{"total":13,"rows":[{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542,"area":null},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73,"area":null},{"id":"2105.09939","title":"Face, Body, Voice: Video Person-Clustering with Multiple Modalities","created":"2021-05-20","cited_by_count":24,"area":null},{"id":"2112.02303","title":"An Annotated Video Dataset for Computing Video Memorability","created":"2021-12-04","cited_by_count":9,"area":null},{"id":"2307.03153","title":"MultiVENT: Multilingual Videos of Events with Aligned Natural Text","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2412.18086","title":"Generating Traffic Scenarios via In-Context Learning to Learn Better Motion Planner","created":"2024-12-24","cited_by_count":6,"area":null},{"id":"2103.14785","title":"A Comprehensive Review of the Video-to-Text Problem","created":"2021-03-27","cited_by_count":5,"area":null},{"id":"2112.05982","title":"Overview of The MediaEval 2021 Predicting Media Memorability Task","created":"2021-12-11","cited_by_count":5,"area":null},{"id":"2402.11812","title":"Interpretable Embedding for Ad-hoc Video Search","created":"2024-02-19","cited_by_count":4,"area":null},{"id":"2201.10243","title":"BERTHA: Video Captioning Evaluation Via Transfer-Learned Human Assessment","created":"2022-01-25","cited_by_count":3,"area":null},{"id":"2212.03955","title":"Experiences from the MediaEval Predicting Media Memorability Task","created":"2022-12-07","cited_by_count":2,"area":null},{"id":"2112.14100","title":"Extended Self-Critical Pipeline for Transforming Videos to Text (TRECVID-VTT Task 2021) -- Team: MMCUniAugsburg","created":"2021-12-28","cited_by_count":1,"area":null},{"id":"2508.02340","title":"Learning Partially-Decorrelated Common Spaces for Ad-hoc Video Search","created":"2025-08-04","cited_by_count":0,"area":null}],"next_cursor":null}