{"total":206,"rows":[{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542,"area":null},{"id":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187,"area":null},{"id":"2104.00946","title":"UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles","created":"2021-04-02","cited_by_count":96,"area":null},{"id":"2107.10161","title":"Evidential Deep Learning for Open Set Action Recognition","created":"2021-07-21","cited_by_count":96,"area":null},{"id":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85,"area":null},{"id":"2302.02515","title":"Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey","created":"2023-02-06","cited_by_count":68,"area":null},{"id":"2304.12301","title":"AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation","created":"2023-04-24","cited_by_count":64,"area":null},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60,"area":null},{"id":"2110.01770","title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","created":"2021-10-05","cited_by_count":53,"area":null},{"id":"2211.09648","title":"HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors","created":"2022-11-17","cited_by_count":47,"area":null},{"id":"2102.00649","title":"Forecasting Action through Contact Representations from First Person Video","created":"2021-02-01","cited_by_count":46,"area":null},{"id":"2102.12321","title":"AGENT: A Benchmark for Core Psychological Reasoning","created":"2021-02-24","cited_by_count":42,"area":null},{"id":"2107.13411","title":"Predicting the Future from First Person (Egocentric) Vision: A Survey","created":"2021-07-28","cited_by_count":36,"area":null},{"id":"2406.08877","title":"EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding","created":"2024-06-13","cited_by_count":36,"area":null},{"id":"2403.12534","title":"ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More","created":"2024-03-19","cited_by_count":33,"area":null},{"id":"2406.07471","title":"OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding","created":"2024-06-11","cited_by_count":32,"area":null},{"id":"2211.00385","title":"Behavioral Intention Prediction in Driving Scenes: A Survey","created":"2022-11-01","cited_by_count":30,"area":null},{"id":"2301.03046","title":"STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition","created":"2023-01-08","cited_by_count":29,"area":null},{"id":"2206.01038","title":"A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications","created":"2022-06-02","cited_by_count":28,"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":"2209.05700","title":"Vision Transformers for Action Recognition: A Survey","created":"2022-09-13","cited_by_count":25,"area":null},{"id":"2304.00387","title":"HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions","created":"2023-04-01","cited_by_count":25,"area":null},{"id":"2410.16668","title":"Satori: Towards Proactive AR Assistant with Belief-Desire-Intention User Modeling","created":"2024-10-22","cited_by_count":25,"area":null},{"id":"2503.12763","title":"A Survey on Human Interaction Motion Generation","created":"2025-03-17","cited_by_count":25,"area":null},{"id":"2106.11650","title":"A Survey on Human-aware Robot Navigation","created":"2021-06-22","cited_by_count":24,"area":null},{"id":"2203.05114","title":"OpenTAL: Towards Open Set Temporal Action Localization","created":"2022-03-10","cited_by_count":23,"area":null},{"id":"2107.03178","title":"Levels of explainable artificial intelligence for human-aligned conversational explanations","created":"2021-07-07","cited_by_count":21,"area":null},{"id":"2405.10347","title":"Networking Systems for Video Anomaly Detection: A Tutorial and Survey","created":"2024-05-16","cited_by_count":21,"area":null},{"id":"2308.04369","title":"SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognition","created":"2023-08-08","cited_by_count":20,"area":null},{"id":"2503.15275","title":"Challenges and Trends in Egocentric Vision: A Survey","created":"2025-03-19","cited_by_count":20,"area":null},{"id":"2212.06301","title":"Egocentric Video Task Translation","created":"2022-12-13","cited_by_count":19,"area":null},{"id":"2310.17942","title":"Diversifying Spatial-Temporal Perception for Video Domain Generalization","created":"2023-10-27","cited_by_count":19,"area":null},{"id":"2403.19316","title":"Hypergraph-based Multi-View Action Recognition using Event Cameras","created":"2024-03-28","cited_by_count":19,"area":null},{"id":"2304.01110","title":"AutoLabel: CLIP-based framework for Open-set Video Domain Adaptation","created":"2023-04-03","cited_by_count":18,"area":null},{"id":"2407.05106","title":"DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition","created":"2024-07-06","cited_by_count":17,"area":null},{"id":"2212.09381","title":"Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmark","created":"2022-12-19","cited_by_count":16,"area":null},{"id":"2308.09139","title":"The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation","created":"2023-08-17","cited_by_count":16,"area":null},{"id":"2405.15325","title":"On