{"total":24,"rows":[{"id":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84,"area":null},{"id":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63,"area":null},{"id":"2302.13668","title":"Contrastive Video Question Answering via Video Graph Transformer","created":"2023-02-27","cited_by_count":32,"area":null},{"id":"2405.16925","title":"OED: Towards One-stage End-to-End Dynamic Scene Graph Generation","created":"2024-05-27","cited_by_count":23,"area":null},{"id":"2308.05081","title":"Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling","created":"2023-08-09","cited_by_count":15,"area":null},{"id":"2503.07635","title":"Cross-modal Causal Relation Alignment for Video Question Grounding","created":"2025-03-05","cited_by_count":12,"area":null},{"id":"2210.16472","title":"Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation","created":"2022-10-29","cited_by_count":11,"area":null},{"id":"2403.04899","title":"Towards Scene Graph Anticipation","created":"2024-03-07","cited_by_count":10,"area":null},{"id":"2211.06119","title":"SSGVS: Semantic Scene Graph-to-Video Synthesis","created":"2022-11-11","cited_by_count":8,"area":null},{"id":"2304.03754","title":"Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering","created":"2023-04-07","cited_by_count":6,"area":null},{"id":"2306.00012","title":"Graph Neural Network for spatiotemporal data: methods and applications","created":"2023-05-30","cited_by_count":6,"area":null},{"id":"2309.08612","title":"Explaining Vision and Language through Graphs of Events in Space and Time","created":"2023-08-29","cited_by_count":4,"area":null},{"id":"2602.23543","title":"Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2507.15150","title":"Event-based Graph Representation with Spatial and Motion Vectors for Asynchronous Object Detection","created":"2025-07-20","cited_by_count":2,"area":null},{"id":"2510.10671","title":"Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2305.04824","title":"Learning Summary-Worthy Visual Representation for Abstractive Summarization in Video","created":"2023-05-08","cited_by_count":1,"area":null},{"id":"2506.01487","title":"FDSG: Forecasting Dynamic Scene Graphs","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2305.12940","title":"GEST: the Graph of Events in Space and Time as a Common Representation between Vision and Language","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2306.13420","title":"Towards Unseen Triples: Effective Text-Image-joint Learning for Scene Graph Generation","created":"2023-06-23","cited_by_count":0,"area":null},{"id":"2410.07987","title":"A transition towards virtual representations of visual scenes","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2504.02417","title":"Leveraging Static Relationships for Intra-Type and Inter-Type Message Passing in Video Question Answering","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2511.20201","title":"GHR-VQA: Graph-guided Hierarchical Relational Reasoning for Video Question Answering","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2604.19631","title":"MOSA: Motion-Guided Semantic Alignment for Dynamic Scene Graph Generation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2610.20091","title":"RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}