{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:21:08Z","timestamp":1792786868812,"version":"4.5.0"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Artificial Intelligence-National Science and Technology Major Project","award":["2023ZD0121200"],"award-info":[{"award-number":["2023ZD0121200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302474"],"award-info":[{"award-number":["62302474"]}],"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":["62402471"],"award-info":[{"award-number":["62402471"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Fund for Excellent Young Scholars","doi-asserted-by":"publisher","award":["62222212"],"award-info":[{"award-number":["62222212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2025.3649363","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:04:36Z","timestamp":1768255476000},"page":"540-555","source":"Crossref","is-referenced-by-count":3,"title":["Subjective-Objective Emotion-Correlated Generation Network for Subjective Video Captioning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2774-2875","authenticated-orcid":false,"given":"Weidong","family":"Chen","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6764-3375","authenticated-orcid":false,"given":"Peipei","family":"Song","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2839-8693","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-8126","authenticated-orcid":false,"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3158546"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3268004"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3159472"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00191"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01789"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28252"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5364"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00191"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3598709"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611726"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3058555"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681603"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3359045"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3311447"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3333206"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3390984"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29836"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355402"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.472"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657807"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3650042"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27827"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3546312"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00784"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00753"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-558701-3.50007-7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3222623"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3638558"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3526066"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11878-w"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3094362"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.25"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3475957.3484457"},{"key":"ref35","first-page":"38586","article-title":"Massively multilingual corpus of sentiment datasets and multi-faceted sentiment classification benchmark","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Augustyniak"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3117124"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01183"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28891"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3106813"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01007"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-019-10033-9"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2928998"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301363"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547761"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3663572"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475534"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00422"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01811"},{"key":"ref49","first-page":"36993","article-title":"AffectGPT: A new dataset, model, and benchmark for emotion understanding with multimodal large language models","volume-title":"Proc. Forty-second Int. Conf. Mach. Learn.","author":"Lian"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.326"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00515"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671552"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3518"},{"key":"ref54","first-page":"76385","article-title":"MODA: MOdular duplex attention for multimodal perception, cognition, and emotion understanding","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00513"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00330"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29826"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3633334"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32781"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3514250"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3307969"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120867"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680686"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3322329"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103864"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183402"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01204"},{"key":"ref71","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Chen"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8724"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref76","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref78","first-page":"611","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25082-8_1"},{"key":"ref80","article-title":"Separable self-attention for mobile vision transformers","author":"Mehta","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01598"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01426"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612152"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1137"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_1"},{"key":"ref86","article-title":"GPT-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv:2410.21276"},{"key":"ref87","article-title":"VideoLLaMA 3: Frontier multimodal foundation models for image and video understanding","author":"Zhang","year":"2025","journal-title":"arXiv:2501.13106"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11339362.pdf?arnumber=11339362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:10:44Z","timestamp":1770671444000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339362\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3649363","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}