{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:07:13Z","timestamp":1781586433491,"version":"3.54.5"},"reference-count":27,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209301","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":1,"title":["Visual Semantic Description Generation with MLLMs for Image-Text Matching"],"prefix":"10.1109","author":[{"given":"Junyu","family":"Chen","sequence":"first","affiliation":[{"name":"Chongqing Normal University,Chongqing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihua","family":"Gao","sequence":"additional","affiliation":[{"name":"Chongqing Normal University,Chongqing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyong","family":"Li","sequence":"additional","affiliation":[{"name":"Chongqing Normal University,Chongqing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume-title":"NeurIPS","volume":"28","author":"Ren"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00260"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01361"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"ref10","article-title":"Improving clip training with language rewrites","volume-title":"NeurIPS","volume":"36","author":"Fan"},{"key":"ref11","article-title":"Improving multimodal datasets with image captioning","volume-title":"NeurIPS","volume":"36","author":"Nguyen"},{"key":"ref12","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li"},{"key":"ref13","article-title":"Mllms-augmented visual-language representation learning","author":"Liu","year":"2023"},{"key":"ref14","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657878"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358411"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"ref20","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"NeurIPS","volume":"26","author":"Cuturi"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref22","article-title":"N24news: A new dataset for multimodal news classification","author":"Wang","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3078451"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref25","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"NeurIPS","volume":"34","author":"Li"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3163706"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3318227"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"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\/11209301.pdf?arnumber=11209301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:56:36Z","timestamp":1761890196000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209301\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209301","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}