{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T02:57:33Z","timestamp":1783825053457,"version":"3.55.0"},"reference-count":58,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171294"],"award-info":[{"award-number":["62171294"]}],"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":["62101344"],"award-info":[{"award-number":["62101344"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010226","name":"Department of Education of Guangdong Province","doi-asserted-by":"publisher","award":["2018KCXTD027"],"award-info":[{"award-number":["2018KCXTD027"]}],"id":[{"id":"10.13039\/501100010226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022A1515010159"],"award-info":[{"award-number":["2022A1515010159"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2020A1515010959"],"award-info":[{"award-number":["2020A1515010959"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key project of Shenzhen Science and Technology Plan","award":["20220810180617001"],"award-info":[{"award-number":["20220810180617001"]}]},{"DOI":"10.13039\/501100009019","name":"Shenzhen University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009019","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015803","name":"Tencent","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientific Research Foundation for Young Teachers of Shenzhen University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2023.3241802","type":"journal-article","created":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T19:55:49Z","timestamp":1675367749000},"page":"8805-8816","source":"Crossref","is-referenced-by-count":24,"title":["Multiple Relational Learning Network for Joint Referring Expression Comprehension and Segmentation"],"prefix":"10.1109","volume":"25","author":[{"given":"Guoguang","family":"Hua","sequence":"first","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen Key Laboratory of Advanced Machine Learning and Applications, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8461-1946","authenticated-orcid":false,"given":"Muxin","family":"Liao","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen Key Laboratory of Advanced Machine Learning and Applications, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7616-8382","authenticated-orcid":false,"given":"Shishun","family":"Tian","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen Key Laboratory of Advanced Machine Learning and Applications, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen Key Laboratory of Advanced Machine Learning and Applications, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1389-9089","authenticated-orcid":false,"given":"Wenbin","family":"Zou","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen Key Laboratory of Advanced Machine Learning and Applications, College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref3","first-page":"7685","article-title":"Language and visual entity relationship graph for agent navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hong","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7698"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref9","first-page":"1","article-title":"Referring expression object segmentation with caption-aware consistency","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Chen","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref11","first-page":"787","article-title":"ReferItGame: Referring to objects in photographs of natural scenes","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process","author":"Sahar","year":"2014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2971171"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074008"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2811621"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3139467"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.122"},{"key":"ref29","first-page":"1","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chung","year":"2014"},{"key":"ref30","article-title":"RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free","author":"Fu","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3090426"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3147385"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.066"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref37","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Repress","author":"Kingma","year":"2014"},{"key":"ref38","first-page":"1","article-title":"SGDR: Stochastic gradient descent with restarts","volume-title":"Proc. Int. Conf. Learn. Repress.","author":"Loshchilov","year":"2016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2991504"},{"key":"ref41","first-page":"4967","article-title":"A simple neural network module for relational reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Santor","year":"2017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref45","article-title":"PPGN: Phrase-guided proposal generation network for referring expression comprehension","author":"Yang","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413850"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2942480"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414006"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794220"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.304"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_5"},{"key":"ref54","article-title":"YOLOv3: An Incremental Improvement","author":"Redmon","year":"2018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.05.059"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/10035452.pdf?arnumber=10035452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:26:16Z","timestamp":1705019176000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10035452\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3241802","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}