{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:52:42Z","timestamp":1784299962151,"version":"3.55.0"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC3807600"],"award-info":[{"award-number":["2023YFC3807600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Personalized Health and Related Technologies (PHRT) of the ETH domain","award":["iDoc 2021-360"],"award-info":[{"award-number":["iDoc 2021-360"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3371348","type":"journal-article","created":{"date-parts":[[2024,3,5]],"date-time":"2024-03-05T19:24:10Z","timestamp":1709666650000},"page":"1782-1794","source":"Crossref","is-referenced-by-count":77,"title":["Toward Robust Referring Image Segmentation"],"prefix":"10.1109","volume":"33","author":[{"given":"Jianzong","family":"Wu","sequence":"first","affiliation":[{"name":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0550-8247","authenticated-orcid":false,"given":"Xiangtai","family":"Li","sequence":"additional","affiliation":[{"name":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xia","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4868-6526","authenticated-orcid":false,"given":"Henghui","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Information Technology and Electrical Engineering, ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8735-2516","authenticated-orcid":false,"given":"Yunhai","family":"Tong","sequence":"additional","affiliation":[{"name":"National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"The University of Sydney, Camperdown, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Benchmarking the robustness of instance segmentation models","author":"Altindis","year":"2021","journal-title":"arXiv:2109.01123"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00352"},{"key":"ref5","article-title":"Referring expression object segmentation with caption-aware consistency","author":"Chen","year":"2019","journal-title":"arXiv:1910.04748"},{"key":"ref6","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. NIPS","author":"Cheng"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217852"},{"key":"ref13","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref16","first-page":"1","article-title":"Generalisation in humans and deep neural networks","volume-title":"Proc. NIPS","volume":"31","author":"Geirhos"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref18","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019","journal-title":"arXiv:1903.12261"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.270"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00885"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00988"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-srw.22"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00501"},{"key":"ref31","article-title":"Transformer-based visual segmentation: A survey","author":"Li","year":"2023","journal-title":"arXiv:2304.09854"},{"key":"ref32","article-title":"Towards robust referring video object segmentation with cyclic relational consensus","author":"Li","year":"2022","journal-title":"arXiv:2207.01203"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_42"},{"key":"ref34","article-title":"PanopticPartFormer++: A unified and decoupled view for panoptic part segmentation","author":"Li","year":"2023","journal-title":"arXiv:2301.00954"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_45"},{"key":"ref36","article-title":"SFNet: Faster, accurate, and domain agnostic semantic segmentation via semantic flow","author":"Li","year":"2022","journal-title":"arXiv:2207.04415"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6805"},{"key":"ref39","article-title":"MaIL: A unified mask-image-language trimodal network for referring image segmentation","author":"Li","year":"2021","journal-title":"arXiv:2111.10747"},{"key":"ref40","article-title":"Local\u2013global context aware transformer for language-guided video segmentation","author":"Liang","year":"2022","journal-title":"arXiv:2203.09773"},{"key":"ref41","article-title":"ClawCraneNet: Leveraging object-level relation for text-based video segmentation","author":"Liang","year":"2021","journal-title":"arXiv:2103.10702"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref44","first-page":"1","article-title":"Instance-specific feature propagation for referring segmentation","volume-title":"Proc. TMM","author":"Liu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079993"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref49","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414006"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00412"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref55","first-page":"1","article-title":"Exploring generalization in deep learning","volume-title":"Proc. NIPS","volume":"30","author":"Neyshabur"},{"key":"ref56","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref57","first-page":"8093","article-title":"Overfitting in adversarially robust deep learning","volume-title":"Proc. ICML","author":"Rice"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00747"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1072-8"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref61","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. ICML","author":"Touvron"},{"key":"ref62","article-title":"Examining the impact of blur on recognition by convolutional networks","author":"Vasiljevic","year":"2016","journal-title":"arXiv:1611.05760"},{"key":"ref63","article-title":"CRIS: CLIP-driven referring image segmentation","author":"Wang","year":"2021","journal-title":"arXiv:2111.15174"},{"key":"ref64","first-page":"1","article-title":"STEP: Segmenting and tracking every pixel","volume-title":"Proc. NIPS","author":"Weber"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02005"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3361862"},{"key":"ref68","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. NIPS","author":"Xie"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_31"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00900"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref76","first-page":"1","article-title":"Rethinking mobile block for efficient neural models","volume-title":"Proc. ICCV","author":"Zhang"},{"key":"ref77","article-title":"EATFormer: Improving vision transformer inspired by evolutionary algorithm","author":"Zhang","year":"2022","journal-title":"arXiv:2206.09325"},{"key":"ref78","first-page":"26674","article-title":"Analogous to evolutionary algorithm: Designing a unified sequence model","volume-title":"Proc. NIPS","author":"Zhang"},{"key":"ref79","first-page":"27378","article-title":"Understanding the robustness in vision transformers","volume-title":"Proc. ICML","author":"Zhou"},{"key":"ref80","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/10346232\/10460426.pdf?arnumber=10460426","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T20:29:51Z","timestamp":1710793791000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10460426\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3371348","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}