{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T03:41:52Z","timestamp":1771645312861,"version":"3.50.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"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":["2022YFB3103704"],"award-info":[{"award-number":["2022YFB3103704"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276248"],"award-info":[{"award-number":["62276248"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Academy of Artificial Intelligence","award":["BAAI2020ZJ0303"],"award-info":[{"award-number":["BAAI2020ZJ0303"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,9,1]]},"DOI":"10.1109\/tpami.2023.3268093","type":"journal-article","created":{"date-parts":[[2023,4,19]],"date-time":"2023-04-19T17:27:28Z","timestamp":1681925248000},"page":"11352-11364","source":"Crossref","is-referenced-by-count":4,"title":["Visual Reasoning: From State to Transformation"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1524-9362","authenticated-orcid":false,"given":"Xin","family":"Hong","sequence":"first","affiliation":[{"name":"CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7811-3262","authenticated-orcid":false,"given":"Yanyan","family":"Lan","sequence":"additional","affiliation":[{"name":"Institute of AI Industrial Research, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1161-8546","authenticated-orcid":false,"given":"Liang","family":"Pang","sequence":"additional","affiliation":[{"name":"Data Intelligence System Research Center, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9509-8674","authenticated-orcid":false,"given":"Jiafeng","family":"Guo","sequence":"additional","affiliation":[{"name":"CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5201-8195","authenticated-orcid":false,"given":"Xueqi","family":"Cheng","sequence":"additional","affiliation":[{"name":"CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2034"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4684-2547-5_2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_30"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.325"},{"key":"ref10","article-title":"Compositional attention networks for machine reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hudson"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00472"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.542"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref23","article-title":"Visual entailment task for visually-grounded language learning","author":"Xie","year":"2018"},{"key":"ref24","article-title":"Visual entailment: A novel task for fine-grained image understanding","author":"Xie","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref26","article-title":"CATER: A diagnostic dataset for compositional actions and temporal reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Girdhar"},{"key":"ref27","article-title":"CLEVRER: Collision events for video representation and reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yi"},{"key":"ref28","first-page":"5083","article-title":"PHYRE: A new benchmark for physical reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bakhtin"},{"key":"ref29","article-title":"Cophy: Counterfactual learning of physical dynamics","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baradel"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298744"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_11"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01133"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.333"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.291"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.318"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.234"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351040"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_20"},{"key":"ref39","article-title":"Blender\u2013A 3D modelling and rendering package","author":"Community","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00431"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-013-0812-6"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.2307\/2332226"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.4324\/9780203088869"},{"key":"ref45","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10210213\/10105523.pdf?arnumber=10105523","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T19:54:50Z","timestamp":1719345290000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10105523\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":48,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3268093","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":[[2023,9,1]]}}}