{"total":29,"rows":[{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2405.03770","title":"Foundation Models for Video Understanding: A Survey","created":"2024-05-06","cited_by_count":46,"area":null},{"id":"2405.13659","title":"EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views","created":"2024-05-22","cited_by_count":26,"area":null},{"id":"2403.01599","title":"SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos","created":"2024-03-03","cited_by_count":24,"area":null},{"id":"2406.08476","title":"RMem: Restricted Memory Banks Improve Video Object Segmentation","created":"2024-06-12","cited_by_count":22,"area":null},{"id":"2402.17128","title":"OSCaR: Object State Captioning and State Change Representation","created":"2024-02-27","cited_by_count":16,"area":null},{"id":"2506.00717","title":"Vid2Coach: Transforming How-To Videos into Task Assistants","created":"2025-05-31","cited_by_count":12,"area":null},{"id":"2412.02071","title":"Progress-Aware Video Frame Captioning","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2412.01987","title":"ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions","created":"2024-12-02","cited_by_count":8,"area":null},{"id":"2604.10409","title":"IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assembly","created":"2026-04-12","cited_by_count":8,"area":null},{"id":"2503.21055","title":"What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning","created":"2025-03-27","cited_by_count":6,"area":null},{"id":"2412.04189","title":"HANDI: Hand-Centric Text-and-Image Conditioned Video Generation","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2503.05962","title":"OSCAR: Object Status and Contextual Awareness for Recipes to Support Non-Visual Cooking","created":"2025-03-07","cited_by_count":5,"area":null},{"id":"2507.15130","title":"Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction","created":"2025-07-20","cited_by_count":5,"area":null},{"id":"2405.01090","title":"Learning Multiple Object States from Actions via Large Language Models","created":"2024-05-02","cited_by_count":4,"area":null},{"id":"2503.11953","title":"SPOC: Spatially-Progressing Object State Change Segmentation in Video","created":"2025-03-15","cited_by_count":3,"area":null},{"id":"2603.11698","title":"OSCBench: Benchmarking Object State Change in Text-to-Video Generation","created":"2026-03-12","cited_by_count":3,"area":null},{"id":"2405.12789","title":"Anticipating Object State Changes in Long Procedural Videos","created":"2024-05-21","cited_by_count":2,"area":null},{"id":"2410.02874","title":"Real-World Cooking Robot System from Recipes Based on Food State Recognition Using Foundation Models and PDDL","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2506.13552","title":"A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2507.03330","title":"Exploring Object Status Recognition for Recipe Progress Tracking in Non-Visual Cooking","created":"2025-07-04","cited_by_count":2,"area":null},{"id":"2509.24129","title":"Mash, Spread, Slice! Learning to Manipulate Object States via Visual Spatial Progress","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2512.00885","title":"HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2503.13821","title":"Stitch-a-Demo: Video Demonstrations from Multistep Descriptions","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2505.02236","title":"Improving Physical Object State Representation in Text-to-Image Generative Systems","created":"2025-05-04","cited_by_count":0,"area":null},{"id":"2604.26565","title":"DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video Annotation","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2607.08514","title":"Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.02044","title":"D\\'ej\\`a Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinates","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.04426","title":"Predict, Then Retrieve: Cross-Instance Future-State Retrieval from Video Prefixes","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":null}