{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T04:37:36Z","timestamp":1774413456835,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3277791","type":"journal-article","created":{"date-parts":[[2023,5,23]],"date-time":"2023-05-23T18:48:46Z","timestamp":1684867726000},"page":"3054-3065","source":"Crossref","is-referenced-by-count":58,"title":["Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentation"],"prefix":"10.1109","volume":"32","author":[{"given":"Chang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering (EEE), Nanyang Technological University, Jurong West, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4868-6526","authenticated-orcid":false,"given":"Henghui","family":"Ding","sequence":"additional","affiliation":[{"name":"Computer Vision Laboratory (CVL), ETH Zürich, Zürich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2288-5079","authenticated-orcid":false,"given":"Yulun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Computer Vision Laboratory (CVL), ETH Zürich, Zürich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9104-2315","authenticated-orcid":false,"given":"Xudong","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering (EEE), Nanyang Technological University, Jurong West, Singapore"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414006"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878975"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2962685"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"},{"key":"ref55","first-page":"4761","article-title":"Cross-modal progressive comprehension for referring segmentation","volume":"44","author":"liu","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00254"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref51","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217852"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref48","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref42","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"xie","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref44","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","author":"kim","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref43","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume":"34","author":"cheng","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref40","first-page":"1","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref35","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Conf NAACL-HLT"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref36","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"2019","journal-title":"arXiv 1907 11692"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.520"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.122"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref2","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"ref20","first-page":"1","article-title":"Referring expression object segmentation with caption-aware consistency","author":"chen","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.333"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10132374.pdf?arnumber=10132374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T18:28:11Z","timestamp":1687199291000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10132374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3277791","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}