{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T21:28:01Z","timestamp":1769030881219,"version":"3.49.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001602","name":"Science Foundation Ireland","doi-asserted-by":"publisher","award":["SFI\/13\/RC\/2106_P2,18\/CRT\/6223"],"award-info":[{"award-number":["SFI\/13\/RC\/2106_P2,18\/CRT\/6223"]}],"id":[{"id":"10.13039\/501100001602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/cbmi66578.2025.11339315","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:38:56Z","timestamp":1768941536000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Vision Projector: Improving Zero-Shot Composed Image Retrieval at Inference"],"prefix":"10.1109","author":[{"given":"Hoang-Bao","family":"Le","sequence":"first","affiliation":[{"name":"Dublin City University,ADAPT Centre,Dublin,Ireland"}]},{"given":"Allie","family":"Tran","sequence":"additional","affiliation":[{"name":"Dublin City University,ADAPT Centre,Dublin,Ireland"}]},{"given":"Binh T.","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Ho Chi Minh University of Science, Vietnam National University,Ho Chi Minh City,Vietnam"}]},{"given":"Liting","family":"Zhou","sequence":"additional","affiliation":[{"name":"Dublin City University,ADAPT Centre,Dublin,Ireland"}]},{"given":"Cathal","family":"Gurrin","sequence":"additional","affiliation":[{"name":"Dublin City University,ADAPT Centre,Dublin,Ireland"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref2","first-page":"21","article-title":"MagicLens: Self-supervised image retrieval with open-ended instructions","volume-title":"Proceedings of the 41st International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"235","author":"Zhang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"issue":"4","key":"ref4","first-page":"2991","article-title":"Data roaming and quality assessment for composed image retrieval","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Levy"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"2556","DOI":"10.18653\/v1\/P18-1238","article-title":"Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Sharma","year":"2018"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref7","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref8","article-title":"Zero-shot composed text-image retrieval","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657831"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01256"},{"key":"ref11","article-title":"The fashion iq dataset: Retrieving images by combining side information and relative natural language feedback","author":"Wu","year":"2021","journal-title":"CVPR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.163"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3593539"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657740"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref19","volume-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref20","article-title":"Dense connector for mllms","author":"Yao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01311"},{"key":"ref22","volume-title":"Reducing task discrepancy of text encoders for zero-shot composed image retrieval","author":"Byun","year":"2024"},{"key":"ref23","volume-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022"},{"key":"ref24","volume-title":"Pretrain like your inference: Masked tuning improves zero-shot composed image retrieval","author":"Chen","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00252"},{"key":"ref26","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume":"35","author":"Liang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","article-title":"Composed image retrieval with text feedback via multi-grained uncertainty regularization","volume-title":"International Conference on Learning Representations (ICLR)","author":"Chen","year":"2024"},{"key":"ref28","article-title":"MLLM-12W: Harnessing multimodal large language model for zero-shot composed image retrieval","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics","author":"Bao"},{"key":"ref29","first-page":"9204","article-title":"Pay attention to mlps","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref30","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.findings-emnlp.49","volume-title":"Approximating two-layer feedforward networks for efficient transformers","author":"Csord\u00e1s","year":"2023"},{"key":"ref33","volume-title":"Sigmoid gating is more sample efficient than softmax gating in mixture of experts","author":"Nguyen","year":"2024"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1644","volume-title":"A corpus for reasoning about natural language grounded in photographs","author":"Suhr","year":"2019"},{"key":"ref35","volume-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2015"},{"key":"ref36","volume-title":"Flax: A neural network library and ecosystem for JAX","author":"Heek","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02070"},{"key":"ref38","volume-title":"Vision-by-language for training-free compositional image retrieval","author":"Karthik","year":"2024"}],"event":{"name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","location":"Dublin, Ireland","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 International Conference on Content-Based Multimedia Indexing (CBMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11339229\/11339242\/11339315.pdf?arnumber=11339315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:11:31Z","timestamp":1768979491000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339315\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/cbmi66578.2025.11339315","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}