{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:52:11Z","timestamp":1761126731126,"version":"3.37.3"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"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":["#U1713209","#61520106009","61773117"],"award-info":[{"award-number":["#U1713209","#61520106009","61773117"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008081","name":"Southeast University","doi-asserted-by":"publisher","award":["#YBJJ1520"],"award-info":[{"award-number":["#YBJJ1520"]}],"id":[{"id":"10.13039\/501100008081","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2020,2,1]]},"DOI":"10.1109\/tpami.2018.2880185","type":"journal-article","created":{"date-parts":[[2018,11,9]],"date-time":"2018-11-09T23:48:22Z","timestamp":1541807302000},"page":"460-474","source":"Crossref","is-referenced-by-count":20,"title":["Inverse Visual Question Answering: A New Benchmark and VQA Diagnosis Tool"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4811-7828","authenticated-orcid":false,"given":"Feng","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2530-1059","authenticated-orcid":false,"given":"Tao","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4867-7486","authenticated-orcid":false,"given":"Timothy M.","family":"Hospedales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6385-6776","authenticated-orcid":false,"given":"Wankou","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9269-334X","authenticated-orcid":false,"given":"Changyin","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"462","article-title":"Image-grounded conversations: Multimodal context for natural question and response generation","author":"mostafazadeh","year":"2017","journal-title":"Proc Int Joint Conf Natural Language Process"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"article-title":"Towards transparent ai systems: Interpreting visual question answering models","year":"2016","author":"goyal","key":"ref33"},{"key":"ref32","first-page":"451","article-title":"Ask, attend and answer: Exploring question-guided spatial attention for visual question answering","author":"xu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.575"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/592"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1170"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1097"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.2200\/S00429ED1V01Y201207AIM018"},{"key":"ref62","first-page":"235","article-title":"Integrated perception with recurrent multi-task neural networks","author":"bilen","year":"2016","journal-title":"Proc Adv Neural Info Process"},{"key":"ref61","article-title":"Active learning for visual question answering: An empirical study","volume":"abs 1711 1732","author":"lin","year":"2017","journal-title":"CoRR"},{"journal-title":"A Theory of Cognitive Dissonance","year":"1962","author":"festinger","key":"ref63"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.1109\/TPAMI.2012.67","article-title":"Recognizing human-object interactions in still images by modeling the mutual context of objects and human poses","volume":"34","author":"yao","year":"2012","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.443"},{"key":"ref25","first-page":"852","article-title":"Visual relationship detection with language priors","author":"lu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref50","article-title":"Microsoft COCO captions: Data collection and evaluation server","volume":"abs 1504 325","author":"chen","year":"2015","journal-title":"CoRR"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref59","first-page":"551","article-title":"Multimodal learning and reasoning for visual question answering","author":"ilievski","year":"2017","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.416"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref56","article-title":"Interpretable counting for visual question answering","author":"trott","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref55","first-page":"3294","article-title":"Skip-thought vectors","author":"kiros","year":"2015","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref54","first-page":"2852","article-title":"Seqgan: Sequence generative adversarial nets with policy gradient","author":"yu","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref53","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref52","article-title":"Exploring nearest neighbor approaches for image captioning","volume":"abs 1505 4467","author":"devlin","year":"2015","journal-title":"CoRR"},{"key":"ref10","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2437384"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1092"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1203"},{"key":"ref13","first-page":"727","article-title":"Revisiting visual question answering baselines","author":"jabri","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref14","first-page":"2953","article-title":"Exploring models and data for image question answering","author":"ren","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref16","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1090"},{"key":"ref19","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref4","first-page":"787","article-title":"Referit game: Referring to objects in photographs of natural scenes","author":"kazemzadeh","year":"2014","journal-title":"Proc Int Conf Empirical Methods Natural Language Process"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"key":"ref6","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1422953112"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5962\/bhl.title.56164"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref7","article-title":"Towards a visual turing challenge","author":"malinowski","year":"2014","journal-title":"NIPS 2014 Workshop on Learning Semantics"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2330697"},{"key":"ref46","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref45","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00898"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM.2016.7795300"},{"article-title":"Understanding neural networks through deep visualization","year":"2015","author":"yosinski","key":"ref42"},{"key":"ref41","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00915"},{"key":"ref43","first-page":"3","article-title":"Generating visual explanations","author":"hendricks","year":"2016","journal-title":"Proc Eur Conf Comput Vis"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8952810\/08528867.pdf?arnumber=8528867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:59:25Z","timestamp":1651067965000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8528867\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,1]]},"references-count":63,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2018.2880185","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2020,2,1]]}}}