{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:58:58Z","timestamp":1759334338445,"version":"build-2065373602"},"reference-count":80,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62401533"],"award-info":[{"award-number":["62401533"]}],"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":["62171427"],"award-info":[{"award-number":["62171427"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3595019","type":"journal-article","created":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T17:45:07Z","timestamp":1754588707000},"page":"6489-6502","source":"Crossref","is-referenced-by-count":0,"title":["Video Segmentation and Tokenization for Model-Based Video Scene Classification"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3843-3920","authenticated-orcid":false,"given":"Qing","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Yajian","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0904-8946","authenticated-orcid":false,"given":"Hang","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Shuxian","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2387-0389","authenticated-orcid":false,"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1892-2551","authenticated-orcid":false,"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"159","article-title":"Enabling access to sound archives through integration, enrichment and retrieval: The EASAIER project","volume-title":"Proc. Int. Soc. Music Inf. Retrieval","author":"Landone","year":"2007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262661"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2017438"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2199972"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2375575"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-73003-5_196"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/5254.708428"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690570"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3037534"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414835"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107205"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33709-3_52"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_36"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2783902"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.843346"},{"key":"ref20","first-page":"38","article-title":"Automating the construction of scene classifiers for content-based video retrieval","volume-title":"Proc. Int. Workshop Multimedia Data Mining","author":"Isral","year":"2004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70716"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00157"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-021-1293-0"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415085"},{"key":"ref28","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2023.104676"},{"key":"ref30","first-page":"20371","article-title":"Mavil: Masked audio-video learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Huang","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196629"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1080\/01638539809545028"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10038206"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0026683"},{"issue":"1","key":"ref35","first-page":"41","article-title":"A comparison of event models for naive Bayes text classification","volume-title":"Proc. AAAI Workshop Learn. Text Categorization","volume":"752","author":"McCallum","year":"1998"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"issue":"122","key":"ref37","first-page":"1","article-title":"Visual categorization with bags of keypoints","volume-title":"Proc. Workshop Stat. Learn. Comput. Vis.","volume":"1","author":"Csurka","year":"2004"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2170665"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2015.2513443"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00696"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2051871"},{"key":"ref42","first-page":"6309","article-title":"Neural discrete representation learning","volume":"30","author":"Oord","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref43","article-title":"Vector-quantized image modeling with improved VQGAN","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2022"},{"key":"ref44","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Villegas","year":"2022"},{"key":"ref45","article-title":"Language model beats diffusionTokenizer is key to visual generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-716"},{"key":"ref47","first-page":"89","article-title":"A study on music genre classification based on universal acoustic models","volume-title":"Proc. Int. Soc. Music Inf. Retrieval","author":"Reed","year":"2006"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495617"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2171"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2044"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053519"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3549555.3549568"},{"key":"ref55","first-page":"45","article-title":"Audio-visual scene classification: Analysis of DCASE 2021 challenge submissions","volume-title":"Proc. Detection Classication Acoust. Scenes Events","author":"Wang","year":"2021"},{"key":"ref56","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2019"},{"key":"ref57","first-page":"95","article-title":"A multi-modal fusion approach for audio-visual scene classification enhanced by CLIP variants","volume-title":"Proc. Detection Classication Acoust. Scenes Events","author":"Okazaki","year":"2021"},{"key":"ref58","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":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP55362.2022.9949447"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3260282"},{"article-title":"Scene classification using acoustic and visual feature","year":"2021","author":"Yang","key":"ref61"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.2307\/2346830"},{"key":"ref63","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1980.1094577"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3115\/974358.974371"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/57167.57214"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/505282.505283"},{"volume-title":"Neural Networks: A Comprehensive Foundation","year":"1998","author":"Haykin","key":"ref69"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445941"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"issue":"11","key":"ref76","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"article-title":"Audio-visual scene classification using a transfer learning based joint optimization strategy","year":"2022","author":"Chen","key":"ref79"},{"year":"2023","key":"ref80","article-title":"GPT-4 technical report"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11119327.pdf?arnumber=11119327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T16:07:52Z","timestamp":1759248472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11119327\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3595019","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}