Learning in Single-View 3D Reconstruction    Luoyang Lin, Dihong Tian arXiv_CV arXiv_CV  Transformer  Reconstruction  Segmentation  3D  Attention  PDF
• 2021-04-29 Analyzing the Nuances of Transformers' Polynomial Simplification Abilities    Vishesh Agarwal, Somak Aditya, Navin Goyal arXiv_AI arXiv_AI  Transformer  Pose  PDF
• 2021-04-28 Inpainting Transformer for Anomaly Detection    Jonathan Pirnay, Keng Chai arXiv_CV arXiv_CV  Transformer  Inpainting  Pose  Detection  Attention  CNN  PDF
• 2021-04-28 Evaluating Document Representations for Content-based Legal Literature Recommendations    Malte Ostendorff, Elliott Ash, Terry Ruas, Bela Gipp, Julian Moreno-Schneider, Georg Rehm arXiv_CL arXiv_CL  Transformer  Embedding  Represenation_Learning  Recommendation  PDF
• 2021-04-28 Twins: Revisiting Spatial Attention Design in Vision Transformers    Xiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang, Haibing Ren, Xiaolin Wei, Huaxia Xia, Chunhua Shen arXiv_AI arXiv_AI  Transformer  Segmentation  Pose  Classification  Deep_Learning  Detection  Attention  Prediction  PDF
• 2021-04-28 HOTR: End-to-End Human-Object Interaction Detection with Transformers    Bumsoo Kim, Junhyun Lee, Jaewoo Kang, Eun-Sol Kim, Hyunwoo J. Kim arXiv_CV arXiv_CV  Transformer  Pose  Action  Classification  Detection  Relation  Object_Detection  Inference  Prediction  PDF
• 2021-04-28 Point Cloud Learning with Transformer    Xian-Feng Han, Yu-Jia Kuang, Guo-Qiang Xiao arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  Recognition  Point_Cloud  3D  Represenation_Learning  Action  Classification  PDF
• 2021-04-28 Medical Transformer: Universal Brain Encoder for 3D MRI Analysis    Eunji Jun, Seungwoo Jeong, Da-Woon Heo, Heung-Il Suk arXiv_AI arXiv_AI  Transformer  Segmentation  Transfer_Learning  3D  Self-Supervised  Pose  Classification  Deep_Learning  Relation  Attention  Medical  Prediction  PDF
• 2021-04-27 ConTNet: Why not use convolution and transformer at the same time?    Haotian Yan, Zhe Li, Weijian Li, Changhu Wang, Ming Wu, Chuang Zhang arXiv_CV arXiv_CV  Transformer  Segmentation  Pose  Classification  Detection  Object_Detection  CNN  Image_Classification  Prediction  PDF
• 2021-04-27 Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges    Michael M. Bronstein, Joan Bruna, Taco Cohen, Petar Veličković arXiv_AI arXiv_AI  Transformer  RNN  Knowledge  Pose  Deep_Learning  PDF
• 2021-04-27 Generating Lead Sheets with Affect: A Novel Conditional seq2seq Framework    Dimos Makris, Kat R. Agres, Dorien Herremans arXiv_SD arXiv_SD  Transformer  Memory_Networks  Pose  Emotion  NMT  PDF
• 2021-04-27 Dual Transformer for Point Cloud Analysis    Xian-Feng Han, Yi-Fei Jin, Hui-Xian Cheng, Guo-Qiang Xiao arXiv_CV arXiv_CV  Image_Caption  Transformer  Segmentation  Point_Cloud  3D  Represenation_Learning  Pose  Quantitative  Classification  Attention  PDF
• 2021-04-27 DPT-FSNet:Dual-path Transformer Based Full-band and Sub-band Fusion Network for Speech Enhancement    Feng Dang, Hangting Chen, Pengyuan Zhang arXiv_SD arXiv_SD  Transformer  Enhancement  Speech  Pose  PDF
• 2021-04-26 Accounting for Agreement Phenomena in Sentence Comprehension with Transformer Language Models: Effects of Similarity-based Interference on Surprisal and Attention    Soo Hyun Ryu, Richard L. Lewis arXiv_CL arXiv_CL  Transformer  Review  Self-Supervised  Relation  Attention  Language_Model  PDF
• 2021-04-26 Morph Call: Probing Morphosyntactic Content of Multilingual Transformers    Vladislav Mikhailov, Oleg Serikov, Ekaterina Artemova arXiv_CL arXiv_CL  Transformer  Knowledge  Pose  Detection  Language_Model  PDF
• 2021-04-26 Teaching a Massive Open Online Course on Natural Language Processing    Ekaterina Artemova, Murat Apishev, Veronika Sarkisyan, Sergey Aksenov, Denis Kirjanov, Oleg Serikov arXiv_CL arXiv_CL  Transformer  Pose  Language_Model  PDF
• 2021-04-26 MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding    Aishwarya Kamath, Mannat Singh, Yann LeCun, Ishan Misra, Gabriel Synnaeve, Nicolas Carion arXiv_CV arXiv_CV  Transformer  Segmentation  Pose  Detection  VQA  Few-Shot  Object_Detection  Caption  QA  PDF
• 2021-04-26 Improve Vision Transformers Training by Suppressing Over-smoothing    Chengyue Gong, Dilin Wang, Meng Li, Vikas Chandra, Qiang Liu arXiv_CV arXiv_CV  Transformer  Pose  Classification  Attention  CNN  PDF
• 2021-04-26 Rich Semantics Improve Few-shot Learning    Mohamed Afham, Salman Khan, Muhammad Haris Khan, Muzammal Naseer, Fahad Shahbaz Khan arXiv_CV arXiv_CV  Transformer  Pose  Relation  Few-Shot  Inference  PDF
• 2021-04-26 Visformer: The Vision-friendly Transformer    Zhengsu Chen, Lingxi Xie, Jianwei Niu, Xuefeng Liu, Longhui Wei, Qi Tian arXiv_CV arXiv_CV  Transformer  Recognition  Pose  Classification  PDF
• 2021-04-26 Easy and Efficient Transformer : Scalable Inference Solution For large NLP mode    Gongzheng li, Yadong Xi, Jingzhen Ding, Duan Wang, Bai Liu, Changjie Fan, Xiaoxi Mao, Zeng Zhao arXiv_CL arXiv_CL  Transformer  Embedding  Optimization  Pose  Inference  PDF
• 2021-04-26 GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization    Jia-Hong Huang, Luka Murn, Marta Mrak, Marcel Worring arXiv_AI arXiv_AI  Transformer  Pose  Attention  Summarization  PDF
• 2021-04-26 Diverse Image Inpainting with Bidirectional and Autoregressive Transformers    Yingchen Yu, Fangneng Zhan, Rongliang Wu, Jianxiong Pan, Kaiwen Cui, Shijian Lu, Feiying Ma, Xuansong Xie, Chunyan Miao arXiv_CV arXiv_CV  Transformer  Inpainting  Pose  Quantitative  Attention  CNN  PDF
• 2021-04-25 Transformers to Fight the COVID-19 Infodemic    Lasitha Uyangodage, Tharindu Ranasinghe, Hansi Hettiarachchi arXiv_CL arXiv_CL  Transformer  Detection  GAN  PDF
• 2021-04-25 Transformer Meets DCFAM: A Novel Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images    Libo Wang, Rui Li, Chenxi Duan, Shenghui Fang arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  Pose  Attention  CNN  Prediction  PDF
• 2021-04-25 Visual Saliency Transformer    Nian Liu, Ni Zhang, Kaiyuan Wan, Junwei Han, Ling Shao arXiv_CV arXiv_CV  Transformer  Salient  Pose  Boundary_Detection  Detection  Object_Detection  Attention  Prediction  PDF
• 2021-04-24 RelTransformer: Balancing the Visual Relationship Detection from Local Context, Scene and Memory    Jun Chen, Aniket Agarwal, Sherif Abdelkarim, Deyao Zhu, Mohamed Elhoseiny arXiv_AI arXiv_AI  Image_Caption  Transformer  Recognition  Pose  Detection  Relation  VQA  Visual_Relation  Caption  Prediction  QA  PDF
• 2021-04-24 M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers    Tianrui Guan, Jun Wang, Shiyi Lan, Rohan Chandra, Zuxuan Wu, Larry Davis, Dinesh Manocha arXiv_CV arXiv_CV  Transformer  Point_Cloud  3D  Detection  Relation  Object_Detection  PDF
• 2021-04-23 Playing Lottery Tickets with Vision and Language    Zhe Gan, Yen-Chun Chen, Linjie Li, Tianlong Chen, Yu Cheng, Shuohang Wang, Jingjing Liu arXiv_CV arXiv_CV  Transformer  Bert  Adversarial  VQA  QA  Matching  PDF
• 2021-04-23 Generating abstractive summaries of Lithuanian news articles using a transformer model    Lukas Stankevičius, Mantas Lukoševičius arXiv_CL arXiv_CL  Transformer  Summarization  PDF
• 2021-04-23 VidTr: Video Transformer Without Convolutions    Xinyu Li, Yanyi Zhang, Chunhui Liu, Bing Shuai, Yi Zhu, Biagio Brattoli, Hao Chen, Ivan Marsic, Joseph Tighe arXiv_CV arXiv_CV  Transformer  3D  Pose  Action  Classification  Attention  Video_Classification  PDF
• 2021-04-23 Skeletor: Skeletal Transformers for Robust Body-Pose Estimation    Tao Jiang, Necati Cihan Camgoz, Richard Bowden arXiv_CV arXiv_CV  Transformer  Tracking  Unsupervised  3D  Pose_Estimation  Pose  Detection  PDF
• 2021-04-23 Learning to Cluster Faces via Transformer    Jinxing Ye, Xioajiang Peng, Baigui Sun, Kai Wang, Xiuyu Sun, Hao Li, Hanqing Wu arXiv_CV arXiv_CV  Transformer  Pose  Face  Relation  PDF
• 2021-04-23 Transfer training from smaller language model    Han Zhang arXiv_CL arXiv_CL  Transformer  Language_Model  PDF
• 2021-04-22 On Geodesic Distances and Contextual Embedding Compression for Text Classification    Rishi Jha, Kai Mihata arXiv_CL arXiv_CL  Transformer  Embedding  Bert  Text_Classification  Pose  Classification  PDF
• 2021-04-22 Multiscale Vision Transformers    Haoqi Fan, Bo Xiong, Karttikeya Mangalam, Yanghao Li, Zhicheng Yan, Jitendra Malik, Christoph Feichtenhofer arXiv_AI arXiv_AI  Transformer  Recognition  Classification  Image_Classification  PDF
• 2021-04-22 VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text    Hassan Akbari, Linagzhe Yuan, Rui Qian, Wei-Hong Chuang, Shih-Fu Chang, Yin Cui, Boqing Gong arXiv_AI arXiv_AI  Transformer  Recognition  Self-Supervised  Action_Recognition  Action  Classification  Image_Classification  Video_Retrieval  PDF
• 2021-04-22 So-ViT: Mind Visual Tokens for Vision Transformer    Jiangtao Xie, Ruiren Zeng, Qilong Wang, Ziqi Zhou, Peihua Li arXiv_AI arXiv_AI  Transformer  Embedding  Pose  Classification  Attention  PDF
• 2021-04-22 Hybrid Encoder: Towards Efficient and Precise Native AdsRecommendation via Hybrid Transformer Encoding Networks    Junhan Yang, Zheng Liu, Bowen Jin, Jianxun Lian, Defu Lian, Akshay Soni, Eun Yong Kang, Yajun Wang, Guangzhong Sun, Xing Xie arXiv_AI arXiv_AI  Transformer  Embedding  Pose  Recommendation  PDF
• 2021-04-22 Token Labeling: Training a 85.5% Top-1 Accuracy Vision Transformer with 56M Parameters on ImageNet    Zihang Jiang, Qibin Hou, Li Yuan, Daquan Zhou, Xiaojie Jin, Anran Wang, Jiashi Feng arXiv_CV arXiv_CV  Transformer  Classification  CNN  PDF
• 2021-04-21 Improving BERT Pretraining with Syntactic Supervision    Giorgos Tziafas, Konstantinos Kogkalidis, Gijs Wijnholds, Michael Moortgat arXiv_CL arXiv_CL  Transformer  Unsupervised  Bert  PDF
• 2021-04-21 Label-Synchronous Speech-to-Text Alignment for ASR Using Forward and Backward Transformers    Yusuke Kida, Tatsuya Komatsu, Masahito Togami arXiv_SD arXiv_SD  Transformer  Recognition  Speech  Pose  Classification  Attention  Speech_Recognition  Inference  Prediction  PDF
• 2021-04-21 'What's The Context?' : Long Context NLM Adaptation for ASR Rescoring in Conversational Agents    Ashish Shenoy, Sravan Bodapati, Monica Sunkara, Srikanth Ronanki, Katrin Kirchhoff arXiv_CL arXiv_CL  Transformer  RNN  Speech  Pose  Classification  Attention  Language_Model  PDF
• 2021-04-20 Analyzing COVID-19 Tweets with Transformer-based Language Models    Philip Feldman, Sim Tiwari, Charissa S. L. Cheah, James R. Foulds, Shimei Pan arXiv_CL arXiv_CL  Transformer  Language_Model  PDF
• 2021-04-20 Modeling Event Plausibility with Consistent Conceptual Abstraction    Ian Porada, Kaheer Suleman, Adam Trischler, Jackie Chi Kit Cheung arXiv_CL arXiv_CL  Transformer  Knowledge  Action  Relation  Language_Model  PDF
• 2021-04-20 Identify, Align, and Integrate: Matching Knowledge Graphs to Commonsense Reasoning Tasks    Lisa Bauer, Mohit Bansal arXiv_AI arXiv_AI  Transformer  Knowledge  Knowledge_Graph  Inference  QA  Matching  PDF
• 2021-04-20 VideoGPT: Video Generation using VQ-VAE and Transformers    Wilson Yan, Yunzhi Zhang, Pieter Abbeel, Aravind Srinivas arXiv_CV arXiv_CV  Transformer  3D  Pose  Attention  GAN  PDF
