{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T13:00:50Z","timestamp":1779886850875,"version":"3.53.1"},"reference-count":48,"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\/iccv51701.2025.01923","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20683-20693","source":"Crossref","is-referenced-by-count":1,"title":["Factorized Learning for Temporally Grounded Video-Language Models"],"prefix":"10.1109","author":[{"given":"Wenzheng","family":"Zeng","sequence":"first","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Difei","family":"Gao","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mike Zheng","family":"Shou","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hwee Tou","family":"Ng","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Abdin","year":"2024","journal-title":"Phi-3 technical report: A highly capable language model locally on your phone"},{"key":"ref2","article-title":"5-vl technical report","author":"Bai","year":"2025","journal-title":"Qwen2"},{"key":"ref3","author":"Bai","year":"2022","journal-title":"Constitutional ai: Harmlessness from ai feedback"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32214"},{"key":"ref5","author":"Cheng","year":"2024","journal-title":"Videollama 2: Advancing spatialtemporal modeling and audio understanding in video-llms"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01229"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32341"},{"key":"ref11","article-title":"Trace: Temporal grounding video llm via causal event modeling","volume-title":"International Conference on Learning Representations","author":"Guo","year":"2025"},{"key":"ref12","author":"Hu","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_12"},{"key":"ref15","article-title":"Rlaif vs","author":"Lee","year":"2023","journal-title":"rlhf: Scaling reinforcement learning from human feedback with ai feedback"},{"key":"ref16","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1093\/oed\/1147809233"},{"key":"ref18","author":"Li","year":"2025","journal-title":"Temporal preference optimization for longform video understanding"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.360"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref22","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"E.T. Bench: Towards open-ended event-level video-language understanding","volume-title":"The Thirtyeight Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Liu","year":"2024"},{"key":"ref24","article-title":"The flan collection: Designing data and methods for effective instruction tuning. In International Conference on Machine Learning, pages 2263122648","volume-title":"PMLR","author":"Longpre","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.26599\/cvm.2025.9450516"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref29","author":"Qian","year":"2024","journal-title":"Momentor: Advancing video large language model with fine-grained temporal reasoning"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref32","author":"Schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref33","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref34","author":"Sun","year":"2023","journal-title":"Eva-clip: Improved training techniques for clip at scale"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.50"},{"key":"ref37","author":"Wang","year":"2024","journal-title":"Hawkeye: Training videotext 11 ms for grounding text in videos"},{"key":"ref38","author":"Wei","year":"2021","journal-title":"Finetuned language models are zero-shot learners"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01254"},{"key":"ref40","author":"Xu","year":"2024","journal-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning"},{"key":"ref41","author":"Yang","year":"2024","journal-title":"Qwen2 technical report"},{"key":"ref42","author":"Yang","year":"2024","journal-title":"Qwen2.5 technical report"},{"key":"ref43","article-title":"Timesuite: Improving mllms for long video understanding via grounded tuning","volume-title":"International Conference on Learning Representations","author":"Zeng","year":"2025"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0823"},{"key":"ref46","author":"Zhang","year":"2024","journal-title":"Direct preference optimization of video large multimodal models from language model reward"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref48","volume-title":"Fine-tuning language models from human preferences","author":"Ziegler","year":"2020"}],"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\/11444149.pdf?arnumber=11444149","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:11:12Z","timestamp":1777529472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444149\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01923","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}