{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T11:42:09Z","timestamp":1793965329037,"version":"4.8.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02254","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"34319-24329","source":"Crossref","is-referenced-by-count":4,"title":["Hierarchy-Aware Pseudo Word Learning with Text Adaptation for Zero-Shot Composed Image Retrieval"],"prefix":"10.1109","author":[{"given":"Zhe","family":"Li","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheren","family":"Fu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Suzhou Institute for Advanced Research, USTC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref5","article-title":"Composed image retrieval with text feedback via multi-grained uncertainty regularization","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27885"},{"key":"ref7","article-title":"Artemis: Attention-based retrieval with textexplicit matching and implicit similarity","volume-title":"International Conference on Learning Representations","author":"Delmas"},{"key":"ref8","article-title":"Modality-agnostic attention fusion for visual search with text feedback","author":"Dodds","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Image2sentence based asymmetrical zero-shot composed image retrieval","volume-title":"The Twelfth International Conference on Learning Representations","author":"Du"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01455"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02485"},{"key":"ref12","article-title":"Compodiff: Versatile composed image retrieval with latent diffusion","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01256"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01590"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/100216.100262"},{"key":"ref17","article-title":"Vision-by-language for training-free compositional image retrieval","volume-title":"The Twelfth International Conference on Learning Representations","author":"Karthik"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref20","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on machine learning","author":"Li"},{"key":"ref21","article-title":"Improving context understanding in multimodal large language models via multimodal composition learning","volume-title":"Forty-first International Conference on Machine Learning","author":"Li"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358411"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369656"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730074"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657831"},{"key":"ref26","article-title":"Zero-shot composed text-image retrieval","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00213"},{"key":"ref28","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","author":"Maddison","year":"2016","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/p14-5010"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref33","article-title":"Rtic: Residual learning for text and image composition using graph convolutional network","author":"Shin","year":"2021","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Improved deep metric learning with multiclass n-pair loss objective","volume":"29","author":"Sohn","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02545"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28324"},{"key":"ref37","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462967"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611817"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657727"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref44","article-title":"Sentence-level prompts benefit composed image retrieval","volume-title":"The Twelfth International Conference on Learning Representations","author":"Xu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3299791"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28479"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657740"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141603"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref50","article-title":"Composed multi-modal retrieval: A survey of approaches and applications","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02327"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444159.pdf?arnumber=11444159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:12:42Z","timestamp":1777612362000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444159\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02254","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}