{"total":53,"rows":[{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490,"area":null},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95,"area":null},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2312.03391","title":"Action Scene Graphs for Long-Form Understanding of Egocentric Videos","created":"2023-12-06","cited_by_count":51,"area":null},{"id":"2401.00789","title":"Retrieval-Augmented Egocentric Video Captioning","created":"2024-01-01","cited_by_count":42,"area":null},{"id":"2303.03373","title":"Detecting Human-Object Contact in Images","created":"2023-03-06","cited_by_count":41,"area":null},{"id":"2203.14240","title":"Audio-Adaptive Activity Recognition Across Video Domains","created":"2022-03-27","cited_by_count":35,"area":null},{"id":"2411.19083","title":"ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives","created":"2024-11-28","cited_by_count":29,"area":null},{"id":"2503.09143","title":"Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding","created":"2025-03-12","cited_by_count":25,"area":null},{"id":"2507.18342","title":"EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs","created":"2025-07-24","cited_by_count":23,"area":null},{"id":"2308.11489","title":"Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition","created":"2023-08-22","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":"2304.00553","title":"From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding","created":"2023-04-02","cited_by_count":19,"area":null},{"id":"2403.09194","title":"Intention-driven Ego-to-Exo Video Generation","created":"2024-03-14","cited_by_count":13,"area":null},{"id":"2408.17168","title":"EMHI: A Multimodal Egocentric Human Motion Dataset with HMD and Body-Worn IMUs","created":"2024-08-30","cited_by_count":13,"area":null},{"id":"2203.00307","title":"Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection","created":"2022-03-01","cited_by_count":12,"area":null},{"id":"2402.00293","title":"FineBio: A Fine-Grained Video Dataset of Biological Experiments with Hierarchical Annotation","created":"2024-02-01","cited_by_count":12,"area":null},{"id":"2309.10171","title":"Specification-Driven Video Search via Foundation Models and Formal Verification","created":"2023-09-18","cited_by_count":10,"area":null},{"id":"2309.13237","title":"Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation","created":"2023-09-23","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":"2406.09646","title":"A Survey of Video Datasets for Grounded Event Understanding","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2310.01636","title":"Adaptive Visual Scene Understanding: Incremental Scene Graph Generation","created":"2023-10-02","cited_by_count":8,"area":null},{"id":"2501.19061","title":"EgoMe: A New Dataset and Challenge for Following Me via Egocentric View in Real World","created":"2025-01-31","cited_by_count":8,"area":"offlinerl"},{"id":"2506.06253","title":"Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2403.19259","title":"J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution","created":"2024-03-28","cited_by_count":7,"area":null},{"id":"2311.00556","title":"ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2410.20621","title":"Egocentric and Exocentric Methods: A Short Survey","created":"2024-10-27","cited_by_count":6,"area":null},{"id":"2202.04947","title":"OWL (Observe, Watch, Listen): Audiovisual Temporal Context for Localizing Actions in Egocentric Videos","created":"2022-02-10","cited_by_count":4,"area":null},{"id":"2207.05182","title":"Fine-grained Activities of People Worldwide","created":"2022-07-11","cited_by_count":4,"area":null},{"id":"2504.05925","title":"SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2510.19255","title":"Advances in 4D Representation: Geometry, Motion, and Interaction","created":"2025-10-22","cited_by_count":4,"area":null},{"id":"2408.12674","title":"One-shot Video Imitation via Parameterized Symbolic Abstraction Graphs","created":"2024-08-22","cited_by_count":3,"area":null},{"id":"2507.12463","title":"MMHU: A Massive-Scale Multimodal Benchmark for Human Behavior Understanding","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2507.16287","title":"Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognition","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2603.09798","title":"Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2305.15692","title":"Deep Neural Networks in Video Human Action Recognition: A Review","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2309.13962","title":"Egocentric RGB+Depth Action Recognition in Industry-Like Settings","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2503.06182","title":"FORESCENE: FOREcasting human activity via latent SCENE graphs diffusion","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2509.23888","title":"AssemblyHands-X: Modeling 3D Hand-Body Coordination for Understanding Bimanual Human Activities","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2606.25842","title":"Graph it first! Enabling Reasoning on Long-form Egocentric Videos through Scene Graphs","created":"2026-06-24","cited_by_count":1,"area":"lr"},{"id":"2204.07280","title":"Invisible-to-Visible: Privacy-Aware Human Instance Segmentation using Airborne Ultrasound via Collaborative Learning Variational Autoencoder","created":"2022-04-15","cited_by_count":0,"area":null},{"id":"2301.03410","title":"In Defense of Structural Symbolic Representation for Video Event-Relation Prediction","created":"2023-01-06","cited_by_count":0,"area":null},{"id":"2406.01662","title":"Few-Shot Classification of Interactive Activities of Daily Living (InteractADL)","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2501.04121","title":"Graph-Based Multimodal and Multi-view Alignment for Keystep Recognition","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2503.14524","title":"Salient Temporal Encoding for Dynamic Scene Graph Generation","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2506.01102","title":"Keystep Recognition using Graph Neural Networks","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2506.23573","title":"Online Human Action Detection during Escorting","created":"2025-06-30","cited_by_count":0,"area":null},{"id":"2602.10818","title":"Resource-Efficient RGB-Only Action Recognition for Edge Deployment","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2605.19578","title":"Lens Privacy Sealing: A New Benchmark and Method for Physical Privacy-Preserving Action Recognition","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2608.20157","title":"G3Ego: Gaze-Guided Graphs for Egocentric Action Understanding","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.30584","title":"Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2610.04506","title":"EgoExo-Next:Benchmarking Vision-Language Models on Visual-Option Next-State and Cross-View Reasoning","created":"2026-10-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}