{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:30Z","timestamp":1777865310941,"version":"3.51.4"},"reference-count":62,"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"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01,1R01AI190103-01"],"award-info":[{"award-number":["R01,1R01AI190103-01"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02063","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22221-22231","source":"Crossref","is-referenced-by-count":0,"title":["Zero-Shot Composed Image Retrieval via Dual-Stream Instruction-Aware Distillation"],"prefix":"10.1109","author":[{"given":"Wenliang","family":"Zhong","sequence":"first","affiliation":[{"name":"The University of Texas at Arlington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rob","family":"Barton","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weizhi","family":"An","sequence":"additional","affiliation":[{"name":"The University of Texas at Arlington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Jiang","sequence":"additional","affiliation":[{"name":"The University of Texas at Arlington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hehuan","family":"Ma","sequence":"additional","affiliation":[{"name":"The University of Texas at Arlington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhi","family":"Guo","sequence":"additional","affiliation":[{"name":"The University of Texas at Arlington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhishek","family":"Dan","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shioulin","family":"Sam","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karim","family":"Bouyarmane","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junzhou","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Texas at Arlington"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3593539"},{"key":"ref3","article-title":"Anthropic","journal-title":"The claude 3 model family: Opus, sonnet, haiku"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00127"},{"key":"ref6","article-title":"Language models are few-shot learners","author":"Brown","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Reducing task discrepancy of text encoders for zero-shot composed image retrieval","author":"Byun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16865"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00489"},{"key":"ref10","article-title":"XTuner Contributors","volume-title":"Xtuner: A toolkit for efficiently fine-tuning llm","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01256"},{"key":"ref13","article-title":"Compodiff: Versatile composed image retrieval with latent diffusion","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"ref16","author":"Hu","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_14"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01590"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.181"},{"key":"ref21","article-title":"Vision-by-language for trainingfree compositional image retrieval","author":"Karthik","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","author":"Koh","journal-title":"Grounding language models to images for multimodal inputs and outputs"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28081"},{"key":"ref25","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","year":"2022"},{"key":"ref26","article-title":"Blip-2 : Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning, pages 1973019742. PMLR","author":"Li","year":"2023"},{"key":"ref27","article-title":"Improving context understanding in multimodal large language models via multimodal composition learning","volume-title":"Forty-first International Conference on Machine Learning. 2, 5","author":"Li"},{"key":"ref28","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref29","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems, 36"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17610"},{"key":"ref34","article-title":"Model compression via distillation and quantization","author":"Polino","year":"2018","journal-title":"arXiv preprint"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"ref37","first-page":"2556","article-title":"Association for Computational Linguistics","volume-title":"Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning","volume":"1","author":"Sharma","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-industry.50"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02545"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28324"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00663"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28334"},{"key":"ref43","article-title":"Can chatgpt defend its belief in truth? evaluating 11 m reasoning via debate","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","author":"Wang","year":"2018","journal-title":"Dataset distillation. arXiv preprint arXiv:1811.10959"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_20"},{"key":"ref46","author":"Wang","year":"2022","journal-title":"Self-instruct: Aligning language models with self-generated instructions. arXiv preprint arXiv:2212.10560"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73021-4_23"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref49","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":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_40"},{"key":"ref51","article-title":"A survey on knowledge distillation of large language models","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01510"},{"key":"ref53","article-title":"Llm lies: Hallucinations are not bugs, but features as adversarial examples","author":"Yao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_15"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref56","article-title":"Magiclens: Self-supervised image retrieval with open-ended instructions","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"A survey of large language models","author":"Xin Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Compositional image retrieval via instruction-aware contrastive learning","author":"Zhong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Tinyllava: A framework of small-scale large multimodal models","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Instruction-following evaluation for large language models","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671640"}],"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\/11445562.pdf?arnumber=11445562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:14:59Z","timestamp":1777529699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445562\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02063","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}