{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:41:33Z","timestamp":1777128093317,"version":"3.51.4"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":["62206267"],"award-info":[{"award-number":["62206267"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tcsvt.2024.3445337","type":"journal-article","created":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T17:37:34Z","timestamp":1724089054000},"page":"13349-13363","source":"Crossref","is-referenced-by-count":5,"title":["Relation-Aware Multi-Pass Comparison Deconfounded Network for Change Captioning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7520-7799","authenticated-orcid":false,"given":"Zhicong","family":"Lu","sequence":"first","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8833-4862","authenticated-orcid":false,"given":"Li","family":"Jin","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6705-8387","authenticated-orcid":false,"given":"Ziwei","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changyuan","family":"Tian","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xian","family":"Sun","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0286-6660","authenticated-orcid":false,"given":"Xiaoyu","family":"Li","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0294-8973","authenticated-orcid":false,"given":"Yi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronic Countermeasures, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0696-5252","authenticated-orcid":false,"given":"Qi","family":"Li","sequence":"additional","affiliation":[{"name":"School of Psychology, Beijing Normal University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangluan","family":"Xu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"4024","article-title":"Learning to describe differences between pairs of similar images","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Jhamtani"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00472"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00210"},{"key":"ref4","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Sutskever"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00275"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3176055"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3154154"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_34"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3254162"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3268004"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00263"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3121705"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref15","volume-title":"Causal Inference in Statistics: A Primer","author":"Pearl","year":"2016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178844"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3121062"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3243725"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3036860"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3177320"},{"key":"ref22","article-title":"Visual recognition with deep nearest centroids","author":"Wang","year":"2022","journal-title":"arXiv:2209.07383"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202574"},{"key":"ref24","first-page":"1873","article-title":"Expressing visual relationships via language","volume-title":"Proc. 57th Annu. Meeting Assoc. Comput. Linguistics","author":"Tan"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.6"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20218"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00198"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169894"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3181490"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3336371"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/384"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.37"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01751"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.56"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.812"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462962"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467289"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref40","first-page":"15816","article-title":"Learnable Fourier features for multi-dimensional spatial positional encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"ref43","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"354","author":"Chu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3328485"},{"key":"ref48","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Gu"},{"key":"ref49","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv:2111.00396"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074803"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref53","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref54","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization ACL","author":"Lin"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref57","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref58","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10811783\/10638627.pdf?arnumber=10638627","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T20:23:02Z","timestamp":1736972582000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10638627\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":59,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3445337","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}