{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:11:59Z","timestamp":1761894719027,"version":"build-2065373602"},"reference-count":42,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209074","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":0,"title":["TalkFashion: Intelligent Virtual Try-On Assistant Based on Multimodal Large Language Model"],"prefix":"10.1109","author":[{"given":"Yujie","family":"Hu","sequence":"first","affiliation":[{"name":"Peking University,School of Electronic and Computer Engineering,China"}]},{"given":"Xuanyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University,School of Electronic and Computer Engineering,China"}]},{"given":"Weiqi","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University,School of Electronic and Computer Engineering,China"}]},{"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University,School of Electronic and Computer Engineering,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Street tryon: Learning in-the-wild virtual try-on from unpaired person images","author":"Cui","year":"2024","journal-title":"CVPR"},{"article-title":"Catvton: Concatenation is all you need for virtual try-on with diffusion models","year":"2024","author":"Chong","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00134"},{"article-title":"Mmtryon: Multi-modal multi-reference control for high-quality fashion generation","year":"2024","author":"Zhang","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680836"},{"article-title":"Vivid: Video virtual try-on using diffusion models","year":"2024","author":"Fang","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00787"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00787"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02255"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref14","article-title":"Dragondiffusion: Enabling drag-style manipulation on diffusion models","author":"Mou","year":"2024","journal-title":"ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00811"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00781"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.32973"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_13"},{"key":"ref19","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"NeurIPS"},{"volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","year":"2023","author":"Chiang","key":"ref20"},{"article-title":"Qwen2 technical report","year":"2024","author":"Yang","key":"ref21"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01137"},{"article-title":"Visual chatgpt: Talking, drawing and editing with visual foundation models","year":"2023","author":"Wu","key":"ref24"},{"key":"ref25","article-title":"Gpt4tools: Teaching large language model to use tools via self-instruction","author":"Yang","year":"2024","journal-title":"NeurIPS"},{"key":"ref26","article-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face","author":"Shen","year":"2024","journal-title":"NeurIPS"},{"article-title":"Gorilla: Large language model connected with massive apis","year":"2023","author":"Patil","key":"ref27"},{"key":"ref28","article-title":"React: Synergizing reasoning and acting in language models","author":"Yao","year":"2023","journal-title":"ICLR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3048039"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref32","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","year":"2024","author":"Wang","key":"ref33"},{"article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","year":"2023","author":"Podell","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref37","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref38","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"article-title":"Ultraedit: Instruction-based fine-grained image editing at scale","year":"2024","author":"Zhao","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01220"}],"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\/11209074.pdf?arnumber=11209074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:34:34Z","timestamp":1761888874000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209074\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209074","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}