• 2021-04-20 Transformer Transforms Salient Object Detection and Camouflaged Object Detection    Yuxin Mao, Jing Zhang, Zhexiong Wan, Yuchao Dai, Aixuan Li, Yunqiu Lv, Xinyu Tian, Deng-Ping Fan, Nick Barnes arXiv_CV arXiv_CV  Transformer  Segmentation  Weakly_Supervised  Salient  Self-Supervised  Pose  Classification  Detection  Relation  Object_Detection  Prediction  PDF
• 2021-04-20 VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization    Pankaj Mishra, Riccardo Verk, Daniele Fornasier, Claudio Piciarelli, Gian Luca Foresti arXiv_AI arXiv_AI  Transformer  Reconstruction  Embedding  Pose  Detection  PDF
• 2021-04-20 Differentiable Model Compression via Pseudo Quantization Noise    Alexandre Défossez, Yossi Adi, Gabriel Synnaeve arXiv_AI arXiv_AI  Transformer  Quantization  Pose  Classification  Image_Classification  Language_Model  PDF
• 2021-04-20 RoFormer: Enhanced Transformer with Rotary Position Embedding    Jianlin Su, Yu Lu, Shengfeng Pan, Bo Wen, Yunfeng Liu arXiv_AI arXiv_AI  Transformer  Embedding  Pose  Attention  Language_Model  PDF
• 2021-04-20 WASSA@IITK at WASSA 2021: Multi-task Learning and Transformer Finetuning for Emotion Classification and Empathy Prediction    Jay Mundra, Rohan Gupta, Sagnik Mukherjee arXiv_CL arXiv_CL  Transformer  Emotion  Classification  Deep_Learning  Relation  Prediction  PDF
• 2021-04-20 M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection    Junke Wang, Zuxuan Wu, Jingjing Chen, Yu-Gang Jiang arXiv_CV arXiv_CV  Transformer  Recognition  Pose  Face  Detection  Image_Compression  Prediction  PDF
• 2021-04-20 Efficient pre-training objectives for Transformers    Luca Di Liello, Matteo Gabburo, Alessandro Moschitti arXiv_CL arXiv_CL  Transformer  Bert  Pose  PDF
• 2021-04-19 Neural Language Models with Distant Supervision to Identify Major Depressive Disorder from Clinical Notes    Bhavani Singh Agnikula Kshatriya, Nicolas A Nunez, Manuel Gardea- Resendez, Euijung Ryu, Brandon J Coombes, Sunyang Fu, Mark A Frye, Joanna M Biernacka, Yanshan Wang arXiv_AI arXiv_AI  Transformer  Unsupervised  Bert  Text_Classification  Pose  Classification  Language_Model  PDF
• 2021-04-19 Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model    Per E Kummervold, Javier de la Rosa, Freddy Wetjen, Svein Arne Brygfjeld arXiv_CL arXiv_CL  Transformer  Recognition  OCR  Bert  Optical_Character  Classification  Language_Model  PDF
• 2021-04-19 Extracting Temporal Event Relation with Syntactic-Guided Temporal Graph Transformer    Shuaicheng Zhang, Lifu Huang, Qiang Ning arXiv_AI arXiv_AI  Transformer  Pose  Action  Classification  Relation  Relation_Extraction  Attention  PDF
• 2021-04-19 Fusing information streams in end-to-end audio-visual speech recognition    Wentao Yu, Steffen Zeiler, Dorothea Kolossa arXiv_SD arXiv_SD  Transformer  Recognition  Speech  Pose  Attention  Speech_Recognition  PDF
• 2021-04-19 Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers    Takaaki Hori, Niko Moritz, Chiori Hori, Jonathan Le Roux arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Pose  Attention  Speech_Recognition  PDF
• 2021-04-19 Probing for Bridging Inference in Transformer Language Models    Onkar Pandit, Yufang Hou arXiv_CL arXiv_CL  Transformer  Bert  Relation  Attention  Inference  Language_Model  Prediction  PDF
• 2021-04-19 Improving Transformer-Kernel Ranking Model Using Conformer and Query Term Independence    Bhaskar Mitra, Sebastian Hofstatter, Hamed Zamani, Nick Craswell arXiv_AI arXiv_AI  Transformer  Pose  Deep_Learning  Attention  Inference  Matching  PDF
• 2021-04-19 BM-NAS: Bilevel Multimodal Neural Architecture Search    Yihang Yin, Siyu Huang, Xiang Zhang, Dejing Dou arXiv_CV arXiv_CV  Transformer  NAS  Pose  Attention  PDF
• 2021-04-19 Code Structure Guided Transformer for Source Code Summarization    Shuzheng Gao, Cuiyun Gao, Yulan He, Jichuan Zeng, Lun Yiu Nie, Xin Xia arXiv_CL arXiv_CL  Transformer  Pose  Attention  Summarization  PDF
• 2021-04-19 BERTić -- The Transformer Language Model for Bosnian, Croatian, Montenegrin and Serbian    Nikola Ljubešić, Davor Lauc arXiv_CL arXiv_CL  Transformer  Recognition  Bert  Speech  Face  Language_Model  Prediction  PDF
• 2021-04-19 Multi-Modal Fusion Transformer for End-to-End Autonomous Driving    Aditya Prakash, Kashyap Chitta, Andreas Geiger arXiv_AI arXiv_AI  Transformer  3D  Pose  Detection  Object_Detection  Attention  Autonomous  PDF
• 2021-04-19 Restoration of Video Frames from a Single Blurred Image with Motion Understanding    Dawit Mureja Argaw, Junsik Kim, Francois Rameau, Chaoning Zhang, In So Kweon arXiv_CV arXiv_CV  Transformer  Restoration  Pose  PDF
• 2021-04-19 TransCrowd: Weakly-Supervised Crowd Counting with Transformer    Dingkang Liang, Xiwu Chen, Wei Xu, Yu Zhou, Xiang Bai arXiv_CV arXiv_CV  Transformer  Knowledge  Pose  Attention  CNN  Prediction  PDF
• 2021-04-19 UVCE-IIITT@DravidianLangTech-EACL2021: Tamil Troll Meme Classification: You need to Pay more Attention    Siddhanth U Hegde, Adeep Hande, Ruba Priyadharshini, Sajeetha Thavareesan, Bharathi Raja Chakravarthi arXiv_CL arXiv_CL  Transformer  Pose  Classification  Attention  Caption  PDF
• 2021-04-19 A novel Time-frequency Transformer and its Application in Fault Diagnosis of Rolling Bearings    Yifei Ding, Minping Jia, Qiuhua Miao, Yudong Cao arXiv_AI arXiv_AI  Transformer  Pose  Action  Deep_Learning  Attention  PDF
• 2021-04-19 IIITT@LT-EDI-EACL2021-Hope Speech Detection: There is always Hope in Transformers    Karthik Puranik, Adeep Hande, Ruba Priyadharshini, Sajeetha Thavareesan, Bharathi Raja Chakravarthi arXiv_CL arXiv_CL  Transformer  Speech  Detection  PDF
• 2021-04-19 BigGreen at SemEval-2021 Task 1: Lexical Complexity Prediction with Assembly Models    Aadil Islam, Weicheng Ma, Soroush Vosoughi arXiv_AI arXiv_AI  Transformer  Bert  Attention  Prediction  PDF
• 2021-04-18 FedNLP: A Research Platform for Federated Learning in Natural Language Processing    Bill Yuchen Lin, Chaoyang He, Zihang Zeng, Hulin Wang, Yufen Huang, Mahdi Soltanolkotabi, Xiang Ren, Salman Avestimehr arXiv_AI arXiv_AI  Transformer  Bert  Text_Classification  Face  Classification  GAN  Language_Model  PDF
• 2021-04-18 Contrastive Out-of-Distribution Detection for Pretrained Transformers    Wenxuan Zhou, Muhao Chen arXiv_CL arXiv_CL  Transformer  Pose  Face  Detection  Inference  PDF
• 2021-04-18 Consistent Accelerated Inference via Confident Adaptive Transformers    Tal Schuster, Adam Fisch, Tommi Jaakkola, Regina Barzilay arXiv_AI arXiv_AI  Transformer  Classification  Inference  Prediction  PDF
• 2021-04-18 On the Strengths of Cross-Attention in Pretrained Transformers for Machine Translation    Mozhdeh Gheini, Xiang Ren, Jonathan May arXiv_CL arXiv_CL  Transformer  Embedding  Transfer_Learning  Zero-Shot  Attention  PDF
• 2021-04-18 Demystifying the Better Performance of Position Encoding Variants for Transformer    Pu-Chin Chen, Henry Tsai, Srinadh Bhojanapalli, Hyung Won Chung, Yin-Wen Chang, Chun-Sung Ferng arXiv_CL arXiv_CL  Transformer  Embedding  Pose  PDF
• 2021-04-18 Knowledge Neurons in Pretrained Transformers    Damai Dai, Li Dong, Yaru Hao, Zhifang Sui, Furu Wei arXiv_CL arXiv_CL  Transformer  Knowledge  Pose  Relation  Language_Model  PDF
• 2021-04-18 mT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs    Zewen Chi, Li Dong, Shuming Ma, Shaohan Huang Xian-Ling Mao, Heyan Huang, Furu Wei arXiv_CL arXiv_CL  Transformer  Recognition  Pose  Classification  Summarization  PDF
• 2021-04-18 Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm    Dongkuan Xu, Ian E.H. Yen, Jinxi Zhao, Zhibin Xiao arXiv_AI arXiv_AI  Transformer  Bert  Sparse  Knowledge  CNN  Language_Model  Prediction  PDF
• 2021-04-18 When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset    Lucia Zheng, Neel Guha, Brandon R. Anderson, Peter Henderson, Daniel E. Ho arXiv_CL arXiv_CL  Transformer  Embedding  Bert  RNN  Self-Supervised  PDF
• 2021-04-17 Higher Order Recurrent Space-Time Transformer    Tsung-Ming Tai, Giuseppe Fiameni, Cheng-Kuang Lee, Oswald Lanz arXiv_CV arXiv_CV  Transformer  Recognition  RNN  Pose  Action_Recognition  Action  Attention  PDF
• 2021-04-17 UPB at SemEval-2021 Task 5: Virtual Adversarial Training for Toxic Spans Detection    Andrei Paraschiv, Dumitru-Clementin Cercel, Mihai Dascalu arXiv_CL arXiv_CL  Transformer  Bert  Adversarial  Detection  PDF
• 2021-04-17 Emotion Classification in a Resource Constrained Language Using Transformer-based Approach    Avishek Das, Omar Sharif, Mohammed Moshiul Hoque, Iqbal H. Sarker arXiv_CL arXiv_CL  Transformer  Bert  RNN  Pose  Emotion  Classification  PDF
• 2021-04-17 TransVG: End-to-End Visual Grounding with Transformers    Jiajun Deng, Zhengyuan Yang, Tianlang Chen, Wengang Zhou, Houqiang Li arXiv_CV arXiv_CV  Transformer  Pose  Action  Attention  Prediction  PDF
• 2021-04-17 Visually Guided Sound Source Separation and Localization using Self-Supervised Motion Representations    Lingyu Zhu, Esa Rahtu arXiv_CV arXiv_CV  Transformer  Embedding  Knowledge  Self-Supervised  Pose  Detection  Object_Detection  Optical_Flow  PDF
• 2021-04-17 Visual Transformer Pruning    Mingjian Zhu, Kai Han, Yehui Tang, Yunhe Wang arXiv_CV arXiv_CV  Transformer  Regularization  Pose  PDF
• 2021-04-17 Hierarchical Transformer Networks for Longitudinal Clinical Document Classification    Yuqi Si, Kirk Roberts arXiv_CL arXiv_CL  Transformer  Bert  Pose  Classification  Prediction  PDF
• 2021-04-16 LAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding    Te-Lin Wu, Cheng Li, Mingyang Zhang, Tao Chen, Spurthi Amba Hombaiah, Michael Bendersky arXiv_CV arXiv_CV  Transformer  Pose  Action  PDF
• 2021-04-16 Capturing Row and Column Semantics in Transformer Based Question Answering over Tables    Michael Glass, Mustafa Canim, Alfio Gliozzo, Saneem Chemmengath, Rishav Chakravarti, Avi Sil, Feifei Pan, Samarth Bharadwaj, Nicolas Rodolfo Fauceglia arXiv_AI arXiv_AI  Transformer  Embedding  Bert  Pose  Action  QA  PDF
• 2021-04-16 AMMU -- A Survey of Transformer-based Biomedical Pretrained Language Models    Katikapalli Subramanyam Kalyan, Ajit Rajasekharan, Sivanesan Sangeetha arXiv_AI arXiv_AI  Transformer  Embedding  Transfer_Learning  Bert  Self-Supervised  Survey  Medical  Language_Model  PDF
• 2021-04-16 Is Your Language Model Ready for Dense Representation Fine-tuning?    Luyu Gao, Jamie Callan arXiv_CL arXiv_CL  Transformer  Embedding  Optimization  Knowledge  Pose  Language_Model  PDF
• 2021-04-16 Variable Instance-Level Explainability for Text Classification    George Chrysostomou, Nikolaos Aletras arXiv_AI arXiv_AI  Transformer  Text_Classification  Pose  Action  Classification  Prediction  PDF
• 2021-04-16 Serial or Parallel? Plug-able Adapter for multilingual machine translation    Yaoming Zhu, Jiangtao Feng, Chengqi Zhao, Mingxuan Wang, Lei Li arXiv_AI arXiv_AI  Transformer  Embedding  Knowledge  Pose  PDF
• 2021-04-16 Cross-Modal Retrieval Augmentation for Multi-Modal Classification    Shir Gur, Natalia Neverova, Chris Stauffer, Ser-Nam Lim, Douwe Kiela, Austin Reiter arXiv_CV arXiv_CV  Image_Caption  Transformer  Embedding  Knowledge  Classification  VQA  Caption  Inference  QA  PDF
• 2021-04-16 Improving Zero-Shot Multi-Lingual Entity Linking    Elliot Schumacher, James Mayfield, Mark Dredze arXiv_CL arXiv_CL  Transformer  Zero-Shot  Knowledge  Adversarial  Pose  Matching  PDF
