{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T22:20:35Z","timestamp":1775082035644,"version":"3.50.1"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"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. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1109\/tpami.2022.3217852","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T00:56:53Z","timestamp":1667523413000},"page":"7900-7916","source":"Crossref","is-referenced-by-count":126,"title":["VLT: Vision-Language Transformer and Query Generation for Referring Segmentation"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4868-6526","authenticated-orcid":false,"given":"Henghui","family":"Ding","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore"}]},{"given":"Suchen","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore"}]},{"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, Nanyang Technological University (NTU), Singapore"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref12","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00147"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref58","first-page":"17 864","article-title":"Per-pixel classification is not all you need for semantic segmentation","author":"cheng","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref54","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","author":"chen","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref51","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"huang","year":"2020"},{"key":"ref50","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"ramesh","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref46","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","author":"xie","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref48","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01322"},{"key":"ref42","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref44","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Representation"},{"key":"ref43","article-title":"Dynamic evaluation of transformer language models","author":"krause","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"ref9","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref4","first-page":"630","article-title":"Dynamic multimodal instance segmentation guided by natural language queries","author":"margffoy-tuay","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref79","article-title":"The 2017 davis challenge on video object segmentation","author":"pont-tuset","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref78","first-page":"123","article-title":"Video object segmentation with language referring expressions","author":"khoreva","year":"2018","journal-title":"Proc Asi Conf Comput Vis"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref31","article-title":"Comprehensive multi-modal interactions for referring image segmentation","author":"jain","year":"2021"},{"key":"ref75","article-title":"Progressive multimodal interaction network for referring video object segmentation","author":"ding","year":"2021","journal-title":"Proc 3rd Large-Scale Video Object Segmentation Challenge"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref33","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":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref76","article-title":"Rethinking cross-modal interaction from a top-down perspective for referring video object segmentation","author":"liang","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_25"},{"key":"ref1","first-page":"108","article-title":"Segmentation from natural language expressions","author":"hu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref39","article-title":"Real-time referring expression comprehension by single-stage grounding network","author":"chen","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414006"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"ref69","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref63","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref21","article-title":"Referring expression object segmentation with caption-aware consistency","author":"chen","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref28","article-title":"MaIL: A unified mask-image-language trimodal network for referring image segmentation","author":"li","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref60","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00689"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09932025.pdf?arnumber=9932025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:36:54Z","timestamp":1685381814000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9932025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":82,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3217852","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":[[2023,6,1]]}}}