{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:04:27Z","timestamp":1772906667003,"version":"3.50.1"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1109\/lsp.2023.3340103","type":"journal-article","created":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T20:08:03Z","timestamp":1702584483000},"page":"521-525","source":"Crossref","is-referenced-by-count":11,"title":["GPTSee: Enhancing Moment Retrieval and Highlight Detection via Description-Based Similarity Features"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8122-7259","authenticated-orcid":false,"given":"Yunzhuo","family":"Sun","sequence":"first","affiliation":[{"name":"School of Physics and Electronics, Hubei Normal University, Huangshi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3738-789X","authenticated-orcid":false,"given":"Yifang","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zien","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukun","family":"Shu","sequence":"additional","affiliation":[{"name":"School of Physics and Electronics, Hubei Normal University, Huangshi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9966-3765","authenticated-orcid":false,"given":"Sidan","family":"Du","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1984","article-title":"ExCL: Extractive clip localization using natural language descriptions","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Ghosh","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00787"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"ref5","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref6","article-title":"Introducing ChatGPT"},{"key":"ref7","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref8","article-title":"Multimodal-GPT: A vision and language model for dialogue with humans","author":"Gong","year":"2023"},{"key":"ref9","article-title":"Videochat: Chat-centric video understanding","author":"Li","year":"2023"},{"key":"ref10","article-title":"Video-ChatGPT: Towards detailed video understanding via large vision and language models","author":"Maaz","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3258628"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref13","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Lei","year":"2021"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"ref17","first-page":"10386","article-title":"Deep supervised cross-modal retrieval","volume-title":"Proc. IEEE\/CVF Conf. Computer Vis. Pattern Recognit.","author":"Zhen","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref19","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3029181"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.4018\/IJSWIS.332768"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639346"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref25","article-title":"MH-DETR: Video moment and highlight detection with cross-modal transformer","author":"Xu","year":"2023"},{"key":"ref26","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref27","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref29","article-title":"Temporal localization of moments in video collections with natural language","author":"Escorcia","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/10380231\/10360488.pdf?arnumber=10360488","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T09:39:59Z","timestamp":1707817199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10360488\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/lsp.2023.3340103","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}