{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:47:51Z","timestamp":1755802071321,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","funder":[{"name":"National Institute of Informatics, Research Organization of Information and Systems","award":["24FS03"],"award-info":[{"award-number":["24FS03"]}]},{"DOI":"10.13039\/501100006374","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["23K11231"],"award-info":[{"award-number":["23K11231"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733488","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:04Z","timestamp":1750876264000},"page":"2013-2017","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Contrastive Learning for Music with Incomplete Modalities"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7682-9336","authenticated-orcid":false,"given":"Koto","family":"Nakata","sequence":"first","affiliation":[{"name":"Hiroshima University, Higashi-Hiroshima City, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6743-2972","authenticated-orcid":false,"given":"Koji","family":"Eguchi","sequence":"additional","affiliation":[{"name":"Hiroshima University, Higashi-Hiroshima City, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Ke Chen Xingjian Du Bilei Zhu Zejun Ma Taylor Berg-Kirkpatrick and Shlomo Dubnov. 2022. Hts-at: a hierarchical token-semantic audio transformer for sound classification and detection. (2022). https:\/\/arxiv.org\/abs\/2202.00874 arXiv: 2202.00874 [cs.SD].","DOI":"10.31219\/osf.io\/d264y"},{"key":"e_1_3_2_1_2_1","unstructured":"Yi-Hui Chou I-Chun Chen Chin-Jui Chang Joann Ching and Yi-Hsuan Yang. 2024. Bert-like pre-training for symbolic piano music classification tasks. (2024). https:\/\/arxiv.org\/abs\/2107.05223 arXiv: 2107.05223 [cs.SD]."},{"key":"e_1_3_2_1_3_1","volume-title":"Bert: pre-training of deep bidirectional transformers for language understanding. (2019). https:\/\/arxiv.org\/abs\/1810.04805 arXiv","author":"Devlin Jacob","year":"1810","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: pre-training of deep bidirectional transformers for language understanding. (2019). https:\/\/arxiv.org\/abs\/1810.04805 arXiv: 1810.04805 [cs.CL]."},{"key":"e_1_3_2_1_4_1","volume-title":"Judith Yue Li, and Daniel P. W. Ellis","author":"Huang Qingqing","year":"2022","unstructured":"Qingqing Huang, Aren Jansen, Joonseok Lee, Ravi Ganti, Judith Yue Li, and Daniel P. W. Ellis. 2022. Mulan: a joint embedding of music audio and natural language. (2022). https:\/\/arxiv.org\/abs\/2208.12415 [eess.AS]"},{"key":"e_1_3_2_1_5_1","volume-title":"Plumbley","author":"Kong Qiuqiang","year":"2020","unstructured":"Qiuqiang Kong, Yin Cao, Turab Iqbal, Yuxuan Wang, Wenwu Wang, and Mark D. Plumbley. 2020. Panns: large-scale pretrained audio neural networks for audio pattern recognition. (2020). https:\/\/arxiv.org\/abs\/1912.10211 arXiv:1912.10211 [cs.SD]."},{"key":"e_1_3_2_1_6_1","unstructured":"Yinhan Liu et al. 2019. Roberta: a robustly optimized bert pretraining approach. (2019). https:\/\/arxiv.org\/abs\/1907.11692 arXiv: 1907.11692 [cs.CL]."},{"key":"e_1_3_2_1_7_1","unstructured":"Ilaria Manco Emmanouil Benetos Elio Quinton and Gy\u00f6rgy Fazekas. 2022. Contrastive audio-language learning for music. (2022). https:\/\/arxiv.org\/abs\/2208.12208 arXiv: 2208.12208 [cs.SD]."},{"key":"e_1_3_2_1_8_1","unstructured":"Jan Melechovsky Abhinaba Roy and Dorien Herremans. 2024. Midicaps: a large-scale midi dataset with text captions. (2024). https:\/\/arxiv.org\/abs\/2406.02255 arXiv: 2406.02255 [eess.AS]."},{"key":"e_1_3_2_1_9_1","unstructured":"Alec Radford et al. 2021. Learning transferable visual models from natural language supervision. (2021). https:\/\/arxiv.org\/abs\/2103.00020 arXiv: 2103.00020 [cs.CV]."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.12.003"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: sentence embeddings using siamese bert-networks. (2019). https:\/\/arxiv.org\/abs\/1908.10084 arXiv:1908.10084 [cs.CL].","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022. High-resolution image synthesis with latent diffusion models. (2022). https:\/\/arxiv.org\/abs\/2112.10752 arXiv: 2112.10752 [cs.CV].","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_13_1","unstructured":"Zineng Tang Ziyi Yang Chenguang Zhu Michael Zeng and Mohit Bansal. 2023. Any-to-any generation via composable diffusion. (2023). https:\/\/arxiv.org\/abs\/2305.11846 arXiv: 2305.11846 [cs.CV]."},{"key":"e_1_3_2_1_14_1","unstructured":"Zehan Wang et al. 2023. Connecting multi-modal contrastive representations. (2023). https:\/\/arxiv.org\/abs\/2305.14381 arXiv: 2305.14381 [cs.LG]."},{"key":"e_1_3_2_1_15_1","unstructured":"Shangda Wu Dingyao Yu Xu Tan and Maosong Sun. 2023. Clamp: contrastive language-music pre-training for cross-modal symbolic music information retrieval. (2023). https:\/\/arxiv.org\/abs\/2304.11029 arXiv: 2304.11029 [cs.SD]."},{"key":"e_1_3_2_1_16_1","unstructured":"Yusong Wu Ke Chen Tianyu Zhang Yuchen Hui Marianna Nezhurina Taylor Berg-Kirkpatrick and Shlomo Dubnov. 2024. Large-scale contrastive language audio pretraining with feature fusion and keyword-to-caption augmentation. (2024). https:\/\/arxiv.org\/abs\/2211.06687 arXiv: 2211.06687 [cs.SD]."},{"key":"e_1_3_2_1_17_1","volume-title":"Juan Carlos Niebles, and Silvio Savarese","author":"Xue Le","year":"2023","unstructured":"Le Xue, Mingfei Gao, Chen Xing, Roberto Mart\u00edn-Mart\u00edn, Jiajun Wu, Caiming Xiong, Ran Xu, Juan Carlos Niebles, and Silvio Savarese. 2023. Ulip: learning a unified representation of language, images, and point clouds for 3d understanding. (2023). https:\/\/arxiv.org\/abs\/2212.05171 arXiv: 2212.05171 [cs.CV]."},{"key":"e_1_3_2_1_18_1","unstructured":"Mingliang Zeng Xu Tan Rui Wang Zeqian Ju Tao Qin and Tie-Yan Liu. 2021. Musicbert: symbolic music understanding with large-scale pre-training. (2021). https:\/\/arxiv.org\/abs\/2106.05630 arXiv: 2106.05630 [cs.SD]."}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Chicago IL USA","acronym":"ICMR '25"},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733488","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:06:03Z","timestamp":1755749163000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733488"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":18,"alternative-id":["10.1145\/3731715.3733488","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733488","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}