{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:12:45Z","timestamp":1761894765290,"version":"build-2065373602"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209793","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Localizing Step-by-Step: Multimodal Long Video Temporal Grounding with LLM"],"prefix":"10.1109","author":[{"given":"Houlun","family":"Chen","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}]},{"given":"Hong","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}]},{"given":"Wei","family":"Feng","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}]},{"given":"Zihan","family":"Song","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}]},{"given":"Jia","family":"Jia","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}]},{"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5803","article-title":"Localizing moments in video with natural language","volume-title":"Proceedings of the IEEE ICCV","author":"Hendricks"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"article-title":"Llm4vg: Large language models evaluation for video grounding","year":"2023","author":"Feng","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref5","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 NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612504"},{"article-title":"Verified: A video corpus moment retrieval benchmark for fine-grained video understanding","volume-title":"The Thirty-eight Conference on NeurIPS","author":"Chen","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01357"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32375"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00192"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00618"},{"key":"ref14","first-page":"38032","article-title":"Long-form video-language pre-training with multimodal temporal contrastive learning","volume":"35","author":"Sun","year":"2022","journal-title":"Advances in NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32341"},{"article-title":"Multi-modal generative ai: Multi-modal llm, diffusion and beyond","year":"2024","author":"Chen","key":"ref16"},{"article-title":"Vidchapters-7m: Video chapters at scale","year":"2023","author":"Yang","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00497"},{"key":"ref19","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li"},{"key":"ref20","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"ICML","author":"Radford"},{"key":"ref21","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in NeurIPS"},{"key":"ref22","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Ming-Wei Chang Kenton"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/app14051894"},{"article-title":"Videochat: Chat-centric video understanding","year":"2023","author":"Li","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"article-title":"Grounded-videollm: Sharpening fine-grained temporal grounding in video large language models","year":"2024","author":"Wang","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_24"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209793.pdf?arnumber=11209793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:35:35Z","timestamp":1761888935000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209793\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209793","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}