{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T12:45:09Z","timestamp":1768394709413,"version":"3.49.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,21]]},"DOI":"10.1109\/mmsp64401.2025.11324228","type":"proceedings-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T20:55:15Z","timestamp":1768337715000},"page":"12-17","source":"Crossref","is-referenced-by-count":0,"title":["DFR: A Decompose-Fuse-Reconstruct Framework for Multi-Modal Few-Shot Segmentation"],"prefix":"10.1109","author":[{"given":"Shuai","family":"Chen","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"}]},{"given":"Fanman","family":"Meng","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"}]},{"given":"Xiwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"}]},{"given":"Haoran","family":"Wei","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"}]},{"given":"Chenhao","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"}]},{"given":"Qingbo","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"}]},{"given":"Hongliang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP55362.2022.9949177"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013717"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00686"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02228"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00694"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27834"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28094"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647485"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref14","article-title":"Languagebind: Extending video-language pretraining to n-modality by language-based semantic alignment","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Zhu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00929"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02224"},{"key":"ref17","article-title":"Matcher: Segment anything with one shot using all-purpose feature matching","volume-title":"The Twelfth International Conference on Learning Representations","author":"Liu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32688"},{"key":"ref19","first-page":"21 450","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Liu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.167"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28355"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3193587"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01886-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref26","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28378"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_22"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02261-x"},{"key":"ref30","article-title":"Avesformer: Efficient transformer design for real-time audio-visual segmentation","author":"Wang","year":"2024"}],"event":{"name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","location":"Beijing, China","start":{"date-parts":[[2025,9,21]]},"end":{"date-parts":[[2025,9,23]]}},"container-title":["2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11324077\/11324018\/11324228.pdf?arnumber=11324228","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T07:51:25Z","timestamp":1768377085000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11324228\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,21]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/mmsp64401.2025.11324228","relation":{},"subject":[],"published":{"date-parts":[[2025,9,21]]}}}