{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:28:18Z","timestamp":1774420098344,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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"}]},{"DOI":"10.13039\/501100004763","name":"Natural Science Foundation of Inner Mongolia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004763","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888578","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["When CLIP Meets PHOC: A Dual-Branch Network for Historical Document Image Retrieval"],"prefix":"10.1109","author":[{"given":"Jing","family":"Zhang","sequence":"first","affiliation":[{"name":"Inner Mongolia University,School of Computer Science,Hohhot,China"}]},{"given":"Hongxi","family":"Wei","sequence":"additional","affiliation":[{"name":"Inner Mongolia University,School of Computer Science,Hohhot,China"}]},{"given":"Qing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Inner Mongolia University,School of Computer Science,Hohhot,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63820-7_1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446514"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39479-9_32"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-013-0203-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333738"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CISP-BMEI.2016.7852739"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC.2017.7978797"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46681-1_52"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019403"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-77383-4_60"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545573"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2019.00309"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI50040.2020.00071"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2339814"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR.2016.0060"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.01.019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.11.017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-022-00423-6"},{"key":"ref19","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00271"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01834"},{"key":"ref22","article-title":"Fine-grained visual prompting","volume":"36","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106390"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref25","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref26","article-title":"Deep Learning with PyTorch Lightning: Swiftly Build High-performance Artificial Intelligence (AI) Models Using Python","author":"Sawarkar","year":"2022","journal-title":"Packt Publishing Ltd"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888578.pdf?arnumber=10888578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:23Z","timestamp":1774416383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888578\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888578","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}