{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:57:23Z","timestamp":1771700243727,"version":"3.50.1"},"reference-count":45,"publisher":"Zhejiang University Press","issue":"5","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Front Inform Technol Electron Eng"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1631\/fitee.2000722","type":"journal-article","created":{"date-parts":[[2021,5,28]],"date-time":"2021-05-28T00:05:37Z","timestamp":1622160337000},"page":"625-637","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Visual commonsense reasoning with directional visual connections","\u9762\u5411\u89c6\u89c9\u5e38\u8bc6\u63a8\u7406\u7684\u6709\u5411\u89c6\u89c9\u8fde\u63a5"],"prefix":"10.1631","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2768-1398","authenticated-orcid":false,"given":"Yahong","family":"Han","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aming","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linchao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"635","published-online":{"date-parts":[[2021,5,28]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00636"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.279"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2017.2711011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2644615"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.285"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2015.03.057"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00209"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01081"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2017.2699184"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00052"},{"key":"ref12","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"Devlin","year":"2019","journal-title":"Proc Conf of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies"},{"key":"ref13","first-page":"67","volume-title":"Expertise in Context: Human and Machine.","author":"Feltovich","year":"1997"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_29"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.169"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2010.5540039"},{"key":"ref20","volume-title":"Multi-modal dual attention memory for video story question answering.","author":"Kim","year":"2018"},{"key":"ref21","volume-title":"Semi-supervised classification with graph convolutional networks.","author":"Kipf","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00999"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref24","volume-title":"VisualBERT: a simple and performant baseline for vision and language.","author":"Li","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.345"},{"key":"ref27","volume-title":"ViLBERT: pre-training task-agnostic visiolinguistic representations for vision-and-language tasks.","author":"Lu","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.576"},{"key":"ref30","first-page":"2659","article-title":"Out of the box: reasoning with graph convolution nets for factual visual question answering","author":"Narasimhan","year":"2018","journal-title":"Proc 32nd Int Conf on Neural Information Processing Systems"},{"key":"ref31","volume-title":"Learning conditioned graph structures for interpretable visual question answering.","author":"Norcliffe-Brown","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.1910001"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.2040000"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1126\/science.1238411"},{"key":"ref35","volume-title":"FiLM: visual reasoning with a general conditioning layer.","author":"Perez","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00214"},{"key":"ref37","volume-title":"VL-BERT: pre-training of generic visual-linguistic representations.","author":"Su","year":"2019"},{"key":"ref38","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van Der Maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2018","journal-title":"Proc Int Conf on Learning Representations"},{"key":"ref41","first-page":"5669","article-title":"Connective cognition network for directional visual commonsense reasoning","author":"Wu","year":"2019","journal-title":"Proc 33rd Conf on Neural Information Processing Systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1110"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00688"},{"key":"ref45","volume-title":"Graph neural networks: a review of methods and applications.","author":"Zhou","year":"2018"}],"container-title":["Frontiers of Information Technology & Electronic Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1631\/FITEE.2000722.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1631\/FITEE.2000722\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1631\/FITEE.2000722.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T06:37:56Z","timestamp":1771655876000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1631\/FITEE.2000722"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5]]},"references-count":45,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["1660"],"URL":"https:\/\/doi.org\/10.1631\/fitee.2000722","relation":{},"ISSN":["2095-9184","2095-9230"],"issn-type":[{"value":"2095-9184","type":"print"},{"value":"2095-9230","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5]]},"assertion":[{"value":"25 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Yahong HAN, Aming WU, Linchao ZHU, and Yi YANG declare that they have no conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethics guidelines"}}]}}