{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T23:49:24Z","timestamp":1779320964756,"version":"3.51.4"},"reference-count":78,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01854","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19936-19946","source":"Crossref","is-referenced-by-count":1,"title":["DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation Through Loopback Synergy"],"prefix":"10.1109","author":[{"given":"Ming","family":"Dai","sequence":"first","affiliation":[{"name":"Southeast University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxuan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Southeast University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiang-jiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu VIS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sen","family":"Yang","sequence":"additional","affiliation":[{"name":"Baidu VIS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxiao","family":"Cai","sequence":"additional","affiliation":[{"name":"Standford University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanpeng","family":"Sun","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wankou","family":"Yang","sequence":"additional","affiliation":[{"name":"Southeast University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"VLMo: Unified visionlanguage pre-training with mixture-of-modality-experts","author":"Bao","year":"2022","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00860"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00215"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_19"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27896"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3867"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32265"},{"key":"ref13","author":"De Brabandere","year":"2017","journal-title":"Semantic instance segmentation with a discriminative loss function"},{"key":"ref14","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.02767"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00073"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"issue":"2","key":"ref22","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Edward","year":"2022","journal-title":"ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00376"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.481"},{"key":"ref26","first-page":"12976","article-title":"Seeing out of the box: End-toend pre-training for vision-language representation learning","author":"Huang","year":"2021","journal-title":"CVPR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref28","first-page":"49044916","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref30","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","author":"Kim","year":"2021","journal-title":"ICML"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref32","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"Lan","year":"2020","journal-title":"ICLR"},{"key":"ref33","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref35","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref36","article-title":"Referring transformer: A onestep approach to multi-task visual grounding","volume":"34","author":"Li","year":"2021","journal-title":"NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref38","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","author":"Li","year":"2022","journal-title":"ICLR"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3163578"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3277791"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.378"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612117"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref51","first-page":"792","article-title":"Modeling context between objects for referring expression understanding","author":"Varun","year":"2016","journal-title":"ECCV"},{"key":"ref52","article-title":"Associative embedding: End-to-end learning for joint detection and grouping","author":"Newell","year":"2017","journal-title":"NeurIPS"},{"key":"ref53","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00395"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01045"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"ref60","author":"Wang","year":"2024","journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32867"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3371348"},{"key":"ref64","author":"Wu","year":"2024","journal-title":"Deepseek-vl2: Mixture-ofexperts vision-language models for advanced multimodal understanding"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref66","article-title":"Oneref: Unified one-tower expression grounding and segmentation with mask referring modeling","author":"Xiao","year":"2024","journal-title":"NeurIPS"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_7"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref72","author":"Yu","year":"2024","journal-title":"A simple baseline with single-encoder for referring image segmentation"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20227"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2614"},{"key":"ref75","first-page":"14729","article-title":"Coupalign: Coupling word-pixel with sentencemask alignments for referring image segmentation","volume":"35","author":"Zhang","year":"2022","journal-title":"NeurIPS"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33194"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445497.pdf?arnumber=11445497","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:56:08Z","timestamp":1777611368000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445497\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01854","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}