{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:07:05Z","timestamp":1761898025623,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687800","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["RISC: Boosting High-quality Referring Image Segmentation via Foundation Model CLIP"],"prefix":"10.1109","author":[{"given":"Zongyuan","family":"Jiang","sequence":"first","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering"}]},{"given":"Jiayu","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group,Platform of AI (PAI)"}]},{"given":"Chongyu","family":"Liu","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering"}]},{"given":"Ning","family":"Zhang","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering"}]},{"given":"Jun","family":"Huang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Platform of AI (PAI)"}]},{"given":"Xue","family":"Gao","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering"}]},{"given":"Lianwen","family":"Jin","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Electronic and Information Engineering"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00679"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00909"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref5","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"ICML","author":"Kim"},{"key":"ref6","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref9","first-page":"14729","article-title":"Coupalign: Coupling word-pixel with sentence-mask alignments for referring image segmentation","volume":"35","author":"Zhang","year":"2022","journal-title":"NIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"article-title":"Bloom: A 176b-parameter open-access multilingual language model","year":"2022","author":"Scao","key":"ref13"},{"issue":"240","key":"ref14","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"JMLR"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"article-title":"Yolov3: An incremental improvement","year":"2018","author":"Redmon","key":"ref20"},{"key":"ref21","first-page":"4424","article-title":"Bidirectional relationship inferring network for referring image segmentation","volume-title":"CVPR","author":"Hu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref29","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume":"34","author":"Li","year":"2021","journal-title":"NIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov","key":"ref34"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687800.pdf?arnumber=10687800","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:36:02Z","timestamp":1727764562000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687800\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687800","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}