the Identification of Temporally Causal Representation with Instantaneous Dependence","created":"2024-05-24","cited_by_count":16,"area":null},{"id":"2403.01560","title":"XOV-Action: Towards Generalizable Open-Vocabulary Action Recognition","created":"2024-03-03","cited_by_count":15,"area":null},{"id":"2101.05043","title":"Video action recognition for lane-change classification and prediction of surrounding vehicles","created":"2021-01-13","cited_by_count":14,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2402.04519","title":"BioDrone: A Bionic Drone-based Single Object Tracking Benchmark for Robust Vision","created":"2024-02-07","cited_by_count":13,"area":null},{"id":"2104.03737","title":"Few-Shot Action Recognition with Compromised Metric via Optimal Transport","created":"2021-04-08","cited_by_count":12,"area":null},{"id":"2408.09764","title":"Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms","created":"2024-08-19","cited_by_count":12,"area":null},{"id":"2409.09953","title":"Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detection","created":"2024-09-16","cited_by_count":12,"area":null},{"id":"2507.15542","title":"HOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation","created":"2025-07-21","cited_by_count":12,"area":null},{"id":"2111.05468","title":"Sparse Adversarial Video Attacks with Spatial Transformations","created":"2021-11-10","cited_by_count":11,"area":null},{"id":"2302.04530","title":"Gaze-based intention estimation: principles, methodologies, and applications in HRI","created":"2023-02-09","cited_by_count":11,"area":null},{"id":"2308.15816","title":"Improving Underwater Visual Tracking With a Large Scale Dataset and Image Enhancement","created":"2023-08-30","cited_by_count":11,"area":null},{"id":"2309.17257","title":"A Survey on Deep Learning Techniques for Action Anticipation","created":"2023-09-29","cited_by_count":11,"area":null},{"id":"2407.14744","title":"A Comprehensive Review of Few-shot Action Recognition","created":"2024-07-20","cited_by_count":11,"area":null},{"id":"2411.14565","title":"Privacy-Preserving Video Anomaly Detection: A Survey","created":"2024-11-21","cited_by_count":11,"area":null},{"id":"2202.13096","title":"Continuous Human Action Recognition for Human-Machine Interaction: A Review","created":"2022-02-26","cited_by_count":10,"area":null},{"id":"2204.07414","title":"SOTVerse: A User-defined Task Space of Single Object Tracking","created":"2022-04-15","cited_by_count":10,"area":null},{"id":"2403.05856","title":"POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-View World","created":"2024-03-09","cited_by_count":10,"area":null},{"id":"2404.15349","title":"A Survey on Multimodal Wearable Sensor-based Human Action Recognition","created":"2024-04-14","cited_by_count":10,"area":null},{"id":"2108.06180","title":"SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments","created":"2021-08-13","cited_by_count":9,"area":null},{"id":"2207.09675","title":"ERA: Expert Retrieval and Assembly for Early Action Prediction","created":"2022-07-20","cited_by_count":9,"area":null},{"id":"2407.04190","title":"Computer Vision for Clinical Gait Analysis: A Gait Abnormality Video Dataset","created":"2024-07-05","cited_by_count":9,"area":null},{"id":"2410.14045","title":"Human Action Anticipation: A Survey","created":"2024-10-17","cited_by_count":9,"area":null},{"id":"2307.10763","title":"Actor-agnostic Multi-label Action Recognition with Multi-modal Query","created":"2023-07-20","cited_by_count":8,"area":null},{"id":"2403.06734","title":"Real-Time Multimodal Cognitive Assistant for Emergency Medical Services","created":"2024-03-11","cited_by_count":8,"area":null},{"id":"2501.13066","title":"SMART-Vision: Survey of Modern Action Recognition Techniques in Vision","created":"2025-01-22","cited_by_count":8,"area":null},{"id":"2112.09976","title":"Tell me what you see: A zero-shot action recognition method based on natural language descriptions","created":"2021-12-18","cited_by_count":7,"area":null},{"id":"2204.01297","title":"Learning Constrained Dynamic Correlations in Spatiotemporal Graphs for Motion Prediction","created":"2022-04-04","cited_by_count":7,"area":null},{"id":"2303.09044","title":"CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos","created":"2023-03-16","cited_by_count":7,"area":null},{"id":"2305.06114","title":"Few-shot Action Recognition via Intra- and Inter-Video Information Maximization","created":"2023-05-10","cited_by_count":7,"area":null},{"id":"2411.01122","title":"OnlineTAS: An Online Baseline for Temporal Action Segmentation","created":"2024-11-02","cited_by_count":7,"area":null},{"id":"2502.02817","title":"A