{"total":83,"rows":[{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56,"area":null},{"id":"2108.12630","title":"GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer","created":"2021-08-28","cited_by_count":54,"area":null},{"id":"2108.11743","title":"Spatio-Temporal Dynamic Inference Network for Group Activity Recognition","created":"2021-08-26","cited_by_count":42,"area":null},{"id":"2204.00746","title":"What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactions","created":"2022-04-02","cited_by_count":35,"area":null},{"id":"2404.05029","title":"LOGO: A Long-Form Video Dataset for Group Action Quality Assessment","created":"2024-04-07","cited_by_count":31,"area":null},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2204.02148","title":"Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition","created":"2022-04-05","cited_by_count":27,"area":null},{"id":"2101.04838","title":"Feature refinement: An expression-specific feature learning and fusion method for micro-expression recognition","created":"2021-01-13","cited_by_count":25,"area":null},{"id":"2103.01933","title":"PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception","created":"2021-03-02","cited_by_count":22,"area":null},{"id":"2207.05254","title":"Hunting Group Clues with Transformers for Social Group Activity Recognition","created":"2022-07-12","cited_by_count":22,"area":null},{"id":"2204.02139","title":"Detector-Free Weakly Supervised Group Activity Recognition","created":"2022-04-05","cited_by_count":20,"area":null},{"id":"2112.05892","title":"COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality","created":"2021-12-11","cited_by_count":19,"area":null},{"id":"2108.04186","title":"Pose is all you need: The pose only group activity recognition system (POGARS)","created":"2021-08-09","cited_by_count":16,"area":null},{"id":"2310.07015","title":"Neural Relational Inference with Fast Modular Meta-learning","created":"2023-10-10","cited_by_count":16,"area":null},{"id":"2303.12149","title":"SPARTAN: Self-supervised Spatiotemporal Transformers Approach to Group Activity Recognition","created":"2023-03-06","cited_by_count":14,"area":null},{"id":"2109.07353","title":"Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos","created":"2021-09-15","cited_by_count":13,"area":null},{"id":"2203.03806","title":"Panoramic Human Activity Recognition","created":"2022-03-08","cited_by_count":13,"area":null},{"id":"2311.17948","title":"Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2307.03353","title":"A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision","created":"2023-07-07","cited_by_count":11,"area":null},{"id":"2312.02878","title":"Towards More Practical Group Activity Detection: A New Benchmark and Model","created":"2023-12-05","cited_by_count":11,"area":null},{"id":"2102.03513","title":"Privacy-Preserving Video Classification with Convolutional Neural Networks","created":"2021-02-06","cited_by_count":10,"area":null},{"id":"2106.13201","title":"DROID: Driver-centric Risk Object Identification","created":"2021-06-24","cited_by_count":9,"area":null},{"id":"2302.03477","title":"Explainable Action Prediction through Self-Supervision on Scene Graphs","created":"2023-02-07","cited_by_count":9,"area":null},{"id":"2110.15609","title":"BiC-Net: Learning Efficient Spatio-Temporal Relation for Text-Video Retrieval","created":"2021-10-29","cited_by_count":8,"area":null},{"id":"2303.00977","title":"Ego-Vehicle Action Recognition based on Semi-Supervised Contrastive Learning","created":"2023-03-02","cited_by_count":8,"area":null},{"id":"2305.06310","title":"SoGAR: Self-supervised Spatiotemporal Attention-based Social Group Activity Recognition","created":"2023-04-27","cited_by_count":8,"area":null},{"id":"2203.03843","title":"Self-supervised Social Relation Representation for Human Group Detection","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2207.06235","title":"Entry-Flipped Transformer for Inference and Prediction of Participant Behavior","created":"2022-07-13","cited_by_count":7,"area":null},{"id":"2303.11180","title":"Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation","created":"2023-03-20","cited_by_count":7,"area":null},{"id":"2310.00670","title":"A Hierarchical Graph-based Approach for