{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:37:00Z","timestamp":1763203020070,"version":"build-2065373602"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11208912","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval"],"prefix":"10.1109","author":[{"given":"Junyang","family":"Chen","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University,School of Computer Science and Engineering,Guangzhou,China"}]},{"given":"Hanjiang","family":"Lai","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,School of Computer Science and Engineering,Guangzhou,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28324"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref7","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00565"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01256"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_32"},{"key":"ref15","article-title":"Image2sentence based asymmetrical zero-shot composed image retrieval","author":"Du","year":"2024","journal-title":"ICLR"},{"key":"ref16","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inform. Process. Syst","volume":"33","author":"Brown"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref19","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref20","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"ICML.","author":"Chen","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00663"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11208912.pdf?arnumber=11208912","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:41:17Z","timestamp":1761889277000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11208912\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11208912","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}