Decade of Action Quality Assessment: Largest Systematic Survey of Trends, Challenges, and Future Directions","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2504.13351","title":"Chain-of-Modality: Learning Manipulation Programs from Multimodal Human Videos with Vision-Language-Models","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2109.02747","title":"WhyAct: Identifying Action Reasons in Lifestyle Vlogs","created":"2021-09-06","cited_by_count":6,"area":null},{"id":"2410.01341","title":"Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2410.03302","title":"Action Selection Learning for Multi-label Multi-view Action Recognition","created":"2024-10-04","cited_by_count":6,"area":null},{"id":"2412.06182","title":"Towards Long Video Understanding via Fine-detailed Video Story Generation","created":"2024-12-09","cited_by_count":6,"area":null},{"id":"2412.16233","title":"WiFi CSI Based Temporal Activity Detection via Dual Pyramid Network","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2501.12681","title":"Can masking background and object reduce static bias for zero-shot action recognition?","created":"2025-01-22","cited_by_count":6,"area":null},{"id":"2103.14785","title":"A Comprehensive Review of the Video-to-Text Problem","created":"2021-03-27","cited_by_count":5,"area":null},{"id":"2107.05140","title":"Review of Video Predictive Understanding: Early Action Recognition and Future Action Prediction","created":"2021-07-11","cited_by_count":5,"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":"2306.11046","title":"FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation","created":"2023-06-19","cited_by_count":5,"area":null},{"id":"2310.04294","title":"Graph learning in robotics: a survey","created":"2023-10-06","cited_by_count":5,"area":null},{"id":"2310.13483","title":"Application of deep learning for livestock behaviour recognition: A systematic literature review","created":"2023-10-20","cited_by_count":5,"area":null},{"id":"2311.14775","title":"VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG","created":"2023-11-24","cited_by_count":5,"area":null},{"id":"2402.02431","title":"Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition","created":"2024-02-04","cited_by_count":5,"area":null},{"id":"2403.06102","title":"Coherent Temporal Synthesis for Incremental Action Segmentation","created":"2024-03-10","cited_by_count":5,"area":null},{"id":"2407.06162","title":"RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model","created":"2024-06-02","cited_by_count":5,"area":null},{"id":"2412.13594","title":"Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learning","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2202.09545","title":"Going Deeper into Recognizing Actions in Dark Environments: A Comprehensive Benchmark Study","created":"2022-02-19","cited_by_count":4,"area":null},{"id":"2206.10491","title":"Bi-Calibration Networks for Weakly-Supervised Video Representation Learning","created":"2022-06-21","cited_by_count":4,"area":null},{"id":"2210.14862","title":"Visual Semantic Parsing: From Images to Abstract Meaning Representation","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2308.16552","title":"Prompt-enhanced Hierarchical Transformer Elevating Cardiopulmonary Resuscitation Instruction via Temporal Action Segmentation","created":"2023-08-31","cited_by_count":4,"area":null},{"id":"2403.15444","title":"A Survey of IMU Based Cross-Modal Transfer Learning in Human Activity Recognition","created":"2024-03-17","cited_by_count":4,"area":null},{"id":"2412.10804","title":"Medical Manifestation-Aware De-Identification","created":"2024-12-14","cited_by_count":4,"area":null},{"id":"2504.02287","title":"MultiSensor-Home: A Wide-area Multi-modal Multi-view Dataset for Action Recognition and Transformer-based Sensor Fusion","created":"2025-04-03","cited_by_count":4,"area":null},{"id":"2506.05274","title":"From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2101.04954","title":"EventAnchor: Reducing Human Interactions in Event Annotation of Racket Sports Videos","created":"2021-01-13","cited_by_count":3,"area":null},{"id":"2302.01921","title":"Transformers in Action Recognition: A Review on Temporal Modeling","created":"2022-12-29","cited_by_count":3,"area":null},{"id":"2304.14104","title":"Learning Human-Human Interactions in Images from Weak Textual Supervision","created":"2023-04-27","cited_by_count":3,"area":null},{"id":"2305.01111","title":"Local and Global Contextual Features Fusion for Pedestrian Intention Prediction","created":"2023-05-01","cited_by_count":3,"area":null},{"id":"2306.11862","title":"Proactive Human-Robot Co-Assembly: Leveraging Human Intention Prediction and Robust Safe Control","created":"2023-06-20","cited_by_count":3,"area":null}],"next_cursor":"100"}