{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:01:39Z","timestamp":1777568499084,"version":"3.51.4"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10445738","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"7895-7899","source":"Crossref","is-referenced-by-count":5,"title":["Visual Prompt Tuning for Weakly Supervised Phrase Grounding"],"prefix":"10.1109","author":[{"given":"Pengyue","family":"Lin","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence"}]},{"given":"Zhihan","family":"Yu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence"}]},{"given":"Mingcong","family":"Lu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence"}]},{"given":"Fangxiang","family":"Feng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence"}]},{"given":"Ruifan","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence"}]},{"given":"Xiaojie","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref2","first-page":"28222","article-title":"What is where by looking: Weakly-supervised open-world phrase-grounding without text inputs","volume-title":"NeurIPS","author":"Shaharabany"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00556"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_44"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00269"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.558"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/112"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1059-x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01276"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00182"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"ref14","first-page":"1","article-title":"Adapting clip for phrase localization without further training","author":"Li","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747841"},{"key":"ref17","first-page":"1","article-title":"Alpha-clip: A clip model focusing on wherever you want","author":"Sun","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref23","first-page":"1","article-title":"Fine-grained visual prompting","volume-title":"NeurIPS","author":"Yang"},{"key":"ref24","first-page":"2641","article-title":"Flickr30k entities: Collecting region-to-phrase correspondences for richer imageto-sentence models","volume-title":"ICCV","author":"Plummer"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.95"},{"key":"ref28","first-page":"13","article-title":"The iapr tc-12 benchmark: A new evaluation resource for visual information systems","volume-title":"International workshop ontoImage","volume":"2","author":"Grubinger"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859701"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3490585"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10445738.pdf?arnumber=10445738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:55:01Z","timestamp":1722574501000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445738\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445738","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}