{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:59:33Z","timestamp":1777888773900,"version":"3.51.4"},"reference-count":33,"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\/iccv51701.2025.01500","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16165-16174","source":"Crossref","is-referenced-by-count":0,"title":["Text2Outfit: Controllable Outfit Generation With Multimodal Language Models"],"prefix":"10.1109","author":[{"given":"Yuanhao","family":"Zhai","sequence":"first","affiliation":[{"name":"State University of New York at Buffalo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yen-Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minxu","family":"Peng","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Larry S.","family":"Davis","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashwin","family":"Chandramouli","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[{"name":"State University of New York at Buffalo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Doermann","sequence":"additional","affiliation":[{"name":"State University of New York at Buffalo"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"ref3","volume-title":"Introducing the next generation of claude","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tetc.2023.3268363"},{"issue":"3","key":"ref5","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-23052-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01290"},{"key":"ref8","article-title":"DreamLLM: Synergistic multimodal comprehension and creation","author":"Dong","year":"2024","journal-title":"In ICLR"},{"key":"ref9","first-page":"1078","article-title":"Learning fashion compatibility with bidirectional 1stms","author":"Han","year":"2017","journal-title":"In ACM MM"},{"key":"ref10","author":"Hu","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00788"},{"key":"ref12","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"In ICML","author":"Jia","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530104"},{"key":"ref14","article-title":"Generating images with multimodal language models","author":"Yu Koh","year":"2023","journal-title":"NeurIPS, 36"},{"key":"ref15","first-page":"17283","article-title":"Grounding language models to images for multimodal inputs and outputs","volume-title":"In ICML","author":"Koh","year":"2023"},{"key":"ref16","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified visionlanguage understanding and generation","volume-title":"In ICML","author":"Li","year":"2022"},{"key":"ref17","first-page":"19730","article-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"In ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00664"},{"key":"ref19","article-title":"Improving context understanding in multimodal large language models via multimodal composition learning","volume-title":"In Forty-first International Conference on Machine Learning","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00337"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"ref22","author":"Nussbaum","year":"2024","journal-title":"Nomic embed: Training a reproducible long context text embedder"},{"key":"ref23","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"In ICLR","author":"Podell","year":"2024"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In ICML","author":"Radford","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00359"},{"key":"ref26","first-page":"14398","article-title":"Generative multimodal models are incontext learners","author":"Sun","year":"2024","journal-title":"In CVPR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01047"},{"key":"ref28","author":"van den Oord","year":"2019","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_24"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.527"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.354"},{"key":"ref32","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","volume-title":"In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Zheng"}],"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\/11445402.pdf?arnumber=11445402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:55:49Z","timestamp":1777611349000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445402\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01500","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}