{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:30:57Z","timestamp":1761895857136,"version":"build-2065373602"},"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\/icme59968.2025.11210107","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":["MPT-CLIP: Multi-modal Patch-level Prompt Alignment in CLIP for Zero-shot Semantic Segmentation"],"prefix":"10.1109","author":[{"given":"Boliang","family":"Hao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology Zhejiang Sci-Tech University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangyu","family":"Wu","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong-Liverpool University,Department of Intelligent Science,Suzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Big Data Engineering NingboTech University,Ningbo,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bailing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Computer Science NingboTech University,Ningbo,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00264"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref3","article-title":"Zero-shot semantic segmentation","volume":"32","author":"Bucher","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref6","first-page":"2","article-title":"A simple baseline for zero-shot semantic segmentation with pre-trained vision-language model","volume":"3","author":"Xu","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_12"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref12","first-page":"547","article-title":"A simple zero-shot prompt weighting technique to improve prompt ensembling in text-image models","volume-title":"International Conference on Machine Learning","author":"Allingham"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"article-title":"Unified vision and language prompt learning","year":"2022","author":"Zang","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref16","first-page":"3515","article-title":"Sinkformers: Transformers with doubly stochastic attention","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Sander"},{"article-title":"Language-driven semantic segmentation","year":"2022","author":"Li","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2615921"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00452"},{"key":"ref20","first-page":"1542","article-title":"Graph optimal transport for cross-domain alignment","volume-title":"International Conference on Machine Learning","author":"Chen"},{"article-title":"Prompt learning with optimal transport for vision-language models","year":"2022","author":"Chen","key":"ref21"},{"key":"ref22","article-title":"Tuning multi-mode token-level prompt alignment across modalities","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","first-page":"2292","article-title":"Lightspeed computation of optimal transport","volume":"26","author":"M Sinkhorn Distances","year":"2013","journal-title":"Advances in neural information processing systems"},{"article-title":"Learning prototype-oriented set representations for meta-learning","year":"2021","author":"Guo","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00845"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"article-title":"MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark","year":"2020","author":"Contributors","key":"ref27"}],"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\/11210107.pdf?arnumber=11210107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:59:56Z","timestamp":1761890396000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210107\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210107","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}