{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T03:46:58Z","timestamp":1768708018751,"version":"3.49.0"},"reference-count":54,"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":["61602197"],"award-info":[{"award-number":["61602197"]}],"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":["L1924068"],"award-info":[{"award-number":["L1924068"]}],"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":["61772076"],"award-info":[{"award-number":["61772076"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-AFSG Research Fund","award":["RF20210005"],"award-info":[{"award-number":["RF20210005"]}]},{"name":"Joint Laboratory of HUST and Pingan Property & Casualty Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3190686","type":"journal-article","created":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T19:34:54Z","timestamp":1657827294000},"page":"5344-5357","source":"Crossref","is-referenced-by-count":14,"title":["Depth-Aware and Semantic Guided Relational Attention Network for Visual Question Answering"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2770-9330","authenticated-orcid":false,"given":"Yuhang","family":"Liu","sequence":"first","affiliation":[{"name":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4488-0102","authenticated-orcid":false,"given":"Wei","family":"Wei","sequence":"additional","affiliation":[{"name":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daowan","family":"Peng","sequence":"additional","affiliation":[{"name":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6795-2311","authenticated-orcid":false,"given":"Xian-Ling","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"He","sequence":"additional","affiliation":[{"name":"Naval University of Engineering, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8629-4622","authenticated-orcid":false,"given":"Pan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.683"},{"key":"ref52","article-title":"Accurate, large minibatch SGD: Training imagenet in 1 hour","author":"goyal","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref10","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"su","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref54","first-page":"5903","article-title":"Learning by abstraction: The neural state machine","author":"hudson","year":"0","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref17","first-page":"1","article-title":"Compositional attention networks for machine reasoning","author":"hudson","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1264","DOI":"10.1109\/TMM.2020.2995278","article-title":"Self-adaptive neural module transformer for visual question answering","volume":"23","author":"huasong","year":"2021","journal-title":"IEEE Trans Multimedia"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60636-7_8"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2943456"},{"key":"ref51","first-page":"746","article-title":"Indoor segmentation and support inference from RGBD images","author":"silberman","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref50","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref47","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1038-2"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref44","first-page":"1571","article-title":"Bilinear attention networks","author":"kim","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3026892"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00209"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00192"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413977"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190771"},{"key":"ref37","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","author":"lee","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475712"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01050"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_41"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4063413"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01098"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01039"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.643"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"ref25","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_25"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.642"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1349"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09830073.pdf?arnumber=9830073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T19:58:04Z","timestamp":1701115084000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9830073\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3190686","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}