{"total":16,"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":"2407.15350","title":"WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2203.07086","title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization","created":"2022-03-14","cited_by_count":10,"area":null},{"id":"2401.11654","title":"ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition","created":"2024-01-22","cited_by_count":8,"area":null},{"id":"2201.05290","title":"Argus++: Robust Real-time Activity Detection for Unconstrained Video Streams with Overlapping Cube Proposals","created":"2022-01-14","cited_by_count":6,"area":null},{"id":"2202.01031","title":"MMSys'22 Grand Challenge on AI-based Video Production for Soccer","created":"2022-02-02","cited_by_count":6,"area":null},{"id":"2210.11707","title":"Video Summarization Overview","created":"2022-10-21","cited_by_count":6,"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":"2404.06173","title":"Improving Interpretable Embeddings for Ad-hoc Video Search with Generative Captions and Multi-word Concept Bank","created":"2024-04-09","cited_by_count":3,"area":null},{"id":"2112.14088","title":"Synchronized Audio-Visual Frames with Fractional Positional Encoding for Transformers in Video-to-Text Translation","created":"2021-12-28","cited_by_count":2,"area":null},{"id":"2406.02780","title":"LADI v2: Multi-label Dataset and Classifiers for Low-Altitude Disaster Imagery","created":"2024-06-04","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":"2312.00268","title":"Academic competitions","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2405.16728","title":"Towards Multi-Task Multi-Modal Models: A Video Generative Perspective","created":"2024-05-26","cited_by_count":0,"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}