{"total":55,"rows":[{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744,"area":null},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2110.05122","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","created":"2021-10-11","cited_by_count":86,"area":null},{"id":"2103.15538","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","created":"2021-03-29","cited_by_count":84,"area":null},{"id":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84,"area":null},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76,"area":"mllm"},{"id":"2112.06197","title":"Video as Conditional Graph Hierarchy for Multi-Granular Question Answering","created":"2021-12-12","cited_by_count":68,"area":null},{"id":"2206.02349","title":"Invariant Grounding for Video Question Answering","created":"2022-06-06","cited_by_count":68,"area":null},{"id":"2406.09396","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","created":"2024-06-13","cited_by_count":68,"area":null},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60,"area":null},{"id":"2103.10095","title":"On Semantic Similarity in Video Retrieval","created":"2021-03-18","cited_by_count":46,"area":null},{"id":"2406.08407","title":"MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos","created":"2024-06-12","cited_by_count":43,"area":"wm"},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"area":null},{"id":"2209.06997","title":"M^4I: Multi-modal Models Membership Inference","created":"2022-09-15","cited_by_count":34,"area":"safety"},{"id":"2205.05019","title":"Learning to Answer Visual Questions from Web Videos","created":"2022-05-10","cited_by_count":30,"area":null},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2403.16998","title":"Understanding Long Videos with Multimodal Language Models","created":"2024-03-25","cited_by_count":25,"area":"mllm"},{"id":"2404.01476","title":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","created":"2024-04-01","cited_by_count":25,"area":"mllm"},{"id":"2302.11217","title":"Connecting Vision and Language with Video Localized Narratives","created":"2023-02-22","cited_by_count":24,"area":null},{"id":"2207.12783","title":"Equivariant and Invariant Grounding for Video Question Answering","created":"2022-07-26","cited_by_count":22,"area":null},{"id":"2301.09209","title":"Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation","created":"2023-01-22","cited_by_count":21,"area":null},{"id":"2205.05739","title":"Learning to Retrieve Videos by Asking Questions","created":"2022-05-11","cited_by_count":18,"area":null},{"id":"2112.03572","title":"Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices","created":"2021-12-07","cited_by_count":17,"area":null},{"id":"2304.08682","title":"Learning Situation Hyper-Graphs for Video Question Answering","created":"2023-04-18","cited_by_count":16,"area":null},{"id":"2305.02519","title":"ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos","created":"2023-05-04","cited_by_count":15,"area":null},{"id":"2104.03762","title":"Video Question Answering with Phrases via Semantic Roles","created":"2021-04-08","cited_by_count":13,"area":null},{"id":"2404.01299","title":"CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes","created":"2024-04-01","cited_by_count":13,"area":"lr"},{"id":"2101.05954","title":"Recent Advances in Video Question Answering: A Review of Datasets and Methods","created":"2021-01-15","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":"2209.06650","title":"WildQA: In-the-Wild Video Question Answering","created":"2022-09-14","cited_by_count":9,"area":null},{"id":"2203.14456","title":"3MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videos","created":"2022-03-28","cited_by_count":8,"area":null},{"id":"2311.01233","title":"Long Story Short: a Summarize-then-Search Method for Long Video Question Answering","created":"2023-11-02","cited_by_count":7,"area":null},{"id":"2504.15270","title":"An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes","created":"2025-04-21","cited_by_count":7,"area":"mllm"},{"id":"2101.01447","title":"End-to-End Video Question-Answer Generation with Generator-Pretester Network","created":"2021-01-05","cited_by_count":6,"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":"2306.09922","title":"Learning to Summarize and Answer Questions about a Virtual Robot's Past Actions","created":"2023-06-16","cited_by_count":5,"area":null},{"id":"2410.09380","title":"Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering","created":"2024-10-12","cited_by_count":5,"area":null},{"id":"2107.10300","title":"iReason: Multimodal Commonsense Reasoning using Videos and Natural Language with Interpretability","created":"2021-06-25","cited_by_count":4,"area":null},{"id":"2202.04015","title":"NEWSKVQA: Knowledge-Aware News Video Question Answering","created":"2022-02-08","cited_by_count":4,"area":null},{"id":"2105.06160","title":"Relation-aware Hierarchical Attention Framework for Video Question Answering","created":"2021-05-13","cited_by_count":3,"area":null},{"id":"2108.04542","title":"TrUMAn: Trope Understanding in Movies and Animations","created":"2021-08-10","cited_by_count":3,"area":null},{"id":"2305.03204","title":"VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation","created":"2023-05-04","cited_by_count":3,"area":"lr"},{"id":"2410.09379","title":"Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering","created":"2024-10-12","cited_by_count":3,"area":null},{"id":"2110.11881","title":"Simple Dialogue System with AUDITED","created":"2021-10-22","cited_by_count":2,"area":null},{"id":"2210.03941","title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling","created":"2022-10-08","cited_by_count":2,"area":null},{"id":"2101.06803","title":"Narration Generation for Cartoon Videos","created":"2021-01-17","cited_by_count":1,"area":null},{"id":"2406.10923","title":"Investigating Video Reasoning Capability of Large Language Models with Tropes in Movies","created":"2024-06-16","cited_by_count":1,"area":"lr"},{"id":"2502.13034","title":"Natural Language Generation from Visual Events: State-of-the-Art and Key Open Questions","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2312.12721","title":"Cross-Modal Reasoning with Event Correlation for Video Question Answering","created":"2023-12-20","cited_by_count":0,"area":null},{"id":"2411.07584","title":"Grounded Video Caption Generation","created":"2024-11-12","cited_by_count":0,"area":null},{"id":"2506.04983","title":"TextVidBench: A Benchmark for Long Video Scene Text Understanding","created":"2025-06-05","cited_by_count":0,"area":"mllm"},{"id":"2608.23330","title":"IntentQA: Intent Question Answering in Videos by Cognitive Context Reasoning","created":"2026-08-24","cited_by_count":0,"area":"lr"}],"next_cursor":null}