{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T20:27:32Z","timestamp":1767990452328,"version":"3.49.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2021ZD0113004"],"award-info":[{"award-number":["2021ZD0113004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3318289","type":"journal-article","created":{"date-parts":[[2023,9,22]],"date-time":"2023-09-22T17:55:09Z","timestamp":1695405309000},"page":"3937-3950","source":"Crossref","is-referenced-by-count":2,"title":["Inexactly Matched Referring Expression Comprehension With Rationale"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6143-0854","authenticated-orcid":false,"given":"Xiaochuan","family":"Li","sequence":"first","affiliation":[{"name":"Inspur Electronic Information Industry Company, Ltd., Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1918-4762","authenticated-orcid":false,"given":"Baoyu","family":"Fan","sequence":"additional","affiliation":[{"name":"Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6318-3342","authenticated-orcid":false,"given":"Runze","family":"Zhang","sequence":"additional","affiliation":[{"name":"Inspur Electronic Information Industry Company, Ltd., Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8483-2511","authenticated-orcid":false,"given":"Kun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Inspur Electronic Information Industry Company, Ltd., Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1303-6681","authenticated-orcid":false,"given":"Zhenhua","family":"Guo","sequence":"additional","affiliation":[{"name":"Inspur Electronic Information Industry Company, Ltd., Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9170-0090","authenticated-orcid":false,"given":"Yaqian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Inspur Electronic Information Industry Company, Ltd., Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4297-4335","authenticated-orcid":false,"given":"Rengang","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00180"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref7","first-page":"89","article-title":"Comprehension","volume-title":"Childrens Reading Comprehension and Assessment","author":"Kintsch","year":"2005"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414038"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475340"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3124317"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3161076"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.375"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00850"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00431"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413905"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01010"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1215"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2840980"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-3064-3_9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(03)00129-3"},{"key":"ref27","first-page":"474","article-title":"Grounding adaptive language games in robotic agents","volume-title":"Proc. 4th Eur. Conf. Artif. Life","volume":"97","author":"Steels","year":"1997"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9792-8"},{"key":"ref29","article-title":"Understanding image and text simultaneously: A dual vision-language machine comprehension task","author":"Ding","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.475"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137605"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.520"},{"key":"ref39","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Su","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3090426"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127346"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181116"},{"key":"ref46","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Cho","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"issue":"8","key":"ref52","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1177\/107769905303000401"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1115\/1.3101882"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10261300.pdf?arnumber=10261300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T06:19:00Z","timestamp":1709360340000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10261300\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3318289","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}