{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T05:27:04Z","timestamp":1738128424648,"version":"3.33.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,8]]},"DOI":"10.1109\/vcip63160.2024.10849886","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:36:57Z","timestamp":1738003017000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["MVBind: Self-Supervised Music Recommendation for Videos via Embedding Space Binding"],"prefix":"10.1109","author":[{"given":"Jiajie","family":"Teng","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,China"}]},{"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}]},{"given":"Yucheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}]},{"given":"Sijing","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}]},{"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Neural Information Processing Systems (NeurIPS)","volume":"33","author":"Baevski"},{"article-title":"Codified audio language modeling learns useful representations for music information retrieval","year":"2021","author":"Castellon","key":"ref2"},{"key":"ref3","first-page":"3965","article-title":"Coatnet: Marrying convolution and attention for all data sizes","volume-title":"Neural Information Processing Systems (NeurIPS)","volume":"34","author":"Dai"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref4"},{"issue":"3s","key":"ref5","first-page":"1","article-title":"Visual attention analysis and prediction on human faces for children with autism spectrum disorder","volume":"15","author":"Duan","year":"2019","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3250956"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3220404"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3172882"},{"key":"ref9","first-page":"6549","article-title":"Saliency in augmented reality","volume-title":"Proceedings of ACM International Conference on Multimedia (ACM MM)","author":"Duan"},{"article-title":"Masked autoencoders as image processors","year":"2023","author":"Duan","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/OJID.2024.3351089"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190831"},{"issue":"4","key":"ref14","doi-asserted-by":"crossref","first-page":"1311","DOI":"10.1007\/s00521-020-05017-z","article-title":"A novel content-based image retrieval approach for classification using glcm features and texture fused lbp variants","volume":"33","author":"Garg","year":"2021","journal-title":"Neural Computing and Applications"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1016\/j.procs.2015.04.038","article-title":"Analysis and design of selenium webdriver automation testing framework","volume":"50","author":"Gojare","year":"2015","journal-title":"Procedia Computer Science"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206046"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00369"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4133-3"},{"article-title":"Voice recognition algorithms using mel frequency cepstral coefficient (mfcc) and dynamic time warping (dtw) techniques","year":"2010","author":"Muda","key":"ref25"},{"issue":"285-296","key":"ref26","first-page":"23","article-title":"A threshold selection method from gray-level histograms","volume":"11","author":"Otsu","year":"1975","journal-title":"Automatica"},{"article-title":"musicnn: Pre-trained convolutional neural networks for music audio tagging","year":"2019","author":"Pons","key":"ref27"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning. Proceedings of Machine Learning Research(PMLR)","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS46773.2023.10182000"},{"key":"ref31","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International Conference on machine learning. Proceedings of Machine Learning Research(PMLR)","author":"Tan"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00224"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-9119-8_5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/icip51287.2024.10647885"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1007\/s11265-019-01508-y","article-title":"Research on image retrieval algorithm based on combination of color and shape features","volume":"93","author":"Zenggang","year":"2021","journal-title":"Journal of signal processing systems"},{"key":"ref37","first-page":"512","article-title":"Perceptual quality assessment of omnidirectional audio-visual signals","volume-title":"CAAI International Conference on Artificial Intelligence","author":"Zhu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-46317-4_29"}],"event":{"name":"2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)","start":{"date-parts":[[2024,12,8]]},"location":"Tokyo, Japan","end":{"date-parts":[[2024,12,11]]}},"container-title":["2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10849624\/10849781\/10849886.pdf?arnumber=10849886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:08:50Z","timestamp":1738044530000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849886\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/vcip63160.2024.10849886","relation":{},"subject":[],"published":{"date-parts":[[2024,12,8]]}}}