{"total":38,"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":"2405.14868","title":"Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis","created":"2024-05-23","cited_by_count":117,"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":"2105.07404","title":"MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions","created":"2021-05-16","cited_by_count":84,"area":null},{"id":"2211.01917","title":"Expanding Accurate Person Recognition to New Altitudes and Ranges: The BRIAR Dataset","created":"2022-11-03","cited_by_count":61,"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":"2107.02396","title":"Semi-TCL: Semi-Supervised Track Contrastive Representation Learning","created":"2021-07-06","cited_by_count":23,"area":null},{"id":"2201.03080","title":"The State of Aerial Surveillance: A Survey","created":"2022-01-09","cited_by_count":20,"area":null},{"id":"2505.12589","title":"SurveillanceVQA-589K: A Benchmark for Comprehensive Surveillance Video-Language Understanding with Large Models","created":"2025-05-19","cited_by_count":18,"area":null},{"id":"2301.03561","title":"Ancilia: Scalable Intelligent Video Surveillance for the Artificial Intelligence of Things","created":"2023-01-09","cited_by_count":17,"area":null},{"id":"2211.04656","title":"MEVID: Multi-view Extended Videos with Identities for Video Person Re-Identification","created":"2022-11-09","cited_by_count":16,"area":null},{"id":"2503.17116","title":"The CASTLE 2024 Dataset: Advancing the Art of Multimodal Understanding","created":"2025-03-21","cited_by_count":16,"area":null},{"id":"2211.02175","title":"Large Scale Real-World Multi-Person Tracking","created":"2022-11-03","cited_by_count":14,"area":null},{"id":"2204.07892","title":"Video Action Detection: Analysing Limitations and Challenges","created":"2022-04-17","cited_by_count":12,"area":null},{"id":"2403.03194","title":"MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets","created":"2024-03-05","cited_by_count":10,"area":null},{"id":"2205.10766","title":"Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey","created":"2022-05-22","cited_by_count":8,"area":null},{"id":"2305.19160","title":"Recognizing People by Body Shape Using Deep Networks of Images and Words","created":"2023-05-30","cited_by_count":8,"area":null},{"id":"2201.05290","title":"Argus++: Robust Real-time Activity Detection for Unconstrained Video Streams with Overlapping Cube Proposals","created":"2022-01-14","cited_by_count":6,"area":null},{"id":"2401.15900","title":"MV2MAE: Multi-View Video Masked Autoencoders","created":"2024-01-29","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":"2107.11494","title":"TinyAction Challenge: Recognizing Real-world Low-resolution Activities in Videos","created":"2021-07-24","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":"2309.09518","title":"NOMAD: A Natural, Occluded, Multi-scale Aerial Dataset, for Emergency Response Scenarios","created":"2023-09-18","cited_by_count":4,"area":null},{"id":"2502.15934","title":"Dissecting Human Body Representations in Deep Networks Trained for Person Identification","created":"2025-02-21","cited_by_count":4,"area":null},{"id":"2506.12992","title":"SmartHome-Bench: A Comprehensive Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal Large Language Models","created":"2025-06-15","cited_by_count":4,"area":null},{"id":"2110.14613","title":"International Workshop on Continual Semi-Supervised Learning: Introduction, Benchmarks and Baselines","created":"2021-10-27","cited_by_count":3,"area":null},{"id":"2402.14136","title":"GDTM: An Indoor Geospatial Tracking Dataset with Distributed Multimodal Sensors","created":"2024-02-21","cited_by_count":3,"area":null},{"id":"2502.07130","title":"Unconstrained Body Recognition at Altitude and Range: Comparing Four Approaches","created":"2025-02-10","cited_by_count":2,"area":null},{"id":"2204.02688","title":"MM-SEAL: A Large-scale Video Dataset of Multi-person Multi-grained Spatio-temporally Action Localization","created":"2022-04-06","cited_by_count":1,"area":null},{"id":"2301.06866","title":"Building Scalable Video Understanding Benchmarks through Sports","created":"2023-01-17","cited_by_count":1,"area":null},{"id":"2409.04187","title":"LITE: A Paradigm Shift in Multi-Object Tracking with Efficient ReID Feature Integration","created":"2024-09-06","cited_by_count":1,"area":null},{"id":"2604.07772","title":"ESOM: Efficiently Understanding Streaming Video Anomalies with Open-world Dynamic Definitions","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2606.20542","title":"CalTennis: Large Multi-View Tennis Video Dataset and Benchmark of Monocular-to-3D Pose Estimation","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2110.13386","title":"Self-Denoising Neural Networks for Few Shot Learning","created":"2021-10-26","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":"2504.03096","title":"Scaling Open-Vocabulary Action Detection","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2512.24386","title":"RedunCut: Measurement-Driven Sampling and Accuracy Performance Modeling for Low-Cost Live Video Analytics","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2605.02784","title":"HumanSplatHMR: Closing the Loop Between Human Mesh Recovery and Gaussian Splatting Avatar","created":"2026-05-04","cited_by_count":0,"area":null}],"next_cursor":null}