{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:10Z","timestamp":1777889650651,"version":"3.51.4"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372014"],"award-info":[{"award-number":["62372014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4252040"],"award-info":[{"award-number":["4252040"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02039","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21961-21971","source":"Crossref","is-referenced-by-count":1,"title":["DisTime: Distribution-Based Time Representation for Video Large Language Models"],"prefix":"10.1109","author":[{"given":"Yingsen","family":"Zeng","sequence":"first","affiliation":[{"name":"Meituan Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zepeng","family":"Huang","sequence":"additional","affiliation":[{"name":"Meituan Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujie","family":"Zhong","sequence":"additional","affiliation":[{"name":"Meituan Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengjian","family":"Feng","sequence":"additional","affiliation":[{"name":"Meituan Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Hu","sequence":"additional","affiliation":[{"name":"Meituan Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Meituan Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref3","article-title":"Cgbench: Clue-grounded question answering benchmark for long video understanding","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Timemarker: A versatile video-llm for long and short video understanding with superior temporal localization ability","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"issue":"3","key":"ref7","volume":"2","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90% chatgpt quality"},{"key":"ref8","article-title":"Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal 11 ms in video analysis","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref10","article-title":"Linvt: Empower your image-level large language model to understand videos","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Saliency-guided detr for moment retrieval and highlight detection","author":"Gordeev","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref13","article-title":"Vtg-llm: Integrating timestamp knowledge into video 11 ms for enhanced video temporal grounding","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"issue":"2","key":"ref14","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref17","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume":"34","author":"Lei","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"In International conference on machine learning","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref22","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume":"33","author":"Li","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.360"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3395778"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00262"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref28","article-title":"Et bench: Towards open-ended event-level video-language understanding","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Llava-mr: Large language-andvision assistant for video moment retrieval","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Valley: Video assistant with large language model enhanced ability","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"The surprising effectiveness of multimodal large language models for video moment retrieval","author":"Meinardus","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Correlation-guided query-dependency calibration for video temporal grounding","author":"Moon","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02561"},{"key":"ref35","article-title":"Momentor: Advancing video large language model with fine-grained temporal reasoning","author":"Qian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00191"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref38","article-title":"xgen-mm-vid (blip-3video): You only need 32 tokens to represent a video even in vlms","author":"Ryoo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_7"},{"key":"ref40","article-title":"Temporal action localization with enhanced instant discriminability","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"ref42","article-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref44","article-title":"Internvideo2. 5: Empowering video mllms with long and rich context modeling","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref45","first-page":"28828","article-title":"Longvideobench: A benchmark for long-context interleaved video-language understanding","volume":"37","author":"Wu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01254"},{"key":"ref47","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0010"},{"key":"ref49","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3354"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_17"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref54","article-title":"Ld-detr: Loop decoder detection transformer for video moment retrieval and highlight detection","author":"Zhao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_2"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref57","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445253.pdf?arnumber=11445253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:18:31Z","timestamp":1777612711000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02039","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}