{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:23:04Z","timestamp":1774419784009,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888602","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Text-Guided Few-Shot Semantic Segmentation with Training-Free Multimodal Feature Matching"],"prefix":"10.1109","author":[{"given":"Guillaume","family":"Buthmann","sequence":"first","affiliation":[{"name":"IBM Research,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoya","family":"Sakai","sequence":"additional","affiliation":[{"name":"IBM Research,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoxiang","family":"Qiu","sequence":"additional","affiliation":[{"name":"IBM Research,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takayuki","family":"Katsuki","sequence":"additional","affiliation":[{"name":"IBM Research,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daiki","family":"Kimura","sequence":"additional","affiliation":[{"name":"IBM Research,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3151\/jact.18.493"},{"key":"ref2","article-title":"Semantic segmentation for autonomous driving: Model evaluation, dataset generation, perspective comparison, and real-time capability","author":"Cakir","year":"2022"},{"key":"ref3","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref4","article-title":"Matcher: Segment anything with one shot using all-purpose feature matching","volume-title":"International Conference on Learning Representations","author":"Liu"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00686"},{"key":"ref6","article-title":"MSANet: Multi-similarity and attention guidance for boosting few-shot segmentation","author":"Iqbal","year":"2022"},{"key":"ref7","article-title":"Zero-shot semantic segmentation","volume":"32","author":"Bucher","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Language-driven semantic segmentation","volume-title":"International Conference on Learning Representations","author":"Li"},{"key":"ref9","first-page":"32 340","article-title":"Zson: Zero-shot object-goal navigation using multimodal goal embeddings","volume":"35","author":"Majumdar","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"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","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning","author":"Jia"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_26"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/e25091353"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/193"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447456"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/1000"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.621"},{"key":"ref22","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_20"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.167"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00071"},{"key":"ref29","article-title":"What a MESS: Multi-domain evaluation of zero-shot semantic segmentation","volume":"36","author":"Blumenstiel","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00394"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888602.pdf?arnumber=10888602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:40Z","timestamp":1774416280000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888602\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888602","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}