{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T01:07:18Z","timestamp":1789348038573,"version":"build-2803163510"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2024.3511426","type":"journal-article","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T19:27:56Z","timestamp":1733340476000},"page":"281-285","source":"Crossref","is-referenced-by-count":7,"title":["MLLM-TA: Leveraging Multimodal Large Language Models for Precise Temporal Video Grounding"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4727-0572","authenticated-orcid":false,"given":"Yi","family":"Liu","sequence":"first","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3850-3722","authenticated-orcid":false,"given":"Haowen","family":"Hou","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5388-9125","authenticated-orcid":false,"given":"Fei","family":"Ma","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4303-7386","authenticated-orcid":false,"given":"Shiguang","family":"Ni","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1006-7594","authenticated-orcid":false,"given":"Fei Richard","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref2","article-title":"QVHighlights: Detecting moments and highlights in videos via natural language queries","author":"Lei","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378477"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547943"},{"issue":"3","key":"ref7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11554-024-01454-4","article-title":"F2S-Net: Learning frame-to-segment prediction for online action detection","volume":"21","author":"Liu","year":"2024","journal-title":"J. Real-Time Image Process."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3117472"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"ref12","article-title":"Introducing chatgpt","year":"2022"},{"key":"ref13","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90 chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref14","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680724"},{"key":"ref16","article-title":"VideoChat: Chat-centric video understanding","author":"Li","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref18","article-title":"Valley: Video assistant with large language model enhanced ability","author":"Luo","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref21","article-title":"Generative technology for human emotion recognition: A scoping review","volume":"115","author":"Ma","year":"2024","journal-title":"Inf. Fusion"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref23","article-title":"Towards calibrated robust fine-tuning of vision-language models","author":"Oh","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01825"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref29","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6820"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/10777595.pdf?arnumber=10777595","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T06:34:00Z","timestamp":1735108440000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10777595\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3511426","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}