• 2021-04-16 Self-supervised Video Retrieval Transformer Network    Xiangteng He, Yulin Pan, Mingqian Tang, Yiliang Lv arXiv_CV arXiv_CV  Transformer  Self-Supervised  Pose  Action  Video_Retrieval  PDF
• 2021-04-16 A Million Tweets Are Worth a Few Points: Tuning Transformers for Customer Service Tasks    Amir Hadifar, Sofie Labat, Véronique Hoste, Chris Develder, Thomas Demeester arXiv_AI arXiv_AI  Transformer  PDF
• 2021-04-16 Generating Bug-Fixes Using Pretrained Transformers    Dawn Drain, Chen Wu, Alexey Svyatkovskiy, Neel Sundaresan arXiv_CL arXiv_CL  Transformer  Embedding  Pose  Detection  Denoising  PDF
• 2021-04-16 Comparison of Grammatical Error Correction Using Back-Translation Models    Aomi Koyama, Kengo Hotate, Masahiro Kaneko, Mamoru Komachi arXiv_CL arXiv_CL  Transformer  RNN  PDF
• 2021-04-16 Investigating Failures of Automatic Translation in the Case of Unambiguous Gender    Adithya Renduchintala, Adina Williams arXiv_CL arXiv_CL  Transformer  NMT  PDF
• 2021-04-16 A Masked Segmental Language Model for Unsupervised Natural Language Segmentation    C.M. Downey, Fei Xia, Gina-Anne Levow, Shane Steinert-Threlkeld arXiv_CL arXiv_CL  Transformer  Segmentation  Unsupervised  Speech  Pose  Attention  Language_Model  PDF
• 2021-04-15 Rethinking Text Line Recognition Models    Daniel Hernandez Diaz, Siyang Qin, Reeve Ingle, Yasuhisa Fujii, Alessandro Bissacco arXiv_CV arXiv_CV  Transformer  Recognition  RNN  Pose  Classification  Attention  Language_Model  PDF
• 2021-04-15 Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?    Eric Lehman, Sarthak Jain, Karl Pichotta, Yoav Goldberg, Byron C. Wallace arXiv_AI arXiv_AI  Transformer  Bert  PDF
• 2021-04-15 Syntax-Aware Graph-to-Graph Transformer for Semantic Role Labelling    Alireza Mohammadshahi, James Henderson arXiv_CL arXiv_CL  Transformer  Embedding  Pose  Relation  Attention  PDF
• 2021-04-15 Self-supervised Video Object Segmentation by Motion Grouping    Charig Yang, Hala Lamdouar, Erika Lu, Andrew Zisserman, Weidi Xie arXiv_CV arXiv_CV  Transformer  Segmentation  Self-Supervised  Pose  Optical_Flow  PDF
• 2021-04-15 Geometry-Free View Synthesis: Transformers and no 3D Priors    Robin Rombach, Patrick Esser, Björn Ommer arXiv_CV arXiv_CV  Transformer  3D  Relation  Attention  PDF
• 2021-04-15 Demystify Optimization Challenges in Multilingual Transformers    Xian Li, Hongyu Gong arXiv_AI arXiv_AI  Transformer  Optimization  Pose  Face  PDF
• 2021-04-15 Time-Stamped Language Model: Teaching Language Models to Understand the Flow of Events    Hossein Rajaby Faghihi, Parisa Kordjamshidi arXiv_AI arXiv_AI  Transformer  Tracking  Pose  Language_Model  Prediction  QA  PDF
• 2021-04-15 Gradient-based Adversarial Attacks against Text Transformers    Chuan Guo, Alexandre Sablayrolles, Hervé Jégou, Douwe Kiela arXiv_AI arXiv_AI  Transformer  Optimization  Adversarial  Pose  PDF
• 2021-04-15 Planning with Entity Chains for Abstractive Summarization    Shashi Narayan, Yao Zhao, Joshua Maynez, Gonçalo Simoes, Ryan McDonald arXiv_CL arXiv_CL  Transformer  Pose  Summarization  Text_Generation  PDF
• 2021-04-15 Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models    Matteo Alleman, Jonathan Mamou, Miguel A Del Rio, Hanlin Tang, Yoon Kim, SueYeon Chung arXiv_CL arXiv_CL  Transformer  Deep_Learning  Language_Model  PDF
• 2021-04-15 Hierarchical Learning for Generation with Long Source Sequences    Tobias Rohde, Xiaoxia Wu, Yinhan Liu arXiv_CL arXiv_CL  Transformer  Classification  Attention  Summarization  PDF
• 2021-04-15 Spectrogram Inpainting for Interactive Generation of Instrument Sounds    Théis Bazin, Gaëtan Hadjeres, Philippe Esling, Mikhail Malt arXiv_AI arXiv_AI  Transformer  Inpainting  Pose  Face  PDF
• 2021-04-15 A Sample-Based Training Method for Distantly Supervised Relation Extraction with Pre-Trained Transformers    Mehrdad Nasser, Mohamad Bagher Sajadi, Behrouz Minaei-Bidgoli arXiv_AI arXiv_AI  Transformer  Bert  Pose  Action  Relation  Relation_Extraction  Prediction  PDF
• 2021-04-15 Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching    Wenxin Hou, Jindong Wang, Xu Tan, Tao Qin, Takahiro Shinozaki arXiv_SD arXiv_SD  Transformer  Unsupervised  Recognition  Speech  Pose  Classification  Speech_Recognition  Matching  PDF
• 2021-04-15 The Role of Context in Detecting Previously Fact-Checked Claims    Shaden Shaar, Firoj Alam, Giovanni Da San Martino, Preslav Nakov arXiv_AI arXiv_AI  Transformer  Pose  PDF
• 2021-04-15 TransRPPG: Remote Photoplethysmography Transformer for 3D Mask Face Presentation Attack Detection    Zitong Yu, Xiaobai Li, Pichao Wang, Guoying Zhao arXiv_CV arXiv_CV  Transformer  Recognition  3D  Knowledge  Pose  Face  Deep_Learning  Detection  Relation  Face_Recognition  Prediction  PDF
• 2021-04-15 BERT based Transformers lead the way in Extraction of Health Information from Social Media    Sidharth R, Abhiraj Tiwari, Parthivi Choubey, Saisha Kashyap, Sahil Khose, Kumud Lakara, Nishesh Singh, Ujjwal Verma arXiv_CL arXiv_CL  Transformer  Bert  Action  Classification  PDF
• 2021-04-15 Adaptive Sparse Transformer for Multilingual Translation    Hongyu Gong, Xian Li, Dmitriy Genzel arXiv_CL arXiv_CL  Transformer  Sparse  Knowledge  Pose  Attention  Inference  PDF
• 2021-04-15 Shoulder Implant X-Ray Manufacturer Classification: Exploring with Vision Transformer    Meng Zhou, Shanglin Mo arXiv_CV arXiv_CV  Transformer  Classification  PDF
• 2021-04-15 TorontoCL at CMCL 2021 Shared Task: RoBERTa with Multi-Stage Fine-Tuning for Eye-Tracking Prediction    Bai Li, Frank Rudzicz arXiv_CL arXiv_CL  Transformer  Tracking  Bert  Prediction  PDF
• 2021-04-15 Vision Transformer using Low-level Chest X-ray Feature Corpus for COVID-19 Diagnosis and Severity Quantification    Sangjoon Park, Gwanghyun Kim, Yujin Oh, Joon Beom Seo, Sang Min Lee, Jin Hwan Kim, Sungjun Moon, Jae-Kwang Lim, Jong Chul Ye arXiv_CV arXiv_CV  Transformer  Embedding  Pose  Attention  PDF
• 2021-04-15 Text Guide: Improving the quality of long text classification by a text selection method based on feature importance    Krzysztof Fiok (1), Waldemar Karwowski (1), Edgar Gutierrez (1) (2), Mohammad Reza Davahli (1), Maciej Wilamowski (3), Tareq Ahram (1), Awad Al-Juaid (4), Jozef Zurada (5) ((1) Department of Industrial Engineering and Management Systems, University of Central Florida, USA, (2) Center for Latin-American Logistics Innovation, LOGyCA, Bogota, Colombia (3) Faculty of Economic Sciences, University of Warsaw, Warsaw, Poland (4) Department of Industrial Engineering, College of Engineering, Taif University, Saudi Arabia (5) Business School, University of Louisville, USA) arXiv_AI arXiv_AI  Transformer  Text_Classification  Optimization  Pose  Classification  Attention  Language_Model  PDF
• 2021-04-15 Low-Resource Task-Oriented Semantic Parsing via Intrinsic Modeling    Shrey Desai, Akshat Shrivastava, Alexander Zotov, Ahmed Aly arXiv_CL arXiv_CL  Transformer  Ontology  PDF
• 2021-04-15 Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models    Yuxuan Lai, Yijia Liu, Yansong Feng, Songfang Huang, Dongyan Zhao arXiv_CL arXiv_CL  Transformer  Bert  Pose  Attention  Language_Model  Prediction  PDF
• 2021-04-14 Disentangling Representations of Text by Masking Transformers    Xiongyi Zhang, Jan-Willem van de Meent, Byron C. Wallace arXiv_CL arXiv_CL  Transformer  Bert  Sparse  Review  Adversarial  Pose  Sentiment  PDF
• 2021-04-14 TWEAC: Transformer with Extendable QA Agent Classifiers    Gregor Geigle, Nils Reimers, Andreas Rücklé, Iryna Gurevych arXiv_CL arXiv_CL  Transformer  Unsupervised  Knowledge  Pose  QA  PDF
• 2021-04-14 Reformulating Sentence Ordering as Conditional Text Generation    Somnath Basu Roy Chowdhury, Faeze Brahman, Snigdha Chaturvedi arXiv_CL arXiv_CL  Transformer  Zero-Shot  Relation  GAN  Text_Generation  PDF
• 2021-04-14 Predicting Discourse Trees from Transformer-based Neural Summarizers    Wen Xiao, Patrick Huber, Giuseppe Carenini arXiv_CL arXiv_CL  Transformer  Attention  Summarization  PDF
• 2021-04-14 Sparse Attention with Linear Units    Biao Zhang, Ivan Titov, Rico Sennrich arXiv_CL arXiv_CL  Transformer  Sparse  Pose  Attention  PDF
• 2021-04-14 UPB at SemEval-2021 Task 1: Combining Deep Learning and Hand-Crafted Features for Lexical Complexity Prediction    George-Eduard Zaharia, Dumitru-Clementin Cercel, Mihai Dascalu arXiv_CL arXiv_CL  Transformer  Embedding  Deep_Learning  Relation  CNN  Language_Model  Prediction  PDF
• 2021-04-14 TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning    Kexin Wang, Nils Reimers, Iryna Gurevych arXiv_CL arXiv_CL  Transformer  Embedding  Unsupervised  Knowledge  Pose  Denoising  Language_Model  PDF
• 2021-04-14 Pose Recognition with Cascade Transformers    Ke Li, Shijie Wang, Xiang Zhang, Yifan Xu, Weijian Xu, Zhuowen Tu arXiv_CV arXiv_CV  Transformer  Recognition  Pose  Detection  Attention  PDF
• 2021-04-14 K-PLUG: Knowledge-injected Pre-trained Language Model for Natural Language Understanding and Generation in E-Commerce    Song Xu, Haoran Li, Peng Yuan, Yujia Wang, Youzheng Wu, Xiaodong He, Ying Liu, Bowen Zhou arXiv_CL arXiv_CL  Transformer  Knowledge  Self-Supervised  Pose  Summarization  Language_Model  PDF
• 2021-04-14 The Surprising Performance of Simple Baselines for Misinformation Detection    Kellin Pelrine, Jacob Danovitch, Reihaneh Rabbany arXiv_CL arXiv_CL  Transformer  RNN  Pose  Detection  Language_Model  PDF
• 2021-04-14 Knowledge-driven Answer Generation for Conversational Search    Mariana Leite, Rafael Ferreira, David Semedo, João Magalhães arXiv_CL arXiv_CL  Transformer  Salient  Knowledge  Knowledge_Graph  Pose  PDF
• 2021-04-14 Dependency Parsing based Semantic Representation Learning with Graph Neural Network for Enhancing Expressiveness of Text-to-Speech    Yixuan Zhou, Changhe Song, Jingbei Li, Zhiyong Wu, Helen Meng arXiv_CL arXiv_CL  Transformer  Embedding  Bert  Represenation_Learning  Speech  Pose  Relation  PDF
• 2021-04-14 Non-autoregressive sequence-to-sequence voice conversion    Tomoki Hayashi, Wen-Chin Huang, Kazuhiro Kobayashi, Tomoki Toda arXiv_CL arXiv_CL  Transformer  Speech  Pose  PDF
• 2021-04-14 VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers    Sharif Amit Kamran, Khondker Fariha Hossain, Alireza Tavakkoli, Stewart Lee Zuckerbrod, Kenton M. Sanders, Salah A. Baker arXiv_CV arXiv_CV  Transformer  Adversarial  Pose  Action  GAN  Prediction  PDF
• 2021-04-14 Towards BERT-based Automatic ICD Coding: Limitations and Opportunities    Damian Pascual, Sandro Luck, Roger Wattenhofer arXiv_AI arXiv_AI  Transformer  Bert  Classification  Medical  PDF
• 2021-04-14 NAREOR: The Narrative Reordering Problem    Varun Gangal, Steven Y. Feng, Eduard Hovy, Teruko Mitamura arXiv_AI arXiv_AI  Transformer  Pose  PDF
• 2021-04-14 Decoupled Spatial-Temporal Transformer 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  Deep_Learning  Attention  PDF
• 2021-04-14 AR-LSAT: Investigating Analytical Reasoning of Text    Wanjun Zhong, Siyuan Wang, Duyu Tang, Zenan Xu, Daya Guo, Jiahai Wang, Jian Yin, Ming Zhou, Nan Duan arXiv_CL arXiv_CL  Transformer  Knowledge  Language_Model  PDF
• 2021-04-13 Simultaneous Face Hallucination and Translation for Thermal to Visible Face Verification using Axial-GAN    Rakhil Immidisetti, Shuowen Hu, Vishal M. Patel arXiv_CV arXiv_CV  Transformer  Surveillance  Adversarial  Pose  Face  Attention  GAN  Matching  PDF
