{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T01:50:07Z","timestamp":1769046607453,"version":"3.49.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"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":["61925201"],"award-info":[{"award-number":["61925201"]}],"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":["61771025"],"award-info":[{"award-number":["61771025"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1109\/tcsvt.2020.2991866","type":"journal-article","created":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T20:19:31Z","timestamp":1588364371000},"page":"1042-1054","source":"Crossref","is-referenced-by-count":34,"title":["Multi-Level Knowledge Injecting for Visual Commonsense Reasoning"],"prefix":"10.1109","volume":"31","author":[{"given":"Zhang","family":"Wen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7658-3845","authenticated-orcid":false,"given":"Yuxin","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.362"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1224"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/179"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76298-0_52"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00895"},{"key":"ref36","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref35","first-page":"4444","article-title":"ConceptNet 5.5: An open multilingual graph of general knowledge","author":"speer","year":"2017","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00036"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00857"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref1","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref20","article-title":"Image question answering: A visual semantic embedding model and a new dataset","author":"ren","year":"2015","journal-title":"arXiv 1505 02074v1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref23","first-page":"1039","article-title":"Neural-symbolic VQA: Disentangling reasoning from vision and language understanding","author":"yi","year":"2018","journal-title":"Proc Neural Inf Process Syst (NeurIPS)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00648"},{"key":"ref25","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc Neural Inf Process Syst (NeurIPS)"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_44"},{"key":"ref55","article-title":"Coco-text: Dataset and benchmark for text detection and recognition in natural images","author":"veit","year":"2016","journal-title":"arXiv 1601 07140"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref52","first-page":"1","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref10","article-title":"Natural language inference","author":"maccartney","year":"2009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29694-9_1"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013027"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1116-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00801"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/126"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00807"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2701413"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2808685"},{"key":"ref49","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol (NAACL-HLT)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_30"},{"key":"ref45","first-page":"6095","article-title":"Macnet: Transferring knowledge from machine comprehension to sequence-to-sequence models","author":"pan","year":"2018","journal-title":"Proc Neural Inf Process Syst (NeurIPS)"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref47","first-page":"1","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"zagoruyko","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref42","first-page":"1394","article-title":"CORPP: Commonsense reasoning and probabilistic planning, as applied to dialog with a mobile robot","author":"zhang","year":"2015","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1043"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/263"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"jialin pan","year":"2010","journal-title":"IEEE Trans Knowl Data Eng"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9370015\/09083951.pdf?arnumber=9083951","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:29Z","timestamp":1652194229000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9083951\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":55,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2020.2991866","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3]]}}}