{"total":50,"rows":[{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"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":"2103.16564","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","created":"2021-03-30","cited_by_count":68,"area":null},{"id":"2101.00443","title":"Semantics for Robotic Mapping, Perception and Interaction: A Survey","created":"2021-01-02","cited_by_count":56,"area":null},{"id":"2104.00969","title":"TubeR: Tubelet Transformer for Video Action Detection","created":"2021-04-02","cited_by_count":55,"area":null},{"id":"2110.15358","title":"Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language","created":"2021-10-28","cited_by_count":55,"area":null},{"id":"2102.11585","title":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","created":"2021-02-23","cited_by_count":54,"area":null},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48,"area":null},{"id":"2209.08323","title":"RGB-Event Fusion for Moving Object Detection in Autonomous Driving","created":"2022-09-17","cited_by_count":40,"area":null},{"id":"2104.03178","title":"The SARAS Endoscopic Surgeon Action Detection (ESAD) dataset: Challenges and methods","created":"2021-04-07","cited_by_count":38,"area":null},{"id":"2110.00111","title":"Deep Learning-based Action Detection in Untrimmed Videos: A Survey","created":"2021-09-30","cited_by_count":32,"area":null},{"id":"2304.01199","title":"On the Benefits of 3D Pose and Tracking for Human Action Recognition","created":"2023-04-03","cited_by_count":32,"area":null},{"id":"2303.15879","title":"STMixer: A One-Stage Sparse Action Detector","created":"2023-03-28","cited_by_count":22,"area":null},{"id":"2102.07887","title":"VA-RED$^2$: Video Adaptive Redundancy Reduction","created":"2021-02-15","cited_by_count":15,"area":null},{"id":"2104.04715","title":"Object Priors for Classifying and Localizing Unseen Actions","created":"2021-04-10","cited_by_count":15,"area":null},{"id":"2208.01949","title":"Negative Frames Matter in Egocentric Visual Query 2D Localization","created":"2022-08-03","cited_by_count":14,"area":null},{"id":"2209.02250","title":"Spatio-Temporal Action Detection Under Large Motion","created":"2022-09-06","cited_by_count":14,"area":null},{"id":"2301.01882","title":"InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation","created":"2023-01-05","cited_by_count":13,"area":null},{"id":"2110.04119","title":"A Multi-viewpoint Outdoor Dataset for Human Action Recognition","created":"2021-10-07","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":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2203.10719","title":"LocATe: End-to-end Localization of Actions in 3D with Transformers","created":"2022-03-21","cited_by_count":8,"area":null},{"id":"2111.05448","title":"Towards Active Vision for Action Localization with Reactive Control and Predictive Learning","created":"2021-11-09","cited_by_count":5,"area":null},{"id":"2304.11975","title":"MRSN: Multi-Relation Support Network for Video Action Detection","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2308.01618","title":"A Survey on Deep Learning-based Spatio-temporal Action Detection","created":"2023-08-03","cited_by_count":5,"area":null},{"id":"2307.06577","title":"RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation","created":"2023-07-13","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":"2407.05610","title":"Described Spatial-Temporal Video Detection","created":"2024-07-08","cited_by_count":3,"area":null},{"id":"2203.03796","title":"PAMI-AD: An Activity Detector Exploiting Part-attention and Motion Information in Surveillance Videos","created":"2022-03-08","cited_by_count":2,"area":null},{"id":"2403.12385","title":"Benchmarking Badminton Action Recognition with a New Fine-Grained Dataset","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2110.09110","title":"Graph Convolution Neural Network For Weakly Supervised Abnormality Localization In Long Capsule Endoscopy Videos","created":"2021-10-18","cited_by_count":1,"area":null},{"id":"2203.10584","title":"Point3D: tracking actions as moving points with 3D CNNs","created":"2022-03-20","cited_by_count":1,"area":null},{"id":"2407.19430","title":"Progressive Domain Adaptation for Thermal Infrared Object Tracking","created":"2024-07-28","cited_by_count":1,"area":null},{"id":"2101.08567","title":"Discovering Multi-Label Actor-Action Association in a Weakly Supervised Setting","created":"2021-01-21","cited_by_count":0,"area":null},{"id":"2101.08581","title":"Hierarchical Graph-RNNs for Action Detection of Multiple Activities","created":"2021-01-21","cited_by_count":0,"area":null},{"id":"2102.03391","title":"Single Run Action Detector over Video Stream -- A Privacy Preserving Approach","created":"2021-02-05","cited_by_count":0,"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":"2111.03319","title":"KORSAL: Key-point Detection based Online Real-Time Spatio-Temporal Action Localization","created":"2021-11-05","cited_by_count":0,"area":null},{"id":"2205.00364","title":"RADNet: A Deep Neural Network Model for Robust Perception in Moving Autonomous Systems","created":"2022-04-30","cited_by_count":0,"area":null},{"id":"2205.05895","title":"Weakly-Supervised Action Detection Guided by Audio Narration","created":"2022-05-12","cited_by_count":0,"area":null},{"id":"2206.08429","title":"Scalable Temporal Localization of Sensitive Activities in Movies and TV Episodes","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2208.12940","title":"Actor-identified Spatiotemporal Action Detection -- Detecting Who Is Doing What in Videos","created":"2022-08-27","cited_by_count":0,"area":null},{"id":"2211.14449","title":"PatchBlender: A Motion Prior for Video Transformers","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2303.07790","title":"Object Detection During Newborn Resuscitation Activities","created":"2023-03-14","cited_by_count":0,"area":null},{"id":"2404.09842","title":"STMixer: A One-Stage Sparse Action Detector","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2409.18408","title":"Query matching for spatio-temporal action detection with query-based object detector","created":"2024-09-27","cited_by_count":0,"area":null},{"id":"2412.13708","title":"JoVALE: Detecting Human Actions in Video Using Audiovisual and Language Contexts","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2503.12969","title":"Action tube generation by person query matching for spatio-temporal action detection","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2507.21247","title":"Dual Guidance Semi-Supervised Action Detection","created":"2025-07-28","cited_by_count":0,"area":null}],"next_cursor":null}