• 2021-04-13 BERT Embeddings Can Track Context in Conversational Search    Rafael Ferreira, David Semedo, Joao Magalhaes arXiv_CL arXiv_CL  Transformer  Embedding  Tracking  Bert  Pose  Action  PDF
• 2021-04-13 Can a Transformer Pass the Wug Test? Tuning Copying Bias in Neural Morphological Inflection Models    Ling Liu, Mans Hulden arXiv_CL arXiv_CL  Transformer  Deep_Learning  Attention  PDF
• 2021-04-13 ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration    Junyu Chen, Yufan He, Eric C. Frey, Ye Li, Yong Du arXiv_CV arXiv_CV  Transformer  Segmentation  Unsupervised  Pose  Classification  Relation  Attention  Medical  CNN  Image_Classification  PDF
• 2021-04-13 Co-Scale Conv-Attentional Image Transformers    Weijian Xu, Yifan Xu, Tyler Chang, Zhuowen Tu arXiv_CV arXiv_CV  Transformer  Segmentation  Embedding  Classification  Detection  Object_Detection  Attention  CNN  PDF
• 2021-04-13 A State-of-the-art Survey of Artificial Neural Networks for Whole-slide Image Analysis:from Popular Convolutional Neural Networks to Potential Visual Transformers    Chen Li, Xintong Li, Xiaoyan Li, Md Mamunur Rahaman, Xiaoqi Li, Jian Wu, Yudong Yao, Marcin Grzegorzek arXiv_CV arXiv_CV  Transformer  Segmentation  Review  Survey  Classification  Detection  CNN  PDF
• 2021-04-13 UAV-ReID: A Benchmark on Unmanned Aerial Vehicle Re-identification    Daniel Organisciak, Brian K. S. Isaac-Medina, Matthew Poyser, Shanfeng Hu, Toby P. Breckon, Hubert P. H. Shum arXiv_CV arXiv_CV  Transformer  Tracking  Knowledge  Pose  Deep_Learning  Re-identification  PDF
• 2021-04-13 Understanding Transformers for Bot Detection in Twitter    Andres Garcia-Silva, Cristian Berrio, Jose Manuel Gomez-Perez arXiv_CL arXiv_CL  Transformer  Bert  Classification  Detection  Language_Model  PDF
• 2021-04-13 What's in your Head? Emergent Behaviour in Multi-Task Transformer Models    Mor Geva, Uri Katz, Aviv Ben-Arie, Jonathan Berant arXiv_CL arXiv_CL  Transformer  Action  Summarization  Language_Model  Prediction  PDF
• 2021-04-13 UPB at SemEval-2021 Task 7: Adversarial Multi-Task Learning for Detecting and Rating Humor and Offense    Răzvan-Alexandru Smădu, Dumitru-Clementin Cercel, Mihai Dascalu arXiv_AI arXiv_AI  Transformer  Embedding  Bert  Text_Classification  RNN  Adversarial  Classification  PDF
• 2021-04-13 Transformer-based Methods for Recognizing Ultra Fine-grained Entities    Emanuela Boros, Antoine Doucet arXiv_CL arXiv_CL  Transformer  Recognition  Action  Language_Model  PDF
• 2021-04-13 Structural analysis of an all-purpose question answering model    Vincent Micheli, Quentin Heinrich, François Fleuret, Wacim Belblidia arXiv_CL arXiv_CL  Transformer  Pose  Attention  Language_Model  PDF
• 2021-04-13 Lessons on Parameter Sharing across Layers in Transformers    Sho Takase, Shun Kiyono arXiv_CL arXiv_CL  Transformer  Pose  PDF
• 2021-04-13 Semantic maps and metrics for science Semantic maps and metrics for science using deep transformer encoders    Brendan Chambers, James Evans arXiv_AI arXiv_AI  Transformer  Embedding  Bert  Face  PDF
• 2021-04-12 Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Machine Translation    Zhong Zhou, Alex Waibel arXiv_AI arXiv_AI  Transformer  Medical  PDF
• 2021-04-12 Paragraph-level Simplification of Medical Texts    Ashwin Devaraj, Iain J. Marshall, Byron C. Wallace, Junyi Jessy Li arXiv_CL arXiv_CL  Transformer  Pose  Medical  Language_Model  PDF
• 2021-04-12 Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble    Giorgos Tziafas, Konstantinos Kogkalidis, Tommaso Caselli arXiv_CL arXiv_CL  Transformer  Bert  Detection  Prediction  PDF
• 2021-04-12 LocalViT: Bringing Locality to Vision Transformers    Yawei Li, Kai Zhang, Jiezhang Cao, Radu Timofte, Luc Van Gool arXiv_CV arXiv_CV  Transformer  Embedding  Action  Classification  Attention  PDF
• 2021-04-12 Escaping the Big Data Paradigm with Compact Transformers    Ali Hassani, Steven Walton, Nikhil Shah, Abulikemu Abuduweili, Jiachen Li, Humphrey Shi arXiv_CV arXiv_CV  Transformer  Embedding  OCR  PDF
• 2021-04-12 Action-Conditioned 3D Human Motion Synthesis with Transformer VAE    Mathis Petrovich, Michael J. Black, Gül Varol arXiv_CV arXiv_CV  Transformer  Recognition  3D  Pose  Action_Recognition  Action  Denoising  PDF
• 2021-04-12 DATE: Detecting Anomalies in Text via Self-Supervision of Transformers    Andrei Manolache, Florin Brad, Elena Burceanu arXiv_CL arXiv_CL  Transformer  Unsupervised  Self-Supervised  Quantitative  Deep_Learning  Detection  PDF
• 2021-04-12 GAttANet: Global attention agreement for convolutional neural networks    Rufin VanRullen, Andrea Alamia arXiv_CV arXiv_CV  Transformer  Attention  CNN  PDF
• 2021-04-12 Cloth Interactive Transformer for Virtual Try-On    Bin Ren, Hao Tang, Fanyang Meng, Runwei Ding, Ling Shao, Philip H.S. Torr, Nicu Sebe arXiv_CV arXiv_CV  Transformer  Pose  Quantitative  Relation  Attention  Matching  PDF
• 2021-04-12 Fine-Tuning Transformers for Identifying Self-Reporting Potential Cases and Symptoms of COVID-19 in Tweets    Max Fleming, Priyanka Dondeti, Caitlin N. Dreisbach, Adam Poliak arXiv_CL arXiv_CL  Transformer  Bert  PDF
• 2021-04-12 Updater-Extractor Architecture for Inductive World State Representations    Arseny Moskvichev, James A. Liu arXiv_AI arXiv_AI  Transformer  RNN  Knowledge  Pose  PDF
• 2021-04-12 Multilingual Language Models Predict Human Reading Behavior    Nora Hollenstein, Federico Pirovano, Ce Zhang, Lena Jäger, Lisa Beinborn arXiv_CL arXiv_CL  Transformer  Tracking  Bert  Language_Model  PDF
• 2021-04-12 Improved Conformer-based End-to-End Speech Recognition Using Neural Architecture Search    Yukun Liu, Ta Li, Pengyuan Zhang, Yonghong Yan arXiv_SD arXiv_SD  Transformer  NAS  Recognition  Speech  Pose  Classification  Speech_Recognition  Image_Classification  PDF
• 2021-04-12 Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation    Chong Zhang, Jieyu Zhao, Huan Zhang, Kai-Wei Chang, Cho-Jui Hsieh arXiv_CL arXiv_CL  Transformer  Pose  Prediction  PDF
• 2021-04-12 Learning dynamic and hierarchical traffic spatiotemporal features with Transformer    Haoyang Yan, Xiaolei Ma arXiv_AI arXiv_AI  Transformer  Pose  Deep_Learning  Attention  PDF
• 2021-04-11 Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling    Aaron Mueller, Mark Dredze arXiv_CL arXiv_CL  Transformer  Embedding  Unsupervised  Zero-Shot  Pose  Classification  Prediction  PDF
• 2021-04-11 Estimating articulatory movements in speech production with transformer networks    Sathvik Udupa, Anwesha Roy, Abhayjeet Singh, Aravind Illa, Prasanta Kumar Ghosh arXiv_SD arXiv_SD  Transformer  Speech  Face  Relation  PDF
• 2021-04-11 Innovative Bert-based Reranking Language Models for Speech Recognition    Shih-Hsuan Chiu, Berlin Chen arXiv_CL arXiv_CL  Transformer  Unsupervised  Recognition  Bert  RNN  Speech  Pose  Speech_Recognition  Language_Model  Prediction  PDF
• 2021-04-11 UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost    Zhen Wu, Lijun Wu, Qi Meng, Yingce Xia, Shufang Xie, Tao Qin, Xinyu Dai, Tie-Yan Liu arXiv_CL arXiv_CL  Transformer  Bert  Text_Classification  Regularization  Pose  Classification  PDF
• 2021-04-11 Disentangled Contrastive Learning for Learning Robust Textual Representations    Xiang Chen, Xin Xie, Zhen Bi, Hongbin Ye, Shumin Deng, Ningyu Zhang, Huajun Chen arXiv_AI arXiv_AI  Transformer  Adversarial  Self-Supervised  Pose  Contrastive_Learning  PDF
• 2021-04-10 Non-autoregressive Transformer-based End-to-end ASR using BERT    Fu-Hao Yu, Kuan-Yu Chen arXiv_CL arXiv_CL  Transformer  Recognition  Bert  Speech  Pose  Attention  Speech_Recognition  Inference  Language_Model  PDF
• 2021-04-10 UTNLP at SemEval-2021 Task 5: A Comparative Analysis of Toxic Span Detection using Attention-based, Named Entity Recognition, and Ensemble Models    Alireza Salemi, Nazanin Sabri, Emad Kebriaei, Behnam Bahrak, Azadeh Shakery arXiv_CL arXiv_CL  Transformer  Embedding  Recognition  Detection  Attention  PDF
• 2021-04-10 ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser    Zhi Chen, Lu Chen, Yanbin Zhao, Ruisheng Cao, Zihan Xu, Su Zhu, Kai Yu arXiv_CL arXiv_CL  Transformer  Pose  Relation  PDF
• 2021-04-09 TransWiC at SemEval-2021 Task 2: Transformer-based Multilingual and Cross-lingual Word-in-Context Disambiguation    Hansi Hettiarachchi, Tharindu Ranasinghe arXiv_AI arXiv_AI  Transformer  Action  PDF
• 2021-04-09 WLV-RIT at SemEval-2021 Task 5: A Neural Transformer Framework for Detecting Toxic Spans    Tharindu Ranasinghe, Diptanu Sarkar, Marcos Zampieri, Alex Ororbia arXiv_AI arXiv_AI  Transformer  Detection  GAN  PDF
• 2021-04-09 Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals    Xi Ye, Rohan Nair, Greg Durrett arXiv_CL arXiv_CL  Transformer  Pose  Classification  Sentiment  Attention  Prediction  PDF
• 2021-04-09 KI-BERT: Infusing Knowledge Context for Better Language and Domain Understanding    Keyur Faldu, Amit Sheth, Prashant Kikani, Hemang Akabari arXiv_AI arXiv_AI  Transformer  Embedding  Bert  Knowledge  Knowledge_Graph  Pose  Deep_Learning  Relation  Attention  PDF
• 2021-04-09 Transformers: 'The End of History' for NLP?    Anton Chernyavskiy, Dmitry Ilvovsky, Preslav Nakov arXiv_CL arXiv_CL  Transformer  Segmentation  Bert  Pose  PDF
• 2021-04-09 BERT-based Chinese Text Classification for Emergency Domain with a Novel Loss Function    Zhongju Wang, Long Wang, Chao Huang, Xiong Luo arXiv_AI arXiv_AI  Transformer  Bert  Text_Classification  Optimization  Pose  Classification  PDF
• 2021-04-09 SI-Score: An image dataset for fine-grained analysis of robustness to object location, rotation and size    Jessica Yung, Rob Romijnders, Alexander Kolesnikov, Lucas Beyer, Josip Djolonga, Neil Houlsby, Sylvain Gelly, Mario Lucic, Xiaohua Zhai arXiv_AI arXiv_AI  Image_Caption  Transformer  Prediction  PDF
• 2021-04-08 Grapheme-to-Phoneme Transformer Model for Transfer Learning Dialects    Eric Engelhart, Mahsa Elyasi, Gaurav Bharaj arXiv_CL arXiv_CL  Transformer  Transfer_Learning  RNN  Speech  Pose  Attention  PDF
• 2021-04-08 Deep Indexed Active Learning for Matching Heterogeneous Entity Representations    Arjit Jain, Sunita Sarawagi, Prithviraj Sen arXiv_AI arXiv_AI  Transformer  Embedding  Pose  Language_Model  Matching  PDF
• 2021-04-08 Handwriting Transformers    Ankan Kumar Bhunia, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan, Mubarak Shah arXiv_CV arXiv_CV  Transformer  Handwriting  Knowledge  Pose  Quantitative  Relation  Few-Shot  Attention  Text_Generation  PDF
• 2021-04-08 On Biasing Transformer Attention Towards Monotonicity    Annette Rios, Chantal Amrhein, Noëmi Aepli, Rico Sennrich arXiv_CL arXiv_CL  Transformer  RNN  Attention  PDF
• 2021-04-08 How Transferable are Reasoning Patterns in VQA?    Corentin Kervadec, Theo Jaunet, Grigory Antipov, Moez Baccouche, Romain Vuillemot, Christian Wolf arXiv_CV arXiv_CV  Transformer  Pose  VQA  Attention  QA  PDF
• 2021-04-08 DeepProg: A Transformer-based Framework for Predicting Disease Prognosis    Huy Hoang Nguyen, Simo Saarakkala, Matthew B. Blaschko, Aleksei Tiulpin arXiv_CV arXiv_CV  Transformer  Knowledge  Pose  Deep_Learning  Prediction  PDF