Recognition and Description Generation of Bimanual Actions in Videos","created":"2023-10-01","cited_by_count":7,"area":null},{"id":"2308.05382","title":"Interaction-aware Joint Attention Estimation Using People Attributes","created":"2023-08-10","cited_by_count":6,"area":null},{"id":"2407.19497","title":"Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph","created":"2024-07-28","cited_by_count":6,"area":null},{"id":"2304.10073","title":"Video-based Contrastive Learning on Decision Trees: from Action Recognition to Autism Diagnosis","created":"2023-04-20","cited_by_count":5,"area":null},{"id":"2312.00188","title":"REACT: Recognize Every Action Everywhere All At Once","created":"2023-11-27","cited_by_count":5,"area":null},{"id":"2510.18357","title":"Learning Human-Object Interaction as Groups","created":"2025-10-21","cited_by_count":5,"area":null},{"id":"2103.10502","title":"Ano-Graph: Learning Normal Scene Contextual Graphs to Detect Video Anomalies","created":"2021-03-18","cited_by_count":4,"area":null},{"id":"2105.06754","title":"Learning Group Activities from Skeletons without Individual Action Labels","created":"2021-05-14","cited_by_count":4,"area":null},{"id":"2109.11243","title":"Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark","created":"2021-09-23","cited_by_count":4,"area":null},{"id":"2207.02425","title":"Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation","created":"2022-07-06","cited_by_count":4,"area":null},{"id":"2212.10207","title":"Graph Neural Networks in Computer Vision -- Architectures, Datasets and Common Approaches","created":"2022-12-20","cited_by_count":4,"area":null},{"id":"2405.18012","title":"Flow-Assisted Motion Learning Network for Weakly-Supervised Group Activity Recognition","created":"2024-05-28","cited_by_count":4,"area":null},{"id":"2503.06522","title":"SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2509.04758","title":"Dynamic Group Detection using VLM-augmented Temporal Groupness Graph","created":"2025-09-05","cited_by_count":4,"area":null},{"id":"2104.14131","title":"Actor-centered Representations for Action Localization in Streaming Videos","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2307.00464","title":"Human-to-Human Interaction Detection","created":"2023-07-02","cited_by_count":3,"area":null},{"id":"2409.18481","title":"Deep Heterogeneous Contrastive Hyper-Graph Learning for In-the-Wild Context-Aware Human Activity Recognition","created":"2024-09-27","cited_by_count":3,"area":null},{"id":"2410.07153","title":"CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition","created":"2024-10-09","cited_by_count":3,"area":null},{"id":"2302.14350","title":"Knowledge Augmented Relation Inference for Group Activity Recognition","created":"2023-02-28","cited_by_count":2,"area":null},{"id":"2303.06439","title":"DECOMPL: Decompositional Learning with Attention Pooling for Group Activity Recognition from a Single Volleyball Image","created":"2023-03-11","cited_by_count":2,"area":null},{"id":"2306.00480","title":"Parallel Neurosymbolic Integration with Concordia","created":"2023-06-01","cited_by_count":2,"area":null},{"id":"2308.15795","title":"Occlusion-Aware Detection and Re-ID Calibrated Network for Multi-Object Tracking","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2403.02753","title":"Learning Group Activity Features Through Person Attribute Prediction","created":"2024-03-05","cited_by_count":2,"area":null},{"id":"2404.07188","title":"GCV-Turbo: End-to-end Acceleration of GNN-based Computer Vision Tasks on FPGA","created":"2024-04-10","cited_by_count":2,"area":null},{"id":"2406.14472","title":"Self-supervised Multi-actor Social Activity Understanding in Streaming Videos","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2503.18553","title":"ATARS: An Aerial Traffic Atomic Activity Recognition and Temporal Segmentation Dataset","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2209.13459","title":"EgoSpeed-Net: Forecasting Speed-Control in Driver Behavior from Egocentric Video Data","created":"2022-09-27","cited_by_count":1,"area":null},{"id":"2304.08803","title":"MLP-AIR: An Efficient MLP-Based Method for Actor Interaction Relation Learning in Group Activity