{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:18:11Z","timestamp":1784179091970,"version":"3.55.0"},"reference-count":58,"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\/iccv51701.2025.02243","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24203-24213","source":"Crossref","is-referenced-by-count":1,"title":["VTimeCoT: Thinking by Drawing for Video Temporal Grounding and Reasoning"],"prefix":"10.1109","author":[{"given":"Jinglei","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanfan","family":"Guo","sequence":"additional","affiliation":[{"name":"Noah's Ark Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rolandos Alexandros","family":"Potamias","sequence":"additional","affiliation":[{"name":"Imperial College London"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiankang","family":"Deng","sequence":"additional","affiliation":[{"name":"Imperial College London"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[{"name":"Noah's Ark Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Abid","year":"2019","journal-title":"Gradio: Hassle-free sharing and testing of ml models in the wild"},{"key":"ref2","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref3","author":"Nahida Akter","year":"2024","journal-title":"Self-imagine: Effective unimodal reasoning with multimodal models using self-imagination"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01227"},{"key":"ref5","author":"Chen","year":"2024","journal-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling"},{"key":"ref6","author":"Cheng","year":"2024","journal-title":"Videollama 2: Advancing spatialtemporal modeling and audio understanding in video-llms"},{"key":"ref7","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90* chatgpt quality"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_18"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02245"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4423"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00916"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_12"},{"key":"ref17","author":"Hurst","year":"2024","journal-title":"Gpt-4o system card"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","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":"ref20","author":"Li","year":"2024","journal-title":"Llava-onevision: Easy visual task transfer"},{"key":"ref21","author":"Li","year":"2025","journal-title":"Imagine while reasoning in space: Multimodal visualization-ofthought"},{"key":"ref22","author":"Li","year":"2024","journal-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref26","author":"Lin","year":"2023","journal-title":"Video-llava: Learning united visual representation by alignment before projection"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref28","first-page":"1","article-title":"St-llm: Large language models are effective temporal learners","volume-title":"European Conference on Computer Vision","author":"Liu","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_8"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00390"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1117"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01257"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01143"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref36","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.544"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.51644\/9781771120920-031"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3429"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.898"},{"key":"ref43","author":"Wang","year":"2024","journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33335-4_14396"},{"key":"ref46","first-page":"90277","article-title":"Mind\u2019s eye of 11 ms: visualization-of-thought elicits spatial reasoning in large language models","volume":"37","author":"Wu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_10"},{"key":"ref48","author":"Xu","year":"2024","journal-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning"},{"key":"ref49","author":"Xue","year":"2024","journal-title":"Longvila: Scaling long-context visual language models for long videos"},{"key":"ref50","author":"Yang","year":"2024","journal-title":"Vript: A video is worth thousands of words"},{"key":"ref51","author":"Yang","year":"2023","journal-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v"},{"key":"ref52","author":"Yang","year":"2023","journal-title":"Mm-react: Prompting chatgpt for multimodal reasoning and action"},{"key":"ref53","article-title":"Doraemongpt: Toward understanding dynamic scenes with large language models (exemplified as a video agent)","volume-title":"Forty-first International Conference on Machine Learning","author":"Yang","year":"2024"},{"key":"ref54","article-title":"mplugowl3: Towards long image-sequence understanding in multimodal large language models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Ye","year":"2024"},{"key":"ref55","author":"Zhang","year":"2025","journal-title":"Videollama 3: Frontier multimodal foundation models for image and video understanding"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00175"},{"key":"ref58","author":"Zhang","year":"2024","journal-title":"Video instruction tuning with synthetic data"}],"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\/11445846.pdf?arnumber=11445846","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:22:56Z","timestamp":1777612976000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445846\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02243","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}