{"total":35,"rows":[{"id":"2405.11656","title":"URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Images","created":"2024-05-19","cited_by_count":111,"area":null},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2401.02955","title":"Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively","created":"2024-01-05","cited_by_count":75,"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":"2503.02579","title":"MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments","created":"2025-03-04","cited_by_count":28,"area":null},{"id":"2503.23715","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","created":"2025-03-31","cited_by_count":26,"area":null},{"id":"2312.03050","title":"HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding","created":"2023-12-05","cited_by_count":22,"area":null},{"id":"2405.10305","title":"4D Panoptic Scene Graph Generation","created":"2024-05-16","cited_by_count":22,"area":null},{"id":"2501.05037","title":"LongViTU: Instruction Tuning for Long-Form Video Understanding","created":"2025-01-09","cited_by_count":13,"area":null},{"id":"2406.01029","title":"CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos","created":"2024-06-03","cited_by_count":11,"area":null},{"id":"2503.15005","title":"Universal Scene Graph Generation","created":"2025-03-19","cited_by_count":11,"area":null},{"id":"2409.10262","title":"Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation","created":"2024-09-16","cited_by_count":10,"area":null},{"id":"2503.00548","title":"Unbiased Video Scene Graph Generation via Visual and Semantic Dual Debiasing","created":"2025-03-01","cited_by_count":6,"area":null},{"id":"2503.15019","title":"Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scene","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2507.04815","title":"From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approach","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2410.22829","title":"Situational Scene Graph for Structured Human-centric Situation Understanding","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2504.07867","title":"SAMJAM: Zero-Shot Video Scene Graph Generation for Egocentric Kitchen Videos","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2506.21813","title":"CAT-SG: A Large Dynamic Scene Graph Dataset for Fine-Grained Understanding of Cataract Surgery","created":"2025-06-26","cited_by_count":4,"area":null},{"id":"2408.02272","title":"COM Kitchens: An Unedited Overhead-view Video Dataset as a Vision-Language Benchmark","created":"2024-08-05","cited_by_count":3,"area":null},{"id":"2408.08305","title":"Towards Flexible Visual Relationship Segmentation","created":"2024-08-15","cited_by_count":2,"area":null},{"id":"2506.00083","title":"Hi-Dyna Graph: Hierarchical Dynamic Scene Graph for Robotic Autonomy in Human-Centric Environments","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2509.06165","title":"UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning","created":"2025-09-07","cited_by_count":2,"area":null},{"id":"2404.06265","title":"Spatial-Temporal Multi-level Association for Video Object Segmentation","created":"2024-04-09","cited_by_count":1,"area":null},{"id":"2405.02162","title":"Mapping the Unseen: Unified Promptable Panoptic Mapping with Dynamic Labeling using Foundation Models","created":"2024-05-03","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":"2507.09200","title":"THYME: Temporal Hierarchical-Cyclic Interactivity Modeling for Video Scene Graphs in Aerial Footage","created":"2025-07-12","cited_by_count":0,"area":null},{"id":"2508.07171","title":"EventRR: Event Referential Reasoning for Referring Video Object Segmentation","created":"2025-08-10","cited_by_count":0,"area":null},{"id":"2511.15948","title":"Click2Graph: Interactive Panoptic Video Scene Graphs from a Single Click","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2603.16645","title":"BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detection","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.10385","title":"GTASA: Ground Truth Annotations for Spatiotemporal Analysis, Evaluation and Training of Video Models","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2604.22274","title":"CAGE-SGG: Counterfactual Active Graph Evidence for Open-Vocabulary Scene Graph Generation","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2604.22546","title":"ReLIC-SGG: Relation Lattice Completion for Open-Vocabulary Scene Graph Generation","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2604.23173","title":"One Identity, Many Roles: Multimodal Entity Coreference for Enhanced Video Situation Recognition","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.12074","title":"BARISTA: A Multi-Task Egocentric Benchmark for Compositional Visual Understanding","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2607.21228","title":"T-STAR: A Large-Scale Benchmark for Spatio-Temporal Panoptic Scene Graph Generation in Satellite Video","created":"2026-07-23","cited_by_count":0,"area":null}],"next_cursor":null}