{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T14:09:35Z","timestamp":1753884575981,"version":"3.40.3"},"reference-count":74,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3555297","type":"journal-article","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T23:45:26Z","timestamp":1743464726000},"page":"57241-57254","source":"Crossref","is-referenced-by-count":1,"title":["BS-BGM: Leveraging Vision Language Models and Shot Boundary for Beat-Synced Video Background Music Generation"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7829-0340","authenticated-orcid":false,"given":"Yuji","family":"Sun","sequence":"first","affiliation":[{"name":"School of Arts, Nanchang University, Honggutan, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunbin","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Arts, Nanchang University, Honggutan, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Fusionopolis, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4135\/9781473984066.n29"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2023.1298361"},{"key":"ref3","article-title":"AI-generated content (AIGC): A survey","author":"Wu","year":"2023","journal-title":"arXiv:2304.06632"},{"key":"ref4","article-title":"A comprehensive survey of AI-generated content (AIGC): A history of generative AI from GAN to ChatGPT","author":"Cao","year":"2023","journal-title":"arXiv:2303.04226"},{"key":"ref5","article-title":"Video-to-Audio generation with hidden alignment","author":"Xu","year":"2024","journal-title":"arXiv:2407.07464"},{"key":"ref6","article-title":"Semantically consistent video-to-audio generation using multimodal language large model","author":"Chen","year":"2024","journal-title":"arXiv:2404.16305"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3040797"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3257565"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_11"},{"key":"ref10","article-title":"Discrete contrastive diffusion for cross-modal music and image generation","author":"Zhu","year":"2022","journal-title":"arXiv:2206.07771"},{"key":"ref11","first-page":"40339","article-title":"Long-term rhythmic video soundtracker","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref12","article-title":"Concatenated masked autoencoders as spatial\u2013temporal learner","author":"Jiang","year":"2023","journal-title":"arXiv:2311.00961"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-023-02160-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02582"},{"key":"ref15","article-title":"TransNet v2: An effective deep network architecture for fast shot transition detection","author":"Sou\u010d ek","year":"2020","journal-title":"arXiv:2008.04838"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00218"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref18","first-page":"1","article-title":"DiReCT: Diagnostic reasoning for clinical notes via large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Wang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.655"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1186\/s40494-024-01334-x"},{"key":"ref21","first-page":"1","article-title":"Direct: Diagnostic reasoning for clinical notes via large language models","volume-title":"Proc. 38th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Wang"},{"key":"ref22","first-page":"3778","article-title":"Relayout: Towards real-world document understanding via layout-enhanced pre-training","volume-title":"Proc. 31st Int. Conf. Comput. Linguistics","author":"Jiang"},{"key":"ref23","article-title":"Putting people in LLMs\u2019 shoes: Generating better answers via question rewriter","author":"Chen","year":"2024","journal-title":"arXiv:2408.10573"},{"key":"ref24","first-page":"453","article-title":"LongVLM: Efficient long video understanding via large language models","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Weng"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref26","article-title":"Exploring the frontier of vision-language models: A survey of current methodologies and future directions","author":"Ghosh","year":"2024","journal-title":"arXiv:2404.07214"},{"issue":"5","key":"ref27","first-page":"6","article-title":"Aist dance video database: Multi-genre, multi-dancer, and multi-camera database for dance information processing","volume-title":"Proc. ISMIR","volume":"1","author":"Tsuchida"},{"key":"ref28","article-title":"Enabling factorized piano music modeling and generation with the maestro dataset","author":"Hawthorne","year":"2018","journal-title":"arXiv:1810.12247"},{"key":"ref29","article-title":"POP909: A pop-song dataset for music arrangement generation","author":"Wang","year":"2020","journal-title":"arXiv:2008.07142"},{"key":"ref30","article-title":"Content-based video-music retrieval using soft intra-modal structure constraint","author":"Hong","year":"2017","journal-title":"arXiv:1704.06761"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856090"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01433"},{"issue":"4","key":"ref34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3626235","article-title":"Diffusion models: A comprehensive survey of methods and applications","volume":"56","author":"Yang","year":"2024","journal-title":"ACM Comput. Surveys"},{"key":"ref35","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref37","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref38","first-page":"5775","article-title":"DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2300310"},{"key":"ref40","first-page":"24804","article-title":"CSDI: Conditional score-based diffusion models for probabilistic time series imputation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tashiro"},{"key":"ref41","article-title":"Symbolic music generation with diffusion models","author":"Mittal","year":"2021","journal-title":"arXiv:2103.16091"},{"article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma","key":"ref42"},{"issue":"7553","key":"ref43","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04072-4"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2024.102463","article-title":"Improving facade parsing with vision transformers and line integration","volume":"60","author":"Wang","year":"2024","journal-title":"Adv. Eng. Informat."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01055"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00259"},{"key":"ref48","first-page":"2037","article-title":"Video background music generation with controllable music transformer","volume-title":"Proc. 29th ACM Int. Conf. Multimedia","author":"Di"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3195527"},{"key":"ref50","first-page":"758","article-title":"Foley music: Learning to generate music from videos","volume-title":"Proc. 16th Eur. Conf. Comput. Vis.","author":"Gan"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3276480"},{"key":"ref52","first-page":"1","article-title":"Diff-foley: Synchronized video-to-audio synthesis with latent diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Luo"},{"key":"ref53","article-title":"Polyffusion: A diffusion model for polyphonic score generation with internal and external controls","author":"Min","year":"2023","journal-title":"arXiv:2307.10304"},{"key":"ref54","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023","journal-title":"arXiv:2301.11325"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"volume-title":"Riffusion-stable Diffusion for Real-time Music Generation","year":"2022","author":"Forsgren","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref58","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref59","article-title":"Video-xl: Extra-long vision language model for hour-scale video understanding","author":"Shu","year":"2024","journal-title":"arXiv:2409.14485"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref61","first-page":"11218","article-title":"TransNet v2: An effective deep network architecture for fast shot transition detection","volume-title":"Proc. 32nd ACM Int. Conf. Multimedia","author":"Soucek"},{"key":"ref62","article-title":"The jazz transformer on the front line: Exploring the shortcomings of AI-composed music through quantitative measures","author":"Wu","year":"2020","journal-title":"arXiv:2008.01307"},{"volume-title":"This is Your Brain on Music: Understanding a Human Obsession","year":"2006","author":"Levitin","key":"ref63"},{"key":"ref64","article-title":"Musicnn: Pre-trained convolutional neural networks for music audio tagging","author":"Pons","year":"2019","journal-title":"arXiv:1909.06654"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016"},{"key":"ref66","article-title":"DiffWave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020","journal-title":"arXiv:2009. 09761"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1461"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"issue":"5","key":"ref69","first-page":"507","article-title":"Meshless local petrov-Galerkin (MLPG) approaches for solving the weakly-singular traction & displacement boundary integral equations","volume":"4","author":"Atluri","year":"2003","journal-title":"Comput. Model. Eng. Sci."},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s004660050346"},{"key":"ref71","volume-title":"The Meshless Method (MLPG) for Domain & BIE Discretiza","volume":"677","author":"Atluri","year":"2004"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2013.03.119"},{"key":"ref73","article-title":"A survey of large language models","author":"Xin Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3390182"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10945856.pdf?arnumber=10945856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T04:16:44Z","timestamp":1743913004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10945856\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3555297","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}