{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T05:03:46Z","timestamp":1750395826666,"version":"3.40.2"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["62106089","62020106012","62332008","62336004"],"award-info":[{"award-number":["62106089","62020106012","62332008","62336004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tsmc.2024.3524682","type":"journal-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T18:56:47Z","timestamp":1737572207000},"page":"2821-2833","source":"Crossref","is-referenced-by-count":2,"title":["ATMNet: Adaptive Two-Stage Modular Network for Accurate Video Captioning"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9015-3128","authenticated-orcid":false,"given":"Tianyang","family":"Xu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0622-4326","authenticated-orcid":false,"given":"Yunjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3967-4497","authenticated-orcid":false,"given":"Xiaoning","family":"Song","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4485-4249","authenticated-orcid":false,"given":"Zheng-Hua","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Surrey, Guildford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-5778","authenticated-orcid":false,"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2625840"},{"key":"ref2","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"Proc. 40th Annu. Meeting Assoc. Comput. Linguist.","author":"Papineni"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3248324"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475519"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref12","article-title":"Image as a foreign language: BEiT pretraining for all vision and vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv:2208.10442"},{"key":"ref13","article-title":"Learning phrase representations using RNN encoderdecoder for statistical machine translation","author":"Cho","year":"2014","journal-title":"arXiv:1406.1078"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5815\/ijigsp.2019.06.01"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8679"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020346032608"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref25","first-page":"6881","article-title":"Rethinking semantic segmentation from a sequenceto- sequence perspective with transformers","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Zheng"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref27","first-page":"1","article-title":"COOT: Cooperative hierarchical transformer for video-text representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ging"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2840341"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref30","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020","journal-title":"arXiv:2002.06353"},{"key":"ref31","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2531671"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01606"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2609153"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"ref37","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. Meas. Mach. Transl.\/Summ.","author":"Banerjee"},{"key":"ref38","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summ. Branches Out","author":"Lin"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref40","first-page":"29","article-title":"Using TF-IDF to determine word relevance in document queries","volume-title":"Proc. 1st Instr. Conf. Mach. Learn.","author":"Ramos"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4076(88)90048-6"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9149229"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00854"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00157"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/384"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref55","article-title":"Video understanding as machine translation","author":"Korbar","year":"2020","journal-title":"arXiv:2006.07203"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican1174-106"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/10933808\/10849988.pdf?arnumber=10849988","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T18:39:16Z","timestamp":1742841556000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849988\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":57,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2024.3524682","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"type":"print","value":"2168-2216"},{"type":"electronic","value":"2168-2232"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}