{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T22:11:37Z","timestamp":1769033497971,"version":"3.49.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002428","name":"Austrian Science Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002428","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/cbmi66578.2025.11339285","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:38:56Z","timestamp":1768941536000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Music4All A+A: A Multimodal Dataset for Music Information Retrieval Tasks"],"prefix":"10.1109","author":[{"given":"Jonas","family":"Geiger","sequence":"first","affiliation":[{"name":"Johannes Kepler University,Linz,Austria"}]},{"given":"Marta","family":"Moscati","sequence":"additional","affiliation":[{"name":"Johannes Kepler University,Linz,Austria"}]},{"given":"Shah","family":"Nawaz","sequence":"additional","affiliation":[{"name":"Johannes Kepler University,Linz,Austria"}]},{"given":"Markus","family":"Schedl","sequence":"additional","affiliation":[{"name":"Johannes Kepler University,Linz,Austria"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref3","first-page":"583","article-title":"Music genre classification: a multilinear approach","volume-title":"International Symposium Music Information Retrieval","author":"Panagakis"},{"key":"ref4","article-title":"Automatic music tag classification based on block-level features","volume-title":"Proc. of SMC","author":"Seyerlehner","year":"2010"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref6","first-page":"622","article-title":"Clap: Contrastive language-audio pre-training model for multi-modal sentiment analysis","volume-title":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval, ser. ICMR \u201823.","author":"Zhao"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref8","article-title":"Mulan: A joint embedding of music audio and natural language","volume-title":"Proceedings of the the 23rd International Society for Music Information Retrieval Conference (ISMIR)","author":"Huang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149712"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2024.100618"},{"key":"ref11","first-page":"23","article-title":"Multi-label music genre classification from audio, text and images using deep features","volume-title":"Proceedings of the 18th International Society for Music Information Retrieval Conference, ISMIR 2017","author":"Oramas"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3536026"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557656"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-4666-3646-0.ch004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-12093-5_2"},{"key":"ref17","author":"Marchand","year":"2016","journal-title":"The extended ballroom dataset"},{"key":"ref18","article-title":"Judging a book by its cover","author":"Iwana","year":"2016","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-14560-5"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervi-sion","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event","volume":"139","author":"Radford"},{"key":"ref21","article-title":"Supervised multimodal bitransformers for classifying images and text","volume-title":"Visually Grounded Interaction and Language (ViGIL), NeurIPS 2019 Workshop","author":"Kiela"},{"key":"ref22","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"139","author":"Kim"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097207"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00713"},{"key":"ref25","first-page":"0","article-title":"Centralnet: a multi-layer approach for multimodal fusion","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops","author":"Vielzeuf"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"4439","DOI":"10.18653\/v1\/2021.findings-emnlp.379","article-title":"MOMENTA: A multimodal framework for detecting harmful memes and their targets","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2021","author":"Pramanick","year":"2021"},{"key":"ref27","first-page":"4585","article-title":"Capalign: Improving cross modal alignment via informative captioning for harmful meme detection","volume-title":"Proceedings of the ACM Web Conference 2024, ser. WWW \u201924","author":"Ji"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01764"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-025-00370-y"}],"event":{"name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","location":"Dublin, Ireland","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 International Conference on Content-Based Multimedia Indexing (CBMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11339229\/11339242\/11339285.pdf?arnumber=11339285","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:15:22Z","timestamp":1768979722000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339285\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/cbmi66578.2025.11339285","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}