{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:51:07Z","timestamp":1777657867145,"version":"3.51.4"},"reference-count":97,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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","award":["62206153"],"award-info":[{"award-number":["62206153"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62321005"],"award-info":[{"award-number":["62321005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62321005"],"award-info":[{"award-number":["62321005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201484"],"award-info":[{"award-number":["62201484"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Artificial Intelligence Laboratory"},{"name":"National Key R&D Program of China","award":["2022ZD0160201"],"award-info":[{"award-number":["2022ZD0160201"]}]},{"name":"HKU Startup Fund, in part by the HKU Seed Fund for Basic Research","award":["EP\/W002981\/1"],"award-info":[{"award-number":["EP\/W002981\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tpami.2024.3468640","type":"journal-article","created":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T19:23:10Z","timestamp":1727292190000},"page":"5238-5255","source":"Crossref","is-referenced-by-count":11,"title":["Language-Aware Vision Transformer for Referring Segmentation"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4376-0109","authenticated-orcid":false,"given":"Zhao","family":"Yang","sequence":"first","affiliation":[{"name":"Shanghai AI Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6877-5353","authenticated-orcid":false,"given":"Jiaqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8269-2689","authenticated-orcid":false,"given":"Xubing","family":"Ye","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1534-4549","authenticated-orcid":false,"given":"Yansong","family":"Tang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6820-2325","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8277-2706","authenticated-orcid":false,"given":"Hengshuang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Hong Kong, Pok Fu Lam, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0259-5732","authenticated-orcid":false,"given":"Philip H. S.","family":"Torr","sequence":"additional","affiliation":[{"name":"Department of Engineering Science, University of Oxford, Oxford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2682628"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00404"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00996"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00147"},{"key":"ref23","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13413-x"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref37","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref38","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217852"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25428"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298839"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6895"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079993"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00417"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00491"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00091"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01418"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284979"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01234"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref64","first-page":"5754","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref65","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref66","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref68","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref74","first-page":"1849","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414006"},{"key":"ref78","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2016"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref82","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref85","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref87","first-page":"388","article-title":"Boundary loss for remote sensing imagery semantic segmentation","volume-title":"Proc. 16th Int. Symp. Neural Netw.","author":"Alexey"},{"key":"ref88","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref91","article-title":"The 2017 DAVIS challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054384"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_20"},{"key":"ref94","article-title":"Hierarchical interaction network for video object segmentation from referring expressions","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Yang"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref97","article-title":"GPT-4 technical report","year":"2023"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11026037\/10694805.pdf?arnumber=10694805","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T04:14:41Z","timestamp":1749183281000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10694805\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":97,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3468640","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}