{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T17:49:54Z","timestamp":1773942594197,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","funder":[{"name":"Institute of Information & communications Technology Planning & Evaluation (IITP)","award":["RS-2022-II220320"],"award-info":[{"award-number":["RS-2022-II220320"]}]},{"DOI":"10.13039\/501100006374","name":"Seoul National University","doi-asserted-by":"publisher","award":["RS-2021-II211343"],"award-info":[{"award-number":["RS-2021-II211343"]}],"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":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730261","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:25:28Z","timestamp":1752456328000},"page":"3085-3089","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Understanding Audio-Text Retrieval Through Singular Value Decomposition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2557-0934","authenticated-orcid":false,"given":"Yoori","family":"Oh","sequence":"first","affiliation":[{"name":"Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0382-7826","authenticated-orcid":false,"given":"Yoseob","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Soongsil University, Seoul, Republic of Korea and Department of Intelligent Semiconductors, Soongsil University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5417-7968","authenticated-orcid":false,"given":"Joonhyeon","family":"Bae","sequence":"additional","affiliation":[{"name":"IPAI, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3609-4259","authenticated-orcid":false,"given":"Jaeheon","family":"Sim","sequence":"additional","affiliation":[{"name":"IPAI, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4210-0312","authenticated-orcid":false,"given":"Kyogu","family":"Lee","sequence":"additional","affiliation":[{"name":"IPAI, Seoul National University, Seoul, Republic of Korea, Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea, and AI Institute, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv","author":"Alexey Dosovitskiy","year":"2010","unstructured":"Dosovitskiy Alexey. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv: 2010.11929 (2020)."},{"key":"e_1_3_2_1_2_1","unstructured":"Sanyuan Chen Yu Wu Chengyi Wang Shujie Liu Daniel Tompkins Zhuo Chen and Furu Wei. 2022. BEATs: Audio Pre-Training with Acoustic Tokenizers. (2022). arxiv: 2212.09058"},{"key":"e_1_3_2_1_3_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Kim Chris Dongjoo","year":"2019","unstructured":"Chris Dongjoo Kim, Byeongchang Kim, Hyunmin Lee, and Gunhee Kim. 2019. Audiocaps: Generating captions for audios in the wild. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 119-132."},{"key":"e_1_3_2_1_7_1","volume-title":"Audio retrieval with natural language queries: A benchmark study","author":"Koepke A Sophia","year":"2022","unstructured":"A Sophia Koepke, Andreea-Maria Oncescu, Joao Henriques, Zeynep Akata, and Samuel Albanie. 2022. Audio retrieval with natural language queries: A benchmark study. IEEE Transactions on Multimedia (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In ICML.","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In ICML."},{"key":"e_1_3_2_1_9_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems, Vol. 34 (2021), 9694-9705."},{"key":"e_1_3_2_1_10_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746786"},{"key":"e_1_3_2_1_12_1","volume-title":"On metric learning for audio-text cross-modal retrieval. arXiv preprint arXiv:2203.15537","author":"Mei Xinhao","year":"2022","unstructured":"Xinhao Mei, Xubo Liu, Jianyuan Sun, Mark D Plumbley, and Wenwu Wang. 2022. On metric learning for audio-text cross-modal retrieval. arXiv preprint arXiv:2203.15537 (2022)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657976"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"e_1_3_2_1_15_1","volume-title":"On Negative Sampling for Contrastive Audio-Text Retrieval. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1-5.","author":"Xie Huang","year":"2023","unstructured":"Huang Xie, Okko R\u00e4s\u00e4nen, and Tuomas Virtanen. 2023. On Negative Sampling for Contrastive Audio-Text Retrieval. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1-5."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096972"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592025"}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730261","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:15:09Z","timestamp":1755864909000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730261"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":17,"alternative-id":["10.1145\/3726302.3730261","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730261","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}