{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T19:12:59Z","timestamp":1784142779686,"version":"3.55.0"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2021ZD0111901"],"award-info":[{"award-number":["2021ZD0111901"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2025"],"award-info":[{"award-number":["U21B2025"]}],"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":["U19B2036"],"award-info":[{"award-number":["U19B2036"]}],"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":["61922080"],"award-info":[{"award-number":["61922080"]}],"id":[{"id":"10.13039\/501100001809","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":[[2023,5,1]]},"DOI":"10.1109\/tpami.2022.3210780","type":"journal-article","created":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T19:44:02Z","timestamp":1664480642000},"page":"5561-5578","source":"Crossref","is-referenced-by-count":25,"title":["CRIC: A VQA Dataset for Compositional Reasoning on Vision and Commonsense"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8494-3492","authenticated-orcid":false,"given":"Difei","family":"Gao","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1830-2595","authenticated-orcid":false,"given":"Ruiping","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8348-392X","authenticated-orcid":false,"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3024-4404","authenticated-orcid":false,"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.766"},{"key":"ref8","first-page":"2953","article-title":"Exploring models and data for image question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref9","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Malinowski"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3045034"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.325"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/179"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01188"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.217"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.283"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00971"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.571"},{"key":"ref30","first-page":"193","article-title":"A large visual question answering dataset for cultural heritage","volume-title":"Proc. Int. Conf. Mach. Learn. Optim. Data Sci.","author":"Asprino"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/949\/1\/012074"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01276"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76298-0_52"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2556195.2556245"},{"key":"ref39","first-page":"1533","article-title":"Semantic parsing on freebase from question-answer pairs","volume-title":"Proc. Conf. Empir. Methods Natural Lang. Process.","author":"Berant"},{"key":"ref40","article-title":"Memory networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Weston"},{"key":"ref41","first-page":"2440","article-title":"End-to-end memory networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sukhbaatar"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1237"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00538"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1090\/qam\/1530"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00207"},{"key":"ref46","first-page":"2654","article-title":"Out of the box: Reasoning with graph convolution nets for factual visual question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Narasimhan"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_28"},{"key":"ref48","article-title":"Incorporating external knowledge to answer open-domain visual questions with dynamic memory networks","author":"Li","year":"2017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_36"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413905"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36124-3_77"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/1706238.1706248"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-934613-03-3.50014-3"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/29.1.308"},{"key":"ref56","first-page":"55","article-title":"The stanford CoreNLP natural language processing toolkit","volume-title":"Proc. 52nd Annu. Meeting Assoc. Comput. Linguistics Syst. Demonstrations","author":"Manning"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.9"},{"key":"ref58","first-page":"6077","article-title":"Bottom-up and top-down attention for image captioning and VQA","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Anderson"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_28"},{"key":"ref60","article-title":"A thousand words are worth more than a picture: Natural language-centric outside-knowledge visual question answering","author":"Gao","year":"2022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref63","article-title":"Compositional attention networks for machine reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hudson"},{"key":"ref64","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6428"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10091695\/09905976.pdf?arnumber=9905976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T19:54:16Z","timestamp":1719345256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9905976\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,1]]},"references-count":76,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3210780","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,1]]}}}