{"total":38,"rows":[{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311,"area":null},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254,"area":null},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184,"area":null},{"id":"2105.11367","title":"FedScale: Benchmarking Model and System Performance of Federated Learning at Scale","created":"2021-05-24","cited_by_count":136,"area":null},{"id":"2107.01153","title":"A Survey on Deep Learning Technique for Video Segmentation","created":"2021-07-02","cited_by_count":132,"area":null},{"id":"2303.16160","title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer","created":"2023-03-28","cited_by_count":130,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2107.09609","title":"QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries","created":"2021-07-20","cited_by_count":72,"area":null},{"id":"2102.12321","title":"AGENT: A Benchmark for Core Psychological Reasoning","created":"2021-02-24","cited_by_count":42,"area":null},{"id":"2211.14154","title":"Interaction Region Visual Transformer for Egocentric Action Anticipation","created":"2022-11-25","cited_by_count":37,"area":null},{"id":"2203.16531","title":"Understanding 3D Object Articulation in Internet Videos","created":"2022-03-30","cited_by_count":36,"area":null},{"id":"2403.19596","title":"LocCa: Visual Pretraining with Location-aware Captioners","created":"2024-03-28","cited_by_count":35,"area":null},{"id":"2111.07868","title":"Tracking People with 3D Representations","created":"2021-11-15","cited_by_count":22,"area":null},{"id":"2211.15501","title":"Proactive Robot Assistance via Spatio-Temporal Object Modeling","created":"2022-11-28","cited_by_count":18,"area":null},{"id":"2207.09425","title":"Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos","created":"2022-07-19","cited_by_count":17,"area":null},{"id":"2109.13499","title":"Modelling Neighbor Relation in Joint Space-Time Graph for Video Correspondence Learning","created":"2021-09-28","cited_by_count":16,"area":null},{"id":"2112.06909","title":"Hallucinating Pose-Compatible Scenes","created":"2021-12-13","cited_by_count":14,"area":null},{"id":"2107.11851","title":"Transcript to Video: Efficient Clip Sequencing from Texts","created":"2021-07-25","cited_by_count":13,"area":null},{"id":"2209.07778","title":"Spatial-then-Temporal Self-Supervised Learning for Video Correspondence","created":"2022-09-16","cited_by_count":13,"area":null},{"id":"2306.03597","title":"Human-Object Interaction Prediction in Videos through Gaze Following","created":"2023-06-06","cited_by_count":13,"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":"2110.03562","title":"Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions","created":"2021-10-07","cited_by_count":8,"area":null},{"id":"2109.02747","title":"WhyAct: Identifying Action Reasons in Lifestyle Vlogs","created":"2021-09-06","cited_by_count":6,"area":null},{"id":"2211.07501","title":"Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions","created":"2022-11-14","cited_by_count":6,"area":null},{"id":"2110.00453","title":"Phonology Recognition in American Sign Language","created":"2021-10-01","cited_by_count":5,"area":null},{"id":"2207.05182","title":"Fine-grained Activities of People Worldwide","created":"2022-07-11","cited_by_count":4,"area":null},{"id":"2208.01753","title":"Two-Stream Transformer Architecture for Long Video Understanding","created":"2022-08-02","cited_by_count":4,"area":null},{"id":"2404.18934","title":"The Visual Experience Dataset: Over 200 Recorded Hours of Integrated Eye Movement, Odometry, and Egocentric Video","created":"2024-02-15","cited_by_count":4,"area":null},{"id":"2506.03440","title":"Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2303.08920","title":"EgoViT: Pyramid Video Transformer for Egocentric Action Recognition","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2603.25539","title":"PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videos","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2109.14744","title":"The Object at Hand: Automated Editing for Mixed Reality Video Guidance from Hand-Object Interactions","created":"2021-09-29","cited_by_count":1,"area":null},{"id":"2112.12409","title":"InstaIndoor and Multi-modal Deep Learning for Indoor Scene Recognition","created":"2021-12-23","cited_by_count":1,"area":null},{"id":"2202.08138","title":"When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs","created":"2022-02-16","cited_by_count":1,"area":null},{"id":"2504.15182","title":"Tiger200K: Manually Curated High Visual Quality Video Dataset from UGC Platform","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2305.18070","title":"Forensic Video Steganalysis in Spatial Domain by Noise Residual Convolutional Neural Network","created":"2023-05-29","cited_by_count":0,"area":null},{"id":"2308.03061","title":"InterTracker: Discovering and Tracking General Objects Interacting with Hands in the Wild","created":"2023-08-06","cited_by_count":0,"area":null},{"id":"2309.06219","title":"Human Action Co-occurrence in Lifestyle Vlogs using Graph Link Prediction","created":"2023-09-12","cited_by_count":0,"area":null}],"next_cursor":null}