Paper Reading AI Learner

PAMI-AD: An Activity Detector Exploiting Part-attention and Motion Information in Surveillance Videos

2022-03-08 01:36:26
Yunhao Du, Zhihang Tong, Junfeng Wan, Binyu Zhang, Yanyun Zhao
arXiv_CV
                 
Abstract

Activity detection in surveillance videos is a challenging task caused by small objects, complex activity categories, its untrimmed nature, etc. In this work, we propose an effective activity detection system for person-only and vehicle-only activities in untrimmed surveillance videos, named PAMI-AD. It consists of four modules, i.e., multi-object tracking, background modeling, activity classifier and post-processing. In particular, we propose a novel part-attention mechanism for person-only activities and a simple but strong motion information encoding method for vehicle-only activities. Our proposed system achieves the best results on the VIRAT dataset. Furthermore, our team won the 1st place in the TRECVID 2021 ActEV challenge.

Abstract (translated)

URL

https://arxiv.org/abs/2203.03796

PDF

https://arxiv.org/pdf/2203.03796.pdf

Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot