{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T03:49:50Z","timestamp":1771645790914,"version":"3.50.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2021YFB3600503"],"award-info":[{"award-number":["2021YFB3600503"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972097"],"award-info":[{"award-number":["61972097"]}],"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":["U21A20472"],"award-info":[{"award-number":["U21A20472"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Scientific Research Project for Technology Promotes Police","award":["2024YZ040001"],"award-info":[{"award-number":["2024YZ040001"]}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2025J01536"],"award-info":[{"award-number":["2025J01536"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2021J01612"],"award-info":[{"award-number":["2021J01612"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Science and Technology Project of Fujian Province","award":["2021HZ022007"],"award-info":[{"award-number":["2021HZ022007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3599078","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T18:48:19Z","timestamp":1755197299000},"page":"7326-7339","source":"Crossref","is-referenced-by-count":1,"title":["Quality-Guided Vision-Language Learning for Long-Term Action Quality Assessment"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3717-8713","authenticated-orcid":false,"given":"Huangbiao","family":"Xu","sequence":"first","affiliation":[{"name":"Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing, College of Computer and Data Science, Fuzhou University, Fuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4518-3273","authenticated-orcid":false,"given":"Huanqi","family":"Wu","sequence":"additional","affiliation":[{"name":"Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing, College of Computer and Data Science, Fuzhou University, Fuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9059-5391","authenticated-orcid":false,"given":"Xiao","family":"Ke","sequence":"additional","affiliation":[{"name":"Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing, College of Computer and Data Science, Fuzhou University, Fuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7397-4661","authenticated-orcid":false,"given":"Yuezhou","family":"Li","sequence":"additional","affiliation":[{"name":"Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing, College of Computer and Data Science, Fuzhou University, Fuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3767-6816","authenticated-orcid":false,"given":"Rui","family":"Xu","sequence":"additional","affiliation":[{"name":"Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing, College of Computer and Data Science, Fuzhou University, Fuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4118-8823","authenticated-orcid":false,"given":"Wenzhong","family":"Guo","sequence":"additional","affiliation":[{"name":"Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing, College of Computer and Data Science, Fuzhou University, Fuzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_36"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_25"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00238"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_24"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2361121"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24553-9_53"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00940"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00805"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3294800"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25392"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3362135"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3328180"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00643"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475438"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32959"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-28865-1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611795"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8537-1_32"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448422"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01744"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00323"},{"key":"ref26","first-page":"1771","article-title":"CoFinal: Enhancing action quality assessment with coarse-to-fine instruction alignment","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Zhou","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413560"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2927118"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613795"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00782"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00296"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120347"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00986"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3281413"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00044"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2973828"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3251108"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3243659"},{"key":"ref41","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3358085"},{"key":"ref44","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2022"},{"key":"ref45","first-page":"33781","article-title":"Bridging the gap between object and image-level representations for open-vocabulary detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bangalath","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01417"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3396272"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref55","first-page":"38149","article-title":"Weakly-supervised multi-granularity map learning for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3473140"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00161"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.16"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3487242"},{"key":"ref64","article-title":"A short note about kinetics-600","author":"Carreira","year":"2018"},{"key":"ref65","article-title":"Parameter efficient multimodal transformers for video representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","year":"2020"},{"key":"ref66","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref67","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11124552.pdf?arnumber=11124552","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T04:44:36Z","timestamp":1761281076000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11124552\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3599078","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}