{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T06:00:15Z","timestamp":1771048815153,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["2018AAA0100604"],"award-info":[{"award-number":["2018AAA0100604"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61720106006"],"award-info":[{"award-number":["61720106006"]}],"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":["62002355"],"award-info":[{"award-number":["62002355"]}],"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":["61832002"],"award-info":[{"award-number":["61832002"]}],"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":["61532009"],"award-info":[{"award-number":["61532009"]}],"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":["61751211"],"award-info":[{"award-number":["61751211"]}],"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":["62072455"],"award-info":[{"award-number":["62072455"]}],"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":["U1705262"],"award-info":[{"award-number":["U1705262"]}],"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":["U1836220"],"award-info":[{"award-number":["U1836220"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research Program of Frontier Sciences of CAS","award":["QYZDJ-SSW-JSC039"],"award-info":[{"award-number":["QYZDJ-SSW-JSC039"]}]},{"DOI":"10.13039\/501100012152","name":"National Postdoctoral Program for Innovative Talents","doi-asserted-by":"publisher","award":["BX20190367"],"award-info":[{"award-number":["BX20190367"]}],"id":[{"id":"10.13039\/501100012152","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L201001"],"award-info":[{"award-number":["L201001"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Province key research, and development plan","award":["BE2020036"],"award-info":[{"award-number":["BE2020036"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3091882","type":"journal-article","created":{"date-parts":[[2021,6,28]],"date-time":"2021-06-28T21:16:51Z","timestamp":1624915011000},"page":"2986-2997","source":"Crossref","is-referenced-by-count":30,"title":["Explicit Cross-Modal Representation Learning for Visual Commonsense Reasoning"],"prefix":"10.1109","volume":"24","author":[{"given":"Xi","family":"Zhang","sequence":"first","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Feifei","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5338"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3026892"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref12","first-page":"615","article-title":"TAB-VCR: Tags and attributes based vcr baselines","volume-title":"Proc. Conf. Workshop Neural Inf. Process. Syst.","volume":"15","author":"Lin","year":"2019"},{"key":"ref13","first-page":"2769","article-title":"Heterogeneous graph learning for visual commonsense reasoning","volume-title":"Proc. Conf. Workshop Neural Inf. Process. Syst.","author":"Yu","year":"2019"},{"key":"ref14","first-page":"5669","article-title":"Connective cognition network for directional visual commonsense reasoning","volume-title":"Proc. Conf. Workshop Neural Inf. Process. Syst.","author":"Wu","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00857"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1455"},{"key":"ref18","article-title":"Neural module networks for reasoning over text","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gupta","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2991866"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1209"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2812"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref27","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Conf. Workshop Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2995278"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002667"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2935678"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6833"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01007"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00684"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/144"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_32"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01283"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01002"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01276"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/153"},{"key":"ref44","article-title":"The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mao","year":"2018"},{"key":"ref45","first-page":"1039","article-title":"Neural-symbolic VQA: Disentangling reasoning from vision and language understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yi","year":"2018"},{"key":"ref46","first-page":"5884","article-title":"Closed loop neural-symbolic learning via integrating neural perception, grammar parsing, and symbolic reasoning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2020"},{"key":"ref47","first-page":"5903","article-title":"Learning by abstraction: The neural state machine","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hudson","year":"2019"},{"key":"ref48","first-page":"5001","article-title":"Visual concept-metaconcept learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Han","year":"2019"},{"key":"ref49","article-title":"Object-centric diagnosis of visual reasoning","author":"Yang","year":"2020"},{"key":"ref50","article-title":"Clevrer: Collision events for video representation and reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yi","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.201"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1152"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_44"},{"key":"ref57","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. Inter. Conf. Learn. Represent.","author":"Kim","year":"2017"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09465732.pdf?arnumber=9465732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T22:59:09Z","timestamp":1705013949000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9465732\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3091882","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}