{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T23:13:00Z","timestamp":1780441980596,"version":"3.54.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012246","name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10688134","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-10","source":"Crossref","is-referenced-by-count":4,"title":["LAIP: Learning Local Alignment from Image-Phrase Modeling for Text-based Person Search"],"prefix":"10.1109","author":[{"given":"Yu","family":"Wu","sequence":"first","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Suzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiguang","family":"Wang","sequence":"additional","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Suzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengxia","family":"Wu","sequence":"additional","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Suzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Cao","sequence":"additional","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Suzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Suzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1a","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref2a","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref3a","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref4a","article-title":"Text-based person search with limited data","author":"Han","year":"2021"},{"key":"ref5a","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref6a","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746846"},{"key":"ref7a","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413864"},{"key":"ref8a","article-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021"},{"key":"ref9a","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2023.3327924"},{"key":"ref10a","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00476"},{"key":"ref11a","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3337653"},{"key":"ref12a","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3310118"},{"key":"ref13a","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"ref14a","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref15a","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00295"},{"key":"ref16a","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612244"},{"key":"ref17a","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18a","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref19a","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref20a","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref21a","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612285"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.081"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"ref5","article-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00295"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref8","first-page":"3873","article-title":"Portalis: using competitive online interactions to support aid initiatives for the homeless","volume-title":"CHI \u201908 extended abstracts on Human factors in computing systems","author":"Li"},{"key":"ref9","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746846"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/1118108.1118117"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547753"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01026"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548057"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2023.3327924"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10688134.pdf?arnumber=10688134","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:23:50Z","timestamp":1727763830000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10688134\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10688134","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}