Recognition","created":"2023-04-18","cited_by_count":1,"area":null},{"id":"2308.13866","title":"Improving Video Violence Recognition with Human Interaction Learning on 3D Skeleton Point Clouds","created":"2023-08-26","cited_by_count":1,"area":null},{"id":"2403.14113","title":"Spatio-Temporal Proximity-Aware Dual-Path Model for Panoramic Activity Recognition","created":"2024-03-21","cited_by_count":1,"area":null},{"id":"2404.09964","title":"Design and Analysis of Efficient Attention in Transformers for Social Group Activity Recognition","created":"2024-04-15","cited_by_count":1,"area":null},{"id":"2409.02385","title":"Unified Framework with Consistency across Modalities for Human Activity Recognition","created":"2024-09-04","cited_by_count":1,"area":null},{"id":"2410.21108","title":"LiGAR: LiDAR-Guided Hierarchical Transformer for Multi-Modal Group Activity Recognition","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2508.07996","title":"Structured Relational Reasoning for Group Activity Assessment","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2603.05926","title":"Towards Driver Behavior Understanding: Weakly-Supervised Risk Perception in Driving Scenes","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2107.13648","title":"Spot What Matters: Learning Context Using Graph Convolutional Networks for Weakly-Supervised Action Detection","created":"2021-07-28","cited_by_count":0,"area":null},{"id":"2203.03087","title":"HAR-GCNN: Deep Graph CNNs for Human Activity Recognition From Highly Unlabeled Mobile Sensor Data","created":"2022-03-07","cited_by_count":0,"area":null},{"id":"2305.05583","title":"Group Activity Recognition via Dynamic Composition and Interaction","created":"2023-05-09","cited_by_count":0,"area":null},{"id":"2307.13541","title":"Group Activity Recognition in Computer Vision: A Comprehensive Review, Challenges, and Future Perspectives","created":"2023-07-25","cited_by_count":0,"area":null},{"id":"2308.15726","title":"AGS: An Dataset and Taxonomy for Domestic Scene Sound Event Recognition","created":"2023-08-30","cited_by_count":0,"area":null},{"id":"2407.19820","title":"ActivityCLIP: Enhancing Group Activity Recognition by Mining Complementary Information from Text to Supplement Image Modality","created":"2024-07-29","cited_by_count":0,"area":null},{"id":"2408.00420","title":"MPT-PAR:Mix-Parameters Transformer for Panoramic Activity Recognition","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2502.09967","title":"VicKAM: Visual Conceptual Knowledge Guided Action Map for Weakly Supervised Group Activity Recognition","created":"2025-02-14","cited_by_count":0,"area":null},{"id":"2503.08933","title":"PromptGAR: Flexible Promptive Group Activity Recognition","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2509.00490","title":"Multi-Focused Video Group Activities Hashing","created":"2025-08-30","cited_by_count":0,"area":null},{"id":"2511.03666","title":"Part-Aware Bottom-Up Group Reasoning for Fine-Grained Social Interaction Detection","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2602.03157","title":"Human-in-the-loop Adaptation in Group Activity Feature Learning for Team Sports Video Retrieval","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2604.04467","title":"Group-DINOmics: Incorporating People Dynamics into DINO for Self-supervised Group Activity Feature Learning","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2605.28604","title":"Mining Multi-Modality Spatio-Temporal Cues for Video Important Person Identification","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.21267","title":"BasketEvent: Understanding Who Did What and When in Basketball Videos","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.23077","title":"Structure over Depth: A Single-Block Spatio-Temporal Transformer for Multi-Entity Reasoning","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2608.27879","title":"What Do Interaction Representations Actually Measure? Pre-Event Separability in Weakly-Supervised Violence Detection","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.24127","title":"Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.32454","title":"De-biasing Skeleton-based Action Recognition with Convex Hull Adaptive Shift","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}