{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T20:43:42Z","timestamp":1770065022863,"version":"3.49.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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":["62322211"],"award-info":[{"award-number":["62322211"]}],"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":["61931008"],"award-info":[{"award-number":["61931008"]}],"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":["62336008"],"award-info":[{"award-number":["62336008"]}],"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":["U21B2038"],"award-info":[{"award-number":["U21B2038"]}],"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":["62225207"],"award-info":[{"award-number":["62225207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["E2ET1104"],"award-info":[{"award-number":["E2ET1104"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key R&#x0026;D Plan Project of Zhejiang Province","award":["2024C01023"],"award-info":[{"award-number":["2024C01023"]}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2020108"],"award-info":[{"award-number":["2020108"]}],"id":[{"id":"10.13039\/501100004739","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":[[2024,7]]},"DOI":"10.1109\/tpami.2024.3365104","type":"journal-article","created":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T23:43:31Z","timestamp":1707867811000},"page":"4926-4943","source":"Crossref","is-referenced-by-count":44,"title":["SMART: Syntax-Calibrated Multi-Aspect Relation Transformer for Change Captioning"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9525-9060","authenticated-orcid":false,"given":"Yunbin","family":"Tu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8437-4824","authenticated-orcid":false,"given":"Liang","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5358-2786","authenticated-orcid":false,"given":"Li","family":"Su","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2510-8993","authenticated-orcid":false,"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186410"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548206"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3226328"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2404834"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.37"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013834"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1436"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1182"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00472"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00198"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074803"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00263"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00275"},{"key":"ref15","first-page":"2095","article-title":"Agnostic change captioning with cycle consistency","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Kim"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/int.22821"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20218"},{"key":"ref18","first-page":"33","article-title":"CLIP4IDC: CLIP for image difference captioning","volume-title":"Proc. Conf. Asia-Pacific Chapter Assoc. Comput. Linguistics","author":"Guo"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123354"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107702"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109204"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_34"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.735"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3242142"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3254162"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3268004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.10.018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2976552"},{"key":"ref35","first-page":"5669","article-title":"Connective cognition network for directional visual commonsense reasoning","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.273"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3159472"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3158546"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3176690"},{"key":"ref44","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref45","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref47","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"Banerjee"},{"key":"ref48","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref51","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073478"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref55","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10550108\/10433795.pdf?arnumber=10433795","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T19:09:22Z","timestamp":1725995362000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10433795\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":55,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3365104","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":[[2024,7]]}}}