Activity Recognition

DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition CVPR 2022 Dual-AI: Dual-Path Actor Interaction Learning for Group Activity Recognition CVPR 2022 Efficient Deep Clustering of Human Activities and How to Improve Evaluation ACML 2022 Federated Multi-Task Attention for Cross-Individual Human Activity Recognition IJCAI 2022 FineDiving: A Fine-Grained Dataset for Procedure-Aware Action Quality Assessment CVPR 2022 Harnessing Fourier Isovists and Geodesic Interaction for Long-Term Crowd Flow Prediction IJCAI 2022 HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction CVPR 2022 Learning Graph-based Residual Aggregation Network for Group Activity Recognition IJCAI 2022 Learning to Focus on the Foreground for Temporal Sentence Grounding COLING 2022 Lifelong Graph Learning CVPR 2022 MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing NeurIPS 2022 MViTv2: Improved Multiscale Vision Transformers for Classification and Detection CVPR 2022 Rethinking the Two-Stage Framework for Grounded Situation Recognition AAAI 2022 Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding EMNLP 2022 Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction CVPR 2022 TubeR: Tubelet Transformer for Video Action Detection CVPR 2022 UnweaveNet: Unweaving Activity Stories CVPR 2022 Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization CVPR 2021 Anticipating Human Actions by Correlating Past With the Future With Jaccard Similarity Measures CVPR 2021 Appearance-Motion Memory Consistency Network for Video Anomaly Detection AAAI 2021 BASAR:Black-Box Attack on Skeletal Action Recognition CVPR 2021 BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation AAAI 2021 Coarse-Fine Networks for Temporal Activity Detection in Videos CVPR 2021 Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation ICCV 2021 Divide and Conquer for Single-Frame Temporal Action Localization ICCV 2021