• 2021-04-08 SiT: Self-supervised vIsion Transformer    Sara Atito, Muhammad Awais, Josef Kittler arXiv_CV arXiv_CV  Transformer  Self-Supervised  Pose  Action  Classification  PDF
• 2021-04-08 Layer Reduction: Accelerating Conformer-Based Self-Supervised Model via Layer Consistency    Jinchuan Tian, Rongzhi Gu, Helin Wang, Yuexian Zou arXiv_CL arXiv_CL  Transformer  Embedding  Recognition  Bert  Speech  Self-Supervised  Pose  Classification  Speech_Recognition  Inference  PDF
• 2021-04-08 Revisiting Simple Neural Probabilistic Language Models    Simeng Sun, Mohit Iyyer arXiv_CL arXiv_CL  Transformer  Embedding  Optimization  Attention  Language_Model  PDF
• 2021-04-08 Multimodal Fusion Refiner Networks    Sethuraman Sankaran, David Yang, Ser-Nam Lim arXiv_AI arXiv_AI  Transformer  Embedding  Unsupervised  Pose  Action  PDF
• 2021-04-07 Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning    Zhicheng Huang, Zhaoyang Zeng, Yupan Huang, Bei Liu, Dongmei Fu, Jianlong Fu arXiv_CV arXiv_CV  Transformer  Represenation_Learning  Salient  Pose  Action  CNN  Inference  Language_Model  PDF
• 2021-04-07 HumAID: Human-Annotated Disaster Incidents Data from Twitter    Firoj Alam, Umair Qazi, Muhammad Imran, Ferda Ofli arXiv_AI arXiv_AI  Transformer  Pose  Classification  Deep_Learning  PDF
• 2021-04-07 Facial Attribute Transformers for Precise and Robust Makeup Transfer    Zhaoyi Wan, Haoran Chen, Jielei Zhang, Wentao Jiang, Cong Yao, Jiebo Luo arXiv_AI arXiv_AI  Transformer  Pose  Face  Action  Quantitative  PDF
• 2021-04-07 FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization    Zhengkun Tian, Jiangyan Yi, Ye Bai, Jianhua Tao, Shuai Zhang, Zhengqi Wen arXiv_CL arXiv_CL  Transformer  Recognition  RNN  Regularization  Speech  Pose  Speech_Recognition  Inference  Prediction  PDF
• 2021-04-07 Deep Transformers for Fast Small Intestine Grounding in Capsule Endoscope Video    Xinkai Zhao, Chaowei Fang, Feng Gao, De-Jun Fan, Xutao Lin, Guanbin Li arXiv_CV arXiv_CV  Transformer  Pose  Classification  Medical  PDF
• 2021-04-07 Interpreting A Pre-trained Model Is A Key For Model Architecture Optimization: A Case Study On Wav2Vec 2.0    Liu Chen, Meysam Asgari arXiv_CL arXiv_CL  Transformer  NAS  Optimization  Speech  Pose  Attention  Language_Model  PDF
• 2021-04-07 LI-Net: Large-Pose Identity-Preserving Face Reenactment Network    Jin Liu, Peng Chen, Tao Liang, Zhaoxing Li, Cai Yu, Shuqiao Zou, Jiao Dai, Jizhong Han arXiv_AI arXiv_AI  Transformer  Facial_Landmark  Pose  Face  Quantitative  PDF
• 2021-04-07 Better Neural Machine Translation by Extracting Linguistic Information from BERT    Hassan S. Shavarani, Anoop Sarkar arXiv_CL arXiv_CL  Transformer  Embedding  Bert  NMT  PDF
• 2021-04-06 Fourier Image Transformer    Tim-Oliver Buchholz, Florian Jug arXiv_CV arXiv_CV  Image_Caption  Transformer  Reconstruction  Pose  Classification  CNN  Image_Classification  PDF
• 2021-04-06 LT-LM: a novel non-autoregressive language model for single-shot lattice rescoring    Anton Mitrofanov, Mariya Korenevskaya, Ivan Podluzhny, Yuri Khokhlov, Aleksandr Laptev, Andrei Andrusenko, Aleksei Ilin, Maxim Korenevsky, Ivan Medennikov, Aleksei Romanenko arXiv_CL arXiv_CL  Transformer  Recognition  RNN  Speech  Pose  Speech_Recognition  Language_Model  PDF
• 2021-04-06 Deep Animation Video Interpolation in the Wild    Li Siyao, Shiyu Zhao, Weijiang Yu, Wenxiu Sun, Dimitris N. Metaxas, Chen Change Loy, Ziwei Liu arXiv_CV arXiv_CV  Transformer  Pose  Prediction  Matching  PDF
• 2021-04-06 Extremely Low Footprint End-to-End ASR System for Smart Device    Zhifu Gao, Yiwu Yao, Shiliang Zhang, Jun Yang, Ming Lei, Ian McLoughlin arXiv_SD arXiv_SD  Transformer  Quantization  Recognition  Speech  Pose  Attention  Speech_Recognition  Language_Model  PDF
• 2021-04-06 CodeTrans: Towards Cracking the Language of Silicone's Code Through Self-Supervised Deep Learning and High Performance Computing    Ahmed Elnaggar, Wei Ding, Llion Jones, Tom Gibbs, Tamas Feher, Christoph Angerer, Silvia Severini, Florian Matthes, Burkhard Rost arXiv_AI arXiv_AI  Transformer  Transfer_Learning  Self-Supervised  Deep_Learning  PDF
• 2021-04-06 Few-Shot Transformation of Common Actions into Time and Space    Pengwan Yang, Pascal Mettes, Cees G. M. Snoek arXiv_CV arXiv_CV  Transformer  Action_Localization  Action  Few-Shot  GAN  Prediction  PDF
• 2021-04-06 Variational Transformer Networks for Layout Generation    Diego Martin Arroyo, Janis Postels, Federico Tombari arXiv_CV arXiv_CV  Transformer  Pose  Face  Detection  Relation  Attention  PDF
• 2021-04-06 Learning to Estimate Hidden Motions with Global Motion Aggregation    Shihao Jiang, Dylan Campbell, Yao Lu, Hongdong Li, Richard Hartley arXiv_CV arXiv_CV  Transformer  Pose  Optical_Flow  PDF
• 2021-04-06 MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms    Kai Middlebrook, Shyam Sudhakaran, David Guy Brizan arXiv_SD arXiv_SD  Transformer  Recognition  Bert  Pose  Action  Attention  CNN  PDF
• 2021-04-06 ODE Transformer: An Ordinary Differential Equation-Inspired Model for Neural Machine Translation    Bei Li, Quan Du, Tao Zhou, Shuhan Zhou, Xin Zeng, Tong Xiao, Jingbo Zhu arXiv_CL arXiv_CL  Transformer  Relation  PDF
• 2021-04-06 Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression    Zigang Geng, Ke Sun, Bin Xiao, Zhaoxiang Zhang, Jingdong Wang arXiv_CV arXiv_CV  Transformer  Pose_Estimation  Pose  Detection  PDF
• 2021-04-06 When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenes    Philipp Bomatter, Mengmi Zhang, Dimitar Karev, Spandan Madan, Claire Tseng, Gabriel Kreiman arXiv_AI arXiv_AI  Transformer  Recognition  3D  Pose  Attention  PDF
• 2021-04-06 Attention Head Masking for Inference Time Content Selection in Abstractive Summarization    Shuyang Cao, Lu Wang arXiv_CL arXiv_CL  Transformer  Salient  Relation  Attention  Summarization  Inference  PDF
• 2021-04-05 Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding    Suyoun Kim, Abhinav Arora, Duc Le, Ching-Feng Yeh, Christian Fuegen, Ozlem Kalinli, Michael L. Seltzer arXiv_CL arXiv_CL  Transformer  Embedding  Recognition  Bert  Speech  Pose  Speech_Recognition  Language_Model  PDF
• 2021-04-05 End-to-End Speaker-Attributed ASR with Transformer    Naoyuki Kanda, Guoli Ye, Yashesh Gaur, Xiaofei Wang, Zhong Meng, Zhuo Chen, Takuya Yoshioka arXiv_CL arXiv_CL  Transformer  Recognition  RNN  Speech  Pose  Attention  Speech_Recognition  PDF
• 2021-04-05 Efficient Attentions for Long Document Summarization    Luyang Huang, Shuyang Cao, Nikolaus Parulian, Heng Ji, Lu Wang arXiv_CL arXiv_CL  Transformer  Salient  Pose  Attention  Summarization  PDF
• 2021-04-05 Compressing Visual-linguistic Model via Knowledge Distillation    Zhiyuan Fang, Jianfeng Wang, Xiaowei Hu, Lijuan Wang, Yezhou Yang, Zicheng Liu arXiv_AI arXiv_AI  Image_Caption  Transformer  Knowledge  Pose  Detection  VQA  Object_Detection  Attention  Caption  QA  PDF
• 2021-04-05 An Empirical Study of Training Self-Supervised Visual Transformers    Xinlei Chen, Saining Xie, Kaiming He arXiv_CV arXiv_CV  Transformer  Self-Supervised  CNN  PDF
• 2021-04-05 Exploring Transformers in Emotion Recognition: a comparison of BERT, DistillBERT, RoBERTa, XLNet and ELECTRA    Diogo Cortiz arXiv_CL arXiv_CL  Transformer  Recognition  Bert  Emotion  Language_Model  PDF
• 2021-04-05 Automating Transfer Credit Assessment in Student Mobility -- A Natural Language Processing-based Approach    Dhivya Chandrasekaran, Vijay Mago arXiv_AI arXiv_AI  Transformer  Knowledge  Pose  PDF
• 2021-04-05 AST: Audio Spectrogram Transformer    Yuan Gong, Yu-An Chung, James Glass arXiv_AI arXiv_AI  Transformer  Speech  Classification  Attention  CNN  PDF
• 2021-04-05 A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification    Xuehu Liu, Pingping Zhang, Chenyang Yu, Huchuan Lu, Xuesheng Qian, Xiaoyun Yang arXiv_AI arXiv_AI  Transformer  Person_Re-identification  Enhancement  Pose  Relation  Re-identification  PDF
• 2021-04-05 Explainability-aided Domain Generalization for Image Classification    Robin M. Schmidt arXiv_CV arXiv_CV  Transformer  Pose  Classification  Attention  Image_Classification  Prediction  PDF
• 2021-04-05 Towards Automated Psychotherapy via Language Modeling    Houjun Liu arXiv_CL arXiv_CL  Transformer  Language_Model  PDF
• 2021-04-05 Inference Time Style Control for Summarization    Shuyang Cao, Lu Wang arXiv_CL arXiv_CL  Transformer  Pose  Summarization  Inference  Prediction  PDF
• 2021-04-04 KnowGraph@IITK at SemEval-2021 Task 11: Building KnowledgeGraph for NLP Research    Shashank Shailabh, Sajal Chaurasia, Ashutosh Modi arXiv_CL arXiv_CL  Transformer  Bert  RNN  Knowledge  Knowledge_Graph  Pose  Action  Language_Model  Prediction  PDF
• 2021-04-04 TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling    Tze Yuang Chong, Xuyang Wang, Lin Yang, Junjie Wang arXiv_CL arXiv_CL  Transformer  Recognition  RNN  Speech  Pose  Attention  Speech_Recognition  Language_Model  PDF
• 2021-04-04 Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks    Endri Kacupaj, Joan Plepi, Kuldeep Singh, Harsh Thakkar, Jens Lehmann, Maria Maleshkova arXiv_CL arXiv_CL  Transformer  Recognition  Knowledge  Knowledge_Graph  Pose  Relation  Attention  PDF
• 2021-04-04 MCL@IITK at SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation using Augmented Data, Signals, and Transformers    Rohan Gupta, Jay Mundra, Deepak Mahajan, Ashutosh Modi arXiv_CL arXiv_CL  Transformer  Bert  Zero-Shot  Pose  Classification  Language_Model  PDF
• 2021-04-04 IITK@Detox at SemEval-2021 Task 5: Semi-Supervised Learning and Dice Loss for Toxic Spans Detection    Archit Bansal, Abhay Kaushik, Ashutosh Modi arXiv_CL arXiv_CL  Transformer  Pose  Detection  Language_Model  PDF
• 2021-04-04 IndT5: A Text-to-Text Transformer for 10 Indigenous Languages    El Moatez Billah Nagoudi, Wei-Rui Chen, Muhammad Abdul-Mageed, Hasan Cavusogl arXiv_CL arXiv_CL  Transformer  Language_Model  PDF
• 2021-04-04 TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition    Zhengkun Tian, Jiangyan Yi, Jianhua Tao, Ye Bai, Shuai Zhang, Zhengqi Wen, Xuefei Liu arXiv_CL arXiv_CL  Transformer  Recognition  RNN  Knowledge  Speech  Pose  Face  Attention  Speech_Recognition  Inference  PDF
• 2021-04-03 MMBERT: Multimodal BERT Pretraining for Improved Medical VQA    Yash Khare, Viraj Bagal, Minesh Mathew, Adithi Devi, U Deva Priyakumar, CV Jawahar arXiv_CV arXiv_CV  Transformer  Bert  Self-Supervised  Pose  VQA  Attention  Medical  Caption  Language_Model  QA  PDF
• 2021-04-03 Deepfake Detection Scheme Based on Vision Transformer and Distillation    Young-Jin Heo, Young-Ju Choi, Young-Woon Lee, Byung-Gyu Kim arXiv_AI arXiv_AI  Transformer  Embedding  Adversarial  Pose  Deep_Learning  Detection  GAN  CNN  PDF
• 2021-04-03 Cross-Modal learning for Audio-Visual Video Parsing    Jatin Lamba, Abhishek, Jayaprakash Akula, Rishabh Dabral, Preethi Jyothi, Ganesh Ramakrishnan arXiv_CV arXiv_CV  Transformer  Adversarial  Self-Supervised  Pose  Attention  PDF
• 2021-04-03 Efficient DETR: Improving End-to-End Object Detector with Dense Prior    Zhuyu Yao, Jiangbo Ai, Boxun Li, Chi Zhang arXiv_CV arXiv_CV  Transformer  Sparse  Pose  Detection  Object_Detection  PDF
• 2021-04-02 SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model    Edresson Casanova, Christopher Shulby, Eren Gölge, Nicolas Michael Müller, Frederico Santos de Oliveira, Arnaldo Candido Junior, Anderson da Silva Soares, Sandra Maria Aluisio, Moacir Antonelli Ponti arXiv_SD arXiv_SD  Transformer  Zero-Shot  Speech  Pose  GAN  CNN  PDF
• 2021-04-02 Using GPT-2 to Create Synthetic Data to Improve the Prediction Performance of NLP Machine Learning Classification Models    Dewayne Whitfield arXiv_CL arXiv_CL  Transformer  Transfer_Learning  Review  Pose  Classification  CNN  Prediction  PDF
• 2021-04-02 LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference    Ben Graham, Alaaeldin El-Nouby, Hugo Touvron, Pierre Stock, Armand Joulin, Hervé Jégou, Matthijs Douze arXiv_CV arXiv_CV  Transformer  Pose  Classification  Attention  CNN  Image_Classification  Inference  PDF
• 2021-04-02 Language-based Video Editing via Multi-Modal Multi-Level Transformer    Tsu-Jui Fu, Xin Eric Wang, Scott T. Grafton, Miguel P. Eckstein, William Yang Wang arXiv_CV arXiv_CV  Transformer  Video_Caption  Knowledge  Pose  PDF
• 2021-04-02 Effect of depth order on iterative nested named entity recognition models    Perceval Wajsburt, Yoann Taillé, Xavier Tannier arXiv_CL arXiv_CL  Transformer  Recognition  Pose  Action  Medical  Prediction  PDF
• 2021-04-02 TubeR: Tube-Transformer for Action Detection    Jiaojiao Zhao, Arthur Li, Chunhui Liu, Shuai Bing, Hao Chen, Cees G.M. Snoek, Joseph Tighe arXiv_CV arXiv_CV  Transformer  Embedding  Tracking  Video_Caption  Pose  Action  Detection  PDF
• 2021-04-02 VisQA: X-raying Vision and Language Reasoning in Transformers    Theo Jaunet, Corentin Kervadec, Romain Vuillemot, Grigory Antipov, Moez Baccouche, Christian Wolf arXiv_CV arXiv_CV  Transformer  Pose  Deep_Learning  VQA  Attention  Prediction  QA  PDF
• 2021-04-02 AAformer: Auto-Aligned Transformer for Person Re-Identification    Kuan Zhu, Haiyun Guo, Shiliang Zhang, Yaowei Wang, Gaopan Huang, Honglin Qiao, Jing Liu, Jinqiao Wang, Ming Tang arXiv_CV arXiv_CV  Transformer  Embedding  Person_Re-identification  Pose  Classification  Detection  Object_Detection  Attention  Re-identification  CNN  Image_Classification  PDF
• 2021-04-02 TFill: Image Completion via a Transformer-Based Architecture    Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai arXiv_CV arXiv_CV  Transformer  Pose  Action  Relation  Attention  Prediction  PDF
• 2021-04-01 Low-Resource Language Modelling of South African Languages    Stuart Mesham, Luc Hayward, Jared Shapiro, Jan Buys arXiv_CL arXiv_CL  Transformer  RNN  Language_Model  PDF
• 2021-04-01 Keyword Transformer: A Self-Attention Model for Keyword Spotting    Axel Berg, Mark O'Connor, Miguel Tairum Cruz arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Attention  Speech_Recognition  CNN  PDF
• 2021-04-01 Canonical and Surface Morphological Segmentation for Nguni Languages    Tumi Moeng, Sheldon Reay, Aaron Daniels, Jan Buys arXiv_CL arXiv_CL  Transformer  Segmentation  Unsupervised  RNN  Face  Attention  Language_Model  PDF
• 2021-04-01 Multitarget Tracking with Transformers    Juliano Pinto, Georg Hess, William Ljungbergh, Yuxuan Xia, Lennart Svensson, Henk Wymeersch arXiv_RO arXiv_RO  Transformer  Surveillance  Tracking  Knowledge  Pose  Autonomous  PDF
• 2021-04-01 ProcessTransformer: Predictive Business Process Monitoring with Transformer Network    Zaharah A. Bukhsh, Aaqib Saeed, Remco M. Dijkman arXiv_AI arXiv_AI  Transformer  Pose  Deep_Learning  Attention  Activity  Prediction  PDF
• 2021-04-01 LoFTR: Detector-Free Local Feature Matching with Transformers    Jiaming Sun, Zehong Shen, Yuang Wang, Hujun Bao, Xiaowei Zhou arXiv_CV arXiv_CV  Transformer  Pose  Detection  Object_Detection  Attention  Matching  PDF
• 2021-04-01 Group-Free 3D Object Detection via Transformers    Ze Liu, Zheng Zhang, Yue Cao, Han Hu, Xin Tong arXiv_CV arXiv_CV  Transformer  Point_Cloud  3D  Pose  Detection  Object_Detection  Attention  PDF
• 2021-04-01 Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis    Ajay Jain, Matthew Tancik, Pieter Abbeel arXiv_AI arXiv_AI  Transformer  Reconstruction  3D  Pose  Few-Shot  PDF
• 2021-04-01 WakaVT: A Sequential Variational Transformer for Waka Generation    Yuka Takeishi, Mingxuan Niu, Jing Luo, Zhong Jin, Xinyu Yang arXiv_AI arXiv_AI  Transformer  Knowledge  Pose  Attention  PDF
• 2021-04-01 Target Transformed Regression for Accurate Tracking    Yutao Cui, Cheng Jiang, Limin Wang, Gangshan Wu arXiv_CV arXiv_CV  Transformer  Tracking  Pose  Relation  Matching  PDF
• 2021-04-01 TrajeVAE -- Controllable Human Motion Generation from Trajectories    Kacper Kania, Marek Kowalski, Tomasz Trzciński arXiv_AI arXiv_AI  Transformer  3D  Pose  Prediction  PDF
• 2021-04-01 Mesh Graphormer    Kevin Lin, Lijuan Wang, Zicheng Liu arXiv_CV arXiv_CV  Transformer  Reconstruction  3D  Pose  Action  Attention  CNN  PDF
• 2021-04-01 Spatial-Temporal Graph Transformer for Multiple Object Tracking    Peng Chu, Jiang Wang, Quanzeng You, Haibin Ling, Zicheng Liu arXiv_CV arXiv_CV  Transformer  Tracking  Sparse  Object_Tracking  Pose  Action  Detection  PDF
• 2021-03-31 Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognition    Timo Lohrenz, Zhengyang Li, Tim Fingscheidt arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Attention  Speech_Recognition  Inference  Language_Model  PDF
• 2021-03-31 Going deeper with Image Transformers    Hugo Touvron, Matthieu Cord, Alexandre Sablayrolles, Gabriel Synnaeve, Hervé Jégou arXiv_CV arXiv_CV  Transformer  Optimization  Classification  CNN  Image_Classification  PDF
• 2021-03-31 Learning Spatio-Temporal Transformer for Visual Tracking    Bin Yan, Houwen Peng, Jianlong Fu, Dong Wang, Huchuan Lu arXiv_CV arXiv_CV  Transformer  Embedding  Tracking  Object_Tracking  Pose  CNN  Prediction  PDF
• 2021-03-31 Adversarial Attacks and Defenses for Speech Recognition Systems    Piotr Żelasko, Sonal Joshi, Yiwen Shao, Jesus Villalba, Jan Trmal, Najim Dehak, Sanjeev Khudanpur arXiv_SD arXiv_SD  Transformer  Gradient_Descent  Recognition  Adversarial  Speech  GAN  Speech_Recognition  PDF
• 2021-03-31 Learning Domain Adaptation with Model Calibration for Surgical Report Generation in Robotic Surgery    Mengya Xu, Mobarakol Islam, Chwee Ming Lim, Hongliang Ren arXiv_RO arXiv_RO  Transformer  Segmentation  Unsupervised  Zero-Shot  Adversarial  Pose  Deep_Learning  Relation  Few-Shot  Caption  PDF
• 2021-03-31 DA-DETR: Domain Adaptive Detection Transformer by Hybrid Attention    Jingyi Zhang, Jiaxing Huang, Zhipeng Luo, Gongjie Zhang, Shijian Lu arXiv_CV arXiv_CV  Transformer  Adversarial  Detection  Object_Detection  Attention  PDF
• 2021-03-31 Robust Facial Expression Recognition with Convolutional Visual Transformers    Fuyan Ma, Bin Sun, Shutao Li arXiv_CV arXiv_CV  Transformer  Recognition  Pose  Face  Relation  Attention  CNN  PDF
• 2021-03-31 CloneBot: Personalized Dialogue-Response Predictions    Tyler Weitzman, Hoon Pyo (Tim) Jeon arXiv_AI arXiv_AI  Transformer  Speech  Attention  Prediction  PDF
• 2021-03-31 On the Robustness of Vision Transformers to Adversarial Examples    Kaleel Mahmood, Rigel Mahmood, Marten van Dijk arXiv_CV arXiv_CV  Transformer  Adversarial  Classification  Attention  CNN  Image_Classification  PDF
• 2021-03-30 Physics-based Differentiable Depth Sensor Simulation    Benjamin Planche, Rajat Vikram Singh arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  Recognition  3D  Optimization  Pose_Estimation  Knowledge  Pose  Classification  Matching  PDF
• 2021-03-30 Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers    Antoine Miech, Jean-Baptiste Alayrac, Ivan Laptev, Josef Sivic, Andrew Zisserman arXiv_CV arXiv_CV  Transformer  Embedding  Attention  Inference  PDF
• 2021-03-30 Read and Attend: Temporal Localisation in Sign Language Videos    Gül Varol, Liliane Momeni, Samuel Albanie, Triantafyllos Afouras, Andrew Zisserman arXiv_CV arXiv_CV  Transformer  Recognition  Attention  PDF
• 2021-03-30 Spatiotemporal Transformer for Video-based Person Re-identification    Tianyu Zhang, Longhui Wei, Lingxi Xie, Zijie Zhuang, Yongfei Zhang, Bo Li, Qi Tian arXiv_CV arXiv_CV  Transformer  Person_Re-identification  Pose  Attention  Re-identification  PDF
• 2021-03-30 Rethinking Spatial Dimensions of Vision Transformers    Byeongho Heo, Sangdoo Yun, Dongyoon Han, Sanghyuk Chun, Junsuk Choe, Seong Joon Oh arXiv_CV arXiv_CV  Transformer  Pose  Classification  Detection  Object_Detection  CNN  Image_Classification  PDF
• 2021-03-30 Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers    Debanjan Chaudhuri, Md Rashad Al Hasan Rony, Jens Lehmann arXiv_CL arXiv_CL  Transformer  Bert  Knowledge  Knowledge_Graph  Pose  Action  Relation  Inference  PDF
• 2021-03-30 Kaleido-BERT: Vision-Language Pre-training on Fashion Domain    Mingchen Zhuge, Dehong Gao, Deng-Ping Fan, Linbo Jin, Ben Chen, Haoming Zhou, Minghui Qiu, Ling Shao arXiv_CV arXiv_CV  Transformer  Recognition  Bert  Image_Retrieval  Self-Supervised  Relation  Caption  PDF
• 2021-03-30 Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation    Shuning Chang, Pichao Wang, Fan Wang, Hao Li, Jiashi Feng arXiv_CV arXiv_CV  Transformer  Video_Caption  Pose  Action  Detection  Activity  CNN  PDF
• 2021-03-30 Self-supervised Image-text Pre-training With Mixed Data In Chest X-rays    Xiaosong Wang, Ziyue Xu, Leo Tam, Dong Yang, Daguang Xu arXiv_CV arXiv_CV  Transformer  Weakly_Supervised  Self-Supervised  Pose  Classification  Medical  Language_Model  PDF
• 2021-03-29 Domain-robust VQA with diverse datasets and methods but no target labels    Mingda Zhang, Tristan Maidment, Ahmad Diab, Adriana Kovashka, Rebecca Hwa arXiv_CV arXiv_CV  Transformer  Unsupervised  Recognition  Optimization  Classification  VQA  QA  PDF
• 2021-03-29 Contextual Text Embeddings for Twi    Paul Azunre, Salomey Osei, Salomey Addo, Lawrence Asamoah Adu-Gyamfi, Stephen Moore, Bernard Adabankah, Bernard Opoku, Clara Asare-Nyarko, Samuel Nyarko, Cynthia Amoaba, Esther Dansoa Appiah, Felix Akwerh, Richard Nii Lante Lawson, Joel Budu, Emmanuel Debrah, Nana Boateng, Wisdom Ofori, Edwin Buabeng-Munkoh, Franklin Adjei, Isaac Kojo Essel Ampomah, Joseph Otoo, Reindorf Borkor, Standylove Birago Mensah, Lucien Mensah, Mark Amoako Marcel, Anokye Acheampong Amponsah, James Ben Hayfron-Acquah arXiv_AI arXiv_AI  Transformer  Embedding  Recognition  Bert  Sentiment_Classification  Knowledge  Speech  Face  NMT  Classification  Sentiment  Language_Model  PDF
• 2021-03-29 Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors    Zeyu Yun, Yubei Chen, Bruno A Olshausen, Yann LeCun arXiv_CL arXiv_CL  Transformer  Embedding  Represenation_Learning  Knowledge  Pose  PDF
• 2021-03-29 PixelTransformer: Sample Conditioned Signal Generation    Shubham Tulsiani, Abhinav Gupta arXiv_CV arXiv_CV  Transformer  3D  Sparse  Pose  PDF
• 2021-03-29 CvT: Introducing Convolutions to Vision Transformers    Haiping Wu, Bin Xiao, Noel Codella, Mengchen Liu, Xiyang Dai, Lu Yuan, Lei Zhang arXiv_CV arXiv_CV  Transformer  Embedding  Attention  CNN  PDF
• 2021-03-29 Transformer-based end-to-end speech recognition with residual Gaussian-based self-attention    Chengdong Liang, Menglong Xu, Xiao-Lei Zhang arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Pose  Relation  Attention  Speech_Recognition  PDF
• 2021-03-29 ViViT: A Video Vision Transformer    Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, Mario Lučić, Cordelia Schmid arXiv_CV arXiv_CV  Transformer  3D  Pose  Classification  CNN  Image_Classification  Video_Classification  PDF
• 2021-03-29 Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers    Hila Chefer, Shir Gur, Lior Wolf arXiv_CV arXiv_CV  Transformer  Segmentation  Pose  Detection  VQA  Object_Detection  Attention  Prediction  PDF
• 2021-03-29 On the Adversarial Robustness of Visual Transformers    Rulin Shao, Zhouxing Shi, Jinfeng Yi, Pin-Yu Chen, Cho-Jui Hsieh arXiv_AI arXiv_AI  Transformer  Adversarial  Classification  Relation  CNN  PDF
• 2021-03-29 English-Twi Parallel Corpus for Machine Translation    Paul Azunre, Salomey Osei, Salomey Addo, Lawrence Asamoah Adu-Gyamfi, Stephen Moore, Bernard Adabankah, Bernard Opoku, Clara Asare-Nyarko, Samuel Nyarko, Cynthia Amoaba, Esther Dansoa Appiah, Felix Akwerh, Richard Nii Lante Lawson, Joel Budu, Emmanuel Debrah, Nana Boateng, Wisdom Ofori, Edwin Buabeng-Munkoh, Franklin Adjei, Isaac Kojo Essel Ampomah, Joseph Otoo, Reindorf Borkor, Standylove Birago Mensah, Lucien Mensah, Mark Amoako Marcel, Anokye Acheampong Amponsah, James Ben Hayfron-Acquah arXiv_AI arXiv_AI  Transformer  Represenation_Learning  Classification  PDF
• 2021-03-29 Monitoring Object Detection Abnormalities via Data-Label and Post-Algorithm Abstractions    Yuhang Chen, Chih-Hong Cheng, Jun Yan, Rongjie Yan arXiv_AI arXiv_AI  Transformer  Tracking  Action  Detection  Object_Detection  Autonomous  PDF
• 2021-03-29 Transformer Tracking    Xin Chen, Bin Yan, Jiawen Zhu, Dong Wang, Xiaoyun Yang, Huchuan Lu arXiv_CV arXiv_CV  Transformer  Tracking  Pose  Action  Classification  Relation  Attention  Matching  PDF
• 2021-03-29 Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding    Pengchuan Zhang, Xiyang Dai, Jianwei Yang, Bin Xiao, Lu Yuan, Lei Zhang, Jianfeng Gao arXiv_AI arXiv_AI  Transformer  Segmentation  Classification  Detection  Object_Detection  Attention  Image_Classification  PDF
• 2021-03-29 Changing the Mind of Transformers for Topically-Controllable Language Generation    Haw-Shiuan Chang, Jiaming Yuan, Mohit Iyyer, Andrew McCallum arXiv_CL arXiv_CL  Transformer  Self-Supervised  Text_Generation  Language_Model  PDF
• 2021-03-29 TFPose: Direct Human Pose Estimation with Transformers    Weian Mao, Yongtao Ge, Chunhua Shen, Zhi Tian, Xinlong Wang, Zhibin Wang arXiv_CV arXiv_CV  Transformer  Pose_Estimation  Pose  Relation  Attention  Prediction  PDF
• 2021-03-28 TransCenter: Transformers with Dense Queries for Multiple-Object Tracking    Yihong Xu, Yutong Ban, Guillaume Delorme, Chuang Gan, Daniela Rus, Xavier Alameda-Pineda arXiv_CV arXiv_CV  Transformer  Tracking  Object_Tracking  Pose  PDF
• 2021-03-28 PENELOPIE: Enabling Open Information Extraction for the Greek Language through Machine Translation    Dimitris Papadopoulos, Nikolaos Papadakis, Nikolaos Matsatsinis arXiv_CL arXiv_CL  Transformer  Action  NMT  PDF
• 2021-03-28 TransICD: Transformer Based Code-wise Attention Model for Explainable ICD Coding    Biplob Biswas, Thai-Hoang Pham, Ping Zhang arXiv_CL arXiv_CL  Transformer  RNN  Pose  Classification  Attention  Medical  Prediction  PDF
• 2021-03-28 HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval    Song Liu, Haoqi Fan, Shengsheng Qian, Yiru Chen, Wenkui Ding, Zhongyuan Wang arXiv_CV arXiv_CV  Transformer  Pose  Action  Attention  Matching  PDF
• 2021-03-27 Machine Learning Meets Natural Language Processing -- The story so far    N.-I. Galanis, P. Vafiadis, K.-G. Mirzaev, G.A. Papakostas arXiv_AI arXiv_AI  Transformer  Bert  Attention  PDF
• 2021-03-27 CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification    Chun-Fu Chen, Quanfu Fan, Rameswar Panda arXiv_CV arXiv_CV  Transformer  Pose  Classification  Attention  CNN  Image_Classification  PDF
• 2021-03-27 TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization    Wei Gao, Fang Wan, Xingjia Pan, Zhiliang Peng, Qi Tian, Zhenjun Han, Bolei Zhou, Qixiang Ye arXiv_CV arXiv_CV  Transformer  Embedding  Weakly_Supervised  Action  Classification  Attention  CNN  PDF
• 2021-03-27 Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers    Tianyu Zhu, Markus Hiller, Mahsa Ehsanpour, Rongkai Ma, Tom Drummond, Hamid Rezatofighi arXiv_CV arXiv_CV  Transformer  Embedding  Tracking  Object_Tracking  Action  Attention  PDF
• 2021-03-27 Face Transformer for Recognition    Yaoyao Zhong, Weihong Deng arXiv_CV arXiv_CV  Transformer  Recognition  Face  Face_Recognition  PDF
• 2021-03-26 Dodrio: Exploring Transformer Models with Interactive Visualization    Zijie J. Wang, Robert Turko, Duen Horng Chau arXiv_AI arXiv_AI  Transformer  Knowledge  Attention  PDF
• 2021-03-26 Understanding Robustness of Transformers for Image Classification    Srinadh Bhojanapalli, Ayan Chakrabarti, Daniel Glasner, Daliang Li, Thomas Unterthiner, Andreas Veit arXiv_AI arXiv_AI  Transformer  Classification  CNN  Image_Classification  PDF
• 2021-03-26 Leveraging neural representations for facilitating access to untranscribed speech from endangered languages    Nay San, Martijn Bartelds, Mitchell Browne, Lily Clifford, Fiona Gibson, John Mansfield, David Nash, Jane Simpson, Myfany Turpin, Maria Vollmer, Sasha Wilmoth, Dan Jurafsky arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Detection  Speech_Recognition  PDF
• 2021-03-26 On the hidden treasure of dialog in video question answering    Deniz Engin, Yannis Avrithis, Ngoc Q. K. Duong, François Schnitzler arXiv_CV arXiv_CV  Transformer  Video_Caption  Knowledge  VQA  Attention  Summarization  QA  PDF
• 2021-03-26 Turning transformer attention weights into zero-shot sequence labelers    Kamil Bujel, Helen Yannakoudakis, Marek Rei arXiv_AI arXiv_AI  Transformer  Zero-Shot  Pose  Attention  Inference  PDF
• 2021-03-26 Lifting Transformer for 3D Human Pose Estimation in Video    Wenhao Li, Hong Liu, Runwei Ding, Mengyuan Liu, Pichao Wang arXiv_CV arXiv_CV  Transformer  3D  Pose_Estimation  Pose  PDF
• 2021-03-26 BART based semantic correction for Mandarin automatic speech recognition system    Yun Zhao, Xuerui Yang, Jinchao Wang, Yongyu Gao, Chao Yan, Yuanfu Zhou arXiv_CL arXiv_CL  Transformer  Recognition  Speech  Pose  Speech_Recognition  Language_Model  PDF
• 2021-03-25 COTR: Correspondence Transformer for Matching Across Images    Wei Jiang, Eduard Trulls, Jan Hosang, Andrea Tagliasacchi, Kwang Moo Yi arXiv_CV arXiv_CV  Transformer  Sparse  Pose  Optical_Flow  Inference  Matching  PDF
• 2021-03-25 Describing and Localizing Multiple Changes with Transformers    Yue Qiu, Shintaro Yamamoto, Kodai Nakashima, Ryota Suzuki, Kenji Iwata, Hirokatsu Kataoka, Yutaka Satoh arXiv_CV arXiv_CV  Transformer  Pose  Attention  Caption  PDF
• 2021-03-25 High-Fidelity Pluralistic Image Completion with Transformers    Ziyu Wan, Jingbo Zhang, Dongdong Chen, Jing Liao arXiv_CV arXiv_CV  Transformer  Reconstruction  Pose  Relation  CNN  PDF
• 2021-03-25 Swin Transformer: Hierarchical Vision Transformer using Shifted Windows    Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, Baining Guo arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  Pose  Classification  Detection  Object_Detection  Attention  Image_Classification  Prediction  PDF
• 2021-03-25 AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting    Ye Yuan, Xinshuo Weng, Yanglan Ou, Kris Kitani arXiv_AI arXiv_AI  Transformer  Pose  Action  Attention  Autonomous  Prediction  PDF
• 2021-03-25 An Image is Worth 16x16 Words, What is a Video Worth?    Gilad Sharir, Asaf Noy, Lihi Zelnik-Manor arXiv_CV arXiv_CV  Transformer  Recognition  3D  Salient  Action_Recognition  Action  Attention  Inference  PDF
• 2021-03-25 Bertinho: Galician BERT Representations    David Vilares, Marcos Garcia, Carlos Gómez-Rodríguez arXiv_CL arXiv_CL  Transformer  Recognition  Bert  Pose  Classification  PDF
• 2021-03-25 K-XLNet: A General Method for Combining Explicit Knowledge with Language Model Pretraining    Ruiqing Yan, Lanchang Sun, Fang Wang, Xiaoming Zhang arXiv_AI arXiv_AI  Transformer  Bert  Knowledge  Knowledge_Graph  Pose  Face  Language_Model  PDF
• 2021-03-25 Predicting Directionality in Causal Relations in Text    Pedram Hosseini, David A. Broniatowski, Mona Diab arXiv_AI arXiv_AI  Transformer  Bert  Relation  Language_Model  PDF
• 2021-03-25 Mask Attention Networks: Rethinking and Strengthen Transformer    Zhihao Fan, Yeyun Gong, Dayiheng Liu, Zhongyu Wei, Siyuan Wang, Jian Jiao, Nan Duan, Ruofei Zhang, Xuanjing Huang arXiv_CL arXiv_CL  Transformer  Represenation_Learning  Pose  Attention  Summarization  PDF
• 2021-03-25 Benchmarking Modern Named Entity Recognition Techniques for Free-text Health Record De-identification    Abdullah Ahmed, Adeel Abbasi, Carsten Eickhoff arXiv_CL arXiv_CL  Transformer  Embedding  Recognition  RNN  Pose  Action  Deep_Learning  Medical  PDF
• 2021-03-24 Vision Transformers for Dense Prediction    René Ranftl, Alexey Bochkovskiy, Vladlen Koltun arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  CNN  Prediction  PDF
• 2021-03-24 FastMoE: A Fast Mixture-of-Expert Training System    Jiaao He, Jiezhong Qiu, Aohan Zeng, Zhilin Yang, Jidong Zhai, Jie Tang arXiv_CL arXiv_CL  Transformer  Face  Language_Model  PDF
• 2021-03-24 Transformer-based ASR using multiple-utterance beam-search    Yoo Rhee Oh, Kiyoung Park, Jeon Gyu Park arXiv_SD arXiv_SD  Transformer  Recognition  Speech  Pose  Speech_Recognition  PDF
• 2021-03-24 Finetuning Pretrained Transformers into RNNs    Jungo Kasai, Hao Peng, Yizhe Zhang, Dani Yogatama, Gabriel Ilharco, Nikolaos Pappas, Yi Mao, Weizhu Chen, Noah A. Smith arXiv_CL arXiv_CL  Transformer  RNN  Pose  Attention  Inference  PDF
• 2021-03-24 Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning    Amaia Salvador, Erhan Gundogdu, Loris Bazzani, Michael Donoser arXiv_CV arXiv_CV  Transformer  Self-Supervised  Pose  Relation  Attention  PDF
• 2021-03-24 Can Vision Transformers Learn without Natural Images?    Kodai Nakashima, Hirokatsu Kataoka, Asato Matsumoto, Kenji Iwata, Nakamasa Inoue arXiv_CV arXiv_CV  Transformer  Self-Supervised  Pose  PDF
• 2021-03-24 Multi-view 3D Reconstruction with Transformer    Dan Wang, Xinrui Cui, Xun Chen, Zhengxia Zou, Tianyang Shi, Septimiu Salcudean, Z. Jane Wang, Rabab Ward arXiv_CV arXiv_CV  Transformer  Reconstruction  3D  Pose  Action  Relation  Attention  Prediction  PDF
• 2021-03-23 The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures    Sushant Singh, Ausif Mahmood arXiv_CL arXiv_CL  Transformer  Quantization  Transfer_Learning  Bert  Knowledge  Action  Deep_Learning  Attention  Inference  Language_Model  PDF
• 2021-03-23 Variable Name Recovery in Decompiled Binary Code using Constrained Masked Language Modeling    Pratyay Banerjee, Kuntal Kumar Pal, Fish Wang, Chitta Baral arXiv_CL arXiv_CL  Transformer  Bert  Pose  Language_Model  Prediction  PDF
• 2021-03-23 Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detection    Jan Philip Wahle, Terry Ruas, Norman Meuschke, Bela Gipp arXiv_AI arXiv_AI  Transformer  Bert  Pose  Classification  Detection  Language_Model  PDF
• 2021-03-23 Modeling the Severity of Complaints in Social Media    Mali Jin, Nikolaos Aletras arXiv_CL arXiv_CL  Transformer  Speech  Face  Action  Classification  Detection  PDF
• 2021-03-23 BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search    Changlin Li, Tao Tang, Guangrun Wang, Jiefeng Peng, Bing Wang, Xiaodan Liang, Xiaojun Chang arXiv_CV arXiv_CV  Transformer  NAS  Unsupervised  Recognition  Self-Supervised  Relation  PDF
• 2021-03-23 Discovering Emotion and Reasoning its Flip in Multi-Party Conversations using Masked Memory Network and Transformer    Shivani Kumar, Anubhav Shrimal, Md Shad Akhtar, Tanmoy Chakraborty arXiv_CL arXiv_CL  Transformer  Recognition  Pose  Emotion  Quantitative  PDF
• 2021-03-23 NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation    Zhicheng Zhou, Cheng Zhao, Daniel Adolfsson, Songzhi Su, Yang Gao, Tom Duckett, Li Sun arXiv_CV arXiv_CV  Transformer  Recognition  Point_Cloud  3D  Pose  SLAM  Detection  Autonomous  PDF
• 2021-03-22 Instance-level Image Retrieval using Reranking Transformers    Fuwen Tan, Jiangbo Yuan, Vicente Ordonez arXiv_CV arXiv_CV  Transformer  Image_Retrieval  Pose  Matching  PDF
• 2021-03-22 Tiny Transformers for Environmental Sound Classification at the Edge    David Elliott, Carlos E. Otero, Steven Wyatt, Evan Martino arXiv_SD arXiv_SD  Transformer  Bert  Action  Classification  PDF
• 2021-03-22 End-to-End Trainable Multi-Instance Pose Estimation with Transformers    Lucas Stoffl, Maxime Vidal, Alexander Mathis arXiv_CV arXiv_CV  Transformer  Pose_Estimation  Knowledge  Pose  Detection  Relation  Object_Detection  CNN  Prediction  Matching  PDF
• 2021-03-22 Transformers Solve the Limited Receptive Field for Monocular Depth Prediction    Guanglei Yang, Hao Tang, Mingli Ding, Nicu Sebe, Elisa Ricci arXiv_CV arXiv_CV  Transformer  Pose  Face  Attention  CNN  Prediction  PDF
• 2021-03-22 Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval    Gregor Geigle, Jonas Pfeiffer, Nils Reimers, Ivan Vulić, Iryna Gurevych arXiv_CV arXiv_CV  Transformer  Zero-Shot  Pose  Attention  PDF
• 2021-03-22 DeepViT: Towards Deeper Vision Transformer    Daquan Zhou, Bingyi Kang, Xiaojie Jin, Linjie Yang, Xiaochen Lian, Qibin Hou, Jiashi Feng arXiv_CV arXiv_CV  Transformer  Represenation_Learning  Pose  Classification  Attention  CNN  Image_Classification  PDF
• 2021-03-22 Incorporating Convolution Designs into Visual Transformers    Kun Yuan, Shaopeng Guo, Ziwei Liu, Aojun Zhou, Fengwei Yu, Wei Wu arXiv_CV arXiv_CV  Transformer  Pose  Relation  Attention  CNN  PDF
• 2021-03-22 Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking    Ning Wang, Wengang Zhou, Jie Wang, Houqaing Li arXiv_CV arXiv_CV  Transformer  Tracking  Object_Tracking  Pose  Attention  Matching  PDF
• 2021-03-22 Multimodal Motion Prediction with Stacked Transformers    Yicheng Liu, Jinghuai Zhang, Liangji Fang, Qinhong Jiang, Bolei Zhou arXiv_AI arXiv_AI  Transformer  Knowledge  Pose  Autonomous  Prediction  PDF
• 2021-03-22 A Large-scale Dataset for Hate Speech Detection on Vietnamese Social Media Texts    Son T. Luu, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen arXiv_CL arXiv_CL  Transformer  Speech  Face  Deep_Learning  Detection  PDF
• 2021-03-21 Paying Attention to Activation Maps in Camera Pose Regression    Yoli Shavit, Ron Ferens, Yosi Keller arXiv_AI arXiv_AI  Transformer  Embedding  Image_Retrieval  Knowledge  Pose  Attention  CNN  PDF
• 2021-03-21 Learning Multi-Scene Absolute Pose Regression with Transformers    Yoli Shavit, Ron Ferens, Yosi Keller arXiv_CV arXiv_CV  Transformer  Embedding  Pose  Attention  CNN  Prediction  PDF
• 2021-03-21 Non-Autoregressive Translation by Learning Target Categorical Codes    Yu Bao, Shujian Huang, Tong Xiao, Dongqi Wang, Xinyu Dai, Jiajun Chen arXiv_AI arXiv_AI  Transformer  Pose  Action  Text_Generation  PDF
• 2021-03-21 Learning Calibrated-Guidance for Object Detection in Aerial Images    Dong Liang, Zongqi Wei, Dong Zhang, Qixiang Geng, Liyan Zhang, Han Sun, Huiyu Zhou, Mingqiang Wei, Pan Gao arXiv_CV arXiv_CV  Transformer  Pose  Detection  Object_Detection  Attention  PDF
• 2021-03-21 Multi-view analysis of unregistered medical images using cross-view transformers    Gijs van Tulder, Yao Tong, Elena Marchiori arXiv_CV arXiv_CV  Transformer  Medical  PDF
• 2021-03-21 MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation    Zachary Seymour, Kowshik Thopalli, Niluthpol Mithun, Han-Pang Chiu, Supun Samarasekera, Rakesh Kumar arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  Reinforcement_Learning  Pose  Attention  Autonomous  PDF
• 2021-03-21 An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-Level Structural Information    Zejun Li, Zhongyu Wei, Zhihao Fan, Haijun Shan, Xuanjing Huang arXiv_AI arXiv_AI  Transformer  Unsupervised  Represenation_Learning  Pose  Matching  PDF
• 2021-03-20 Paying Attention to Multiscale Feature Maps in Multimodal Image Matching    Aviad Moreshet, Yosi Keller arXiv_CV arXiv_CV  Transformer  Embedding  Knowledge  Pose  Attention  Matching  PDF
• 2021-03-19 BERTSurv: BERT-Based Survival Models for Predicting Outcomes of Trauma Patients    Yun Zhao, Qinghang Hong, Xinlu Zhang, Yu Deng, Yuqing Wang, Linda Petzold arXiv_AI arXiv_AI  Transformer  Bert  Deep_Learning  Relation  Attention  Medical  Prediction  PDF
• 2021-03-19 Transferable Model for Shape Optimization subject to Physical Constraints    Lukas Harsch, Johannes Burgbacher, Stefan Riedelbauch arXiv_AI arXiv_AI  Transformer  Optimization  Pose  Action  PDF
• 2021-03-19 MDMMT: Multidomain Multimodal Transformer for Video Retrieval    Maksim Dzabraev, Maksim Kalashnikov, Stepan Komkov, Aleksandr Petiushko arXiv_CV arXiv_CV  Transformer  Video_Caption  Caption  Activity  Video_Retrieval  PDF
• 2021-03-19 ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases    Stéphane d'Ascoli, Hugo Touvron, Matthew Leavitt, Ari Morcos, Giulio Biroli, Levent Sagun arXiv_CV arXiv_CV  Transformer  Classification  Attention  CNN  Image_Classification  PDF
• 2021-03-19 API2Com: On the Improvement of Automatically Generated Code Comments Using API Documentations    Ramin Shahbazi, Rishab Sharma, Fatemeh H. Fard arXiv_CL arXiv_CL  Transformer  RNN  Knowledge  Pose  Face  PDF
• 2021-03-19 Scalable Visual Transformers with Hierarchical Pooling    Zizheng Pan, Bohan Zhuang, Jing Liu, Haoyu He, Jianfei Cai arXiv_CV arXiv_CV  Transformer  Recognition  Pose  Classification  Attention  CNN  Image_Classification  Inference  PDF
• 2021-03-19 Hopper: Multi-hop Transformer for Spatiotemporal Reasoning    Honglu Zhou, Asim Kadav, Farley Lai, Alexandru Niculescu-Mizil, Martin Renqiang Min, Mubbasir Kapadia, Hans Peter Graf arXiv_CV arXiv_CV  Transformer  Pose  Deep_Learning  PDF
• 2021-03-18 UNETR: Transformers for 3D Medical Image Segmentation    Ali Hatamizadeh, Dong Yang, Holger Roth, Daguang Xu arXiv_CV arXiv_CV  Transformer  Segmentation  Semantic_Segmentation  3D  Pose  Medical  CNN  Prediction  PDF
• 2021-03-18 3D Human Pose Estimation with Spatial and Temporal Transformers    Ce Zheng, Sijie Zhu, Matias Mendieta, Taojiannan Yang, Chen Chen, Zhengming Ding arXiv_AI arXiv_AI  Transformer  Segmentation  Semantic_Segmentation  3D  Pose_Estimation  Pose  Quantitative  Classification  Detection  Relation  Object_Detection  CNN  Image_Classification  PDF
• 2021-03-18 Smoothing and Shrinking the Sparse Seq2Seq Search Space    Ben Peters, André F. T. Martins arXiv_CL arXiv_CL  Transformer  Sparse  Regularization  Pose  PDF
• 2021-03-18 Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning    Mandela Patrick, Yuki M. Asano, Bernie Huang, Ishan Misra, Florian Metze, Joao Henriques, Andrea Vedaldi arXiv_CV arXiv_CV  Image_Caption  Transformer  Represenation_Learning  Self-Supervised  Pose  Attention  PDF
• 2021-03-18 DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer    Buyu Li, Yongchi Zhao, Lu Sheng arXiv_AI arXiv_AI  Transformer  3D  Adversarial  Pose  Quantitative  Deep_Learning  Relation  Attention  GAN  Prediction  PDF
• 2021-03-18 Danish Fungi 2020 -- Not Just Another Image Recognition Dataset    Lukáš Picek, Milan Šulc, Jiří Matas, Jacob Heilmann-Clausen, Thomas S. Jeppesen, Thomas Læssøe, Tobias Frøslev arXiv_CV arXiv_CV  Transformer  Recognition  Pose  Classification  CNN  PDF
• 2021-03-18 Enhancing Transformer for Video Understanding Using Gated Multi-Level Attention and Temporal Adversarial Training    Saurabh Sahu, Palash Goyal arXiv_CV arXiv_CV  Transformer  Video_Caption  Regularization  Adversarial  Pose  Quantitative  Attention  PDF
• 2021-03-18 TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain    Kai Wang, Bengbeng He, Wei-Ping Zhu arXiv_SD arXiv_SD  Transformer  Enhancement  Speech  Pose  Denoising  PDF
• 2021-03-17 Transformer-based ASR Incorporating Time-reduction Layer and Fine-tuning with Self-Knowledge Distillation    Md Akmal Haidar, Chao Xing, Mehdi Rezagholizadeh arXiv_AI arXiv_AI  Transformer  Recognition  Knowledge  Speech  Pose  Attention  Speech_Recognition  Inference  Language_Model  PDF
• 2021-03-17 Hierarchical Attention-based Age Estimation and Bias Estimation    Shakediel Hiba, Yosi Keller arXiv_CV arXiv_CV  Transformer  Embedding  Pose  Face  Attention  PDF
• 2021-03-17 Value-aware Approximate Attention    Ankit Gupta, Jonathan Berant arXiv_CL arXiv_CL  Transformer  Sparse  Pose  Attention  Language_Model  PDF
• 2021-03-17 Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer    Xiaojie Gao, Yueming Jin, Yonghao Long, Qi Dou, Pheng-Ann Heng arXiv_AI arXiv_AI  Transformer  Embedding  Recognition  Inference  PDF
• 2021-03-17 SML: a new Semantic Embedding Alignment Transformer for efficient cross-lingual Natural Language Inference    Javier Huertas-Tato, Alejandro Martín, David Camacho arXiv_CL arXiv_CL  Transformer  Embedding  Knowledge  Pose  Face  Relation  Inference  PDF
• 2021-03-17 On the Role of Images for Analyzing Claims in Social Media    Gullal S. Cheema, Sherzod Hakimov, Eric Müller-Budack, Ralph Ewerth arXiv_CV arXiv_CV  Transformer  Pose  Detection  PDF
• 2021-03-17 ENCONTER: Entity Constrained Progressive Sequence Generation via Insertion-based Transformer    Lee-Hsun Hsieh, Yang-Yin Lee, Ee-Peng Lim arXiv_AI arXiv_AI  Transformer  Pose  Language_Model  PDF
• 2021-03-17 You Only Look One-level Feature    Qiang Chen, Yingming Wang, Tong Yang, Xiangyu Zhang, Jian Cheng, Jian Sun arXiv_CV arXiv_CV  Transformer  Optimization  Pose  Detection  Object_Detection  Matching  PDF
• 2021-03-16 Towards physically consistent data-driven weather forecasting: Integrating data assimilation with equivariance-preserving deep spatial transformers    Ashesh Chattopadhyay, Mustafa Mustafa, Pedram Hassanzadeh, Eviatar Bach, Karthik Kashinath arXiv_AI arXiv_AI  Transformer  Pose  CNN  Prediction  PDF
• 2021-03-16 Dense Interaction Learning for Video-based Person Re-identification    Tianyu He, Xin Jin, Xu Shen, Jianqiang Huang, Zhibo Chen, Xian-Sheng Hua arXiv_CV arXiv_CV  Transformer  Embedding  Person_Re-identification  Pose  Action  Relation  Attention  Re-identification  Matching  PDF
• 2021-03-16 Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models    Po-Yao Huang, Mandela Patrick, Junjie Hu, Graham Neubig, Florian Metze, Alexander Hauptmann arXiv_CV arXiv_CV  Transformer  Embedding  Zero-Shot  Pose  Language_Model  PDF
• 2021-03-16 Robustly Optimized and Distilled Training for Natural Language Understanding    Haytham ElFadeel, Stan Peshterliev arXiv_CL