{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:26:30Z","timestamp":1783610790015,"version":"3.55.0"},"reference-count":79,"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. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tpami.2023.3235720","type":"journal-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:17:11Z","timestamp":1673378231000},"page":"1-14","source":"Crossref","is-referenced-by-count":21,"title":["Language-Aware Spatial-Temporal Collaboration for Referring Video Segmentation"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1172-1554","authenticated-orcid":false,"given":"Tianrui","family":"Hui","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9180-2935","authenticated-orcid":false,"given":"Si","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihan","family":"Ding","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaofei","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4805-0926","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0802-9567","authenticated-orcid":false,"given":"Wenguan","family":"Wang","sequence":"additional","affiliation":[{"name":"ReLER Lab, Australian Artificial Intelligence Institute, University of Technology Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luoqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Meitu Inc, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jizhong","family":"Han","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00996"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00404"},{"key":"ref56","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/132"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6895"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref53","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","author":"yang","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01265"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00624"},{"key":"ref55","first-page":"4701","article-title":"Collaborative video object segmentation by multi-scale foreground-background integration","volume":"44","author":"yang","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0212-5"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_38"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref19","first-page":"123","article-title":"Video object segmentation with language referring expressions","author":"khoreva","year":"2018","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00408"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref46","article-title":"Hierarchical interaction network for video object segmentation from referring expressions","author":"yang","year":"2021","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref45","first-page":"585","article-title":"Youtube-VOS: Sequence-to-sequence video object segmentation","author":"xu","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref42","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":"ref41","article-title":"Dynamic routing between capsules","author":"sabour","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref43","first-page":"3719","article-title":"Referring segmentation in images and videos with cross-modal self-attention network","volume":"44","author":"ye","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_39"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref4","article-title":"A survey on deep learning technique for video segmentation","author":"wang","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00907"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.565"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref79","article-title":"A comparison of LSTM and BERT for small corpus","author":"ezen-can","year":"2020"},{"key":"ref34","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref78","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","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":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01111"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref74","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref77","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"liu","year":"2019","journal-title":"arXiv 1907 11692"},{"key":"ref32","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref76","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"kenton","year":"2019","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00713"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00417"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298839"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00420"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref72","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00090"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/10013778.pdf?arnumber=10013778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,6]],"date-time":"2023-06-06T21:25:44Z","timestamp":1686086744000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10013778\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3235720","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]]}}}