{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:55Z","timestamp":1750309495791,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62327808,62088102"],"award-info":[{"award-number":["62327808,62088102"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2020AAA0108102"],"award-info":[{"award-number":["2020AAA0108102"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681389","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"9244-9252","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-grained Correspondence Learning of Audio-language Models for Few-shot Audio Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3882-7959","authenticated-orcid":false,"given":"Shengwei","family":"Zhao","sequence":"first","affiliation":[{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7785-6913","authenticated-orcid":false,"given":"Linhai","family":"Xu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7295-3308","authenticated-orcid":false,"given":"Yuying","family":"Liu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7092-0596","authenticated-orcid":false,"given":"Shaoyi","family":"Du","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Plot: Prompt learning with optimal transport for vision-language models. arXiv preprint arXiv:2210.01253","author":"Chen Guangyi","year":"2022","unstructured":"Guangyi Chen, Weiran Yao, Xiangchen Song, Xinyue Li, Yongming Rao, and Kun Zhang. 2022. Plot: Prompt learning with optimal transport for vision-language models. arXiv preprint arXiv:2210.01253 (2022)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"e_1_3_2_2_3_1","volume-title":"Beats: Audio pre-training with acoustic tokenizers. arXiv preprint arXiv:2212.09058","author":"Chen Sanyuan","year":"2022","unstructured":"Sanyuan Chen, Yu Wu, Chengyi Wang, Shujie Liu, Daniel Tompkins, Zhuo Chen, and Furu Wei. 2022. Beats: Audio pre-training with acoustic tokenizers. arXiv preprint arXiv:2212.09058 (2022)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682558"},{"key":"e_1_3_2_2_6_1","volume-title":"Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems","author":"Cuturi Marco","year":"2013","unstructured":"Marco Cuturi. 2013. Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_2_7_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_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.513"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"e_1_3_2_2_11_1","volume-title":"Natural language supervision for general-purpose audio representations. arXiv preprint arXiv:2309.05767","author":"Elizalde Benjamin","year":"2023","unstructured":"Benjamin Elizalde, Soham Deshmukh, and Huaming Wang. 2023. Natural language supervision for general-purpose audio representations. arXiv preprint arXiv:2309.05767 (2023)."},{"key":"e_1_3_2_2_12_1","volume-title":"Xavier Favory, Jordi Pons, and Xavier Serra.","author":"Fonseca Eduardo","year":"2018","unstructured":"Eduardo Fonseca, Manoj Plakal, Frederic Font, Daniel PW Ellis, Xavier Favory, Jordi Pons, and Xavier Serra. 2018. General-purpose tagging of freesound audio with audioset labels: Task description, dataset, and baseline. arXiv preprint arXiv:1807.09902 (2018)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"e_1_3_2_2_14_1","volume-title":"Ast: Audio spectrogram transformer. arXiv preprint arXiv:2104.01778","author":"Gong Yuan","year":"2021","unstructured":"Yuan Gong, Yu-An Chung, and James Glass. 2021. Ast: Audio spectrogram transformer. arXiv preprint arXiv:2104.01778 (2021)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15919-0_19"},{"key":"e_1_3_2_2_17_1","volume-title":"MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In (Variant) Representations. arXiv preprint arXiv:2305.17191","author":"Heggan Calum","year":"2023","unstructured":"Calum Heggan, Tim Hospedales, Sam Budgett, and Mehrdad Yaghoobi. 2023. MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In (Variant) Representations. arXiv preprint arXiv:2305.17191 (2023)."},{"key":"e_1_3_2_2_18_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_2_19_1","volume-title":"International conference on machine learning. PMLR, 5583--5594","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. Vilt: Vision-and-language transformer without convolution or region supervision. In International conference on machine learning. PMLR, 5583--5594."},{"key":"e_1_3_2_2_20_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_21_1","volume-title":"International conference on machine learning. PMLR, 957--966","author":"Kusner Matt","year":"2015","unstructured":"Matt Kusner, Yu Sun, Nicholas Kolkin, and Kilian Weinberger. 2015. From word embeddings to document distances. In International conference on machine learning. PMLR, 957--966."},{"key":"e_1_3_2_2_22_1","volume-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461","author":"Lewis Mike","year":"2019","unstructured":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)."},{"key":"e_1_3_2_2_23_1","volume-title":"Few-shot Class-incremental Audio Classification Using Stochastic Classifier. arXiv preprint arXiv:2306.02053","author":"Li Yanxiong","year":"2023","unstructured":"Yanxiong Li, Wenchang Cao, Jialong Li, Wei Xie, and Qianhua He. 2023. Few-shot Class-incremental Audio Classification Using Stochastic Classifier. arXiv preprint arXiv:2306.02053 (2023)."},{"key":"e_1_3_2_2_24_1","volume-title":"Adapting Language-Audio Models as Few-Shot Audio Learners. arXiv preprint arXiv:2305.17719","author":"Liang Jinhua","year":"2023","unstructured":"Jinhua Liang, Xubo Liu, Haohe Liu, Huy Phan, Emmanouil Benetos, Mark D Plumbley, and Wenwu Wang. 2023. Adapting Language-Audio Models as Few-Shot Audio Learners. arXiv preprint arXiv:2305.17719 (2023)."},{"key":"e_1_3_2_2_25_1","volume-title":"Multi-granularