{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:18:40Z","timestamp":1784179120456,"version":"3.55.0"},"reference-count":65,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02251","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24286-24296","source":"Crossref","is-referenced-by-count":2,"title":["Timeexpert: an Expert-Guided Video Llm for Video Temporal Grounding"],"prefix":"10.1109","author":[{"given":"Zuhao","family":"Yang","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingchen","family":"Yu","sequence":"additional","affiliation":[{"name":"ByteDance Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunqing","family":"Zhao","sequence":"additional","affiliation":[{"name":"ByteDance Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shijian","family":"Lu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Bai","sequence":"additional","affiliation":[{"name":"ByteDance Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee","year":"2005"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3185"},{"key":"ref5","article-title":"Videollama 2: Advancing spatialtemporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","first-page":"4057","article-title":"Unified scaling laws for routed language models","volume-title":"International Conference on Machine Learning","author":"Clark","year":"2022"},{"key":"ref7","article-title":"An image is worth 16 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Learning factored representations in a deep mixture of experts","author":"Eigen","year":"2013","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Towards an empirical understanding of moe design choices","author":"Fan","year":"2024","journal-title":"arXiv preprint"},{"issue":"120","key":"ref10","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_31"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref14","article-title":"Dynamic mixture of experts: An autotuning approach for efficient transformer models","volume-title":"International Conference on Learning Representations","author":"Guo","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32341"},{"key":"ref16","article-title":"Trace: Temporal grounding video llm via causal event modeling","volume-title":"International Conference on Learning Representations","author":"Guo","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"ref18","first-page":"8275","article-title":"Unleash the potential of clip for video highlight detection","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Han","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_12"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.696"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01318"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref24","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","author":"Lei","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","article-title":"Aria: An open multimodal native mixture-ofexperts model","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3532688"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00262"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref33","article-title":"Valley: Video assistant with large language model enhanced ability","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref35","article-title":"Correlation-guided query-dependency calibration for video temporal grounding","author":"Moon","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.400"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414640"},{"key":"ref39","article-title":"Momentor: Advancing video large language model with fine-grained temporal reasoning","volume-title":"International Conference on Machine Learning","author":"Qian","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref41","article-title":"The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"Outrageously large neural networks"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref45","article-title":"Grounded-videollm: Sharpening fine-grained temporal grounding in video large language models","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref48","article-title":"Internvideo: General video foundation models via generative and discriminative learning","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Hawkeye: Training videotext llms for grounding text in videos","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Star: A benchmark for situated reasoning in real-world videos","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110818"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2984"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref55","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"M6-t: Exploring sparse expert models and beyond","author":"Yang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.694"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02208"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_17"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.361"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref63","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref65","article-title":"Stmoe: Designing stable and transferable sparse expert models","author":"Zoph","year":"2022","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\/11446107.pdf?arnumber=11446107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:49Z","timestamp":1777529929000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446107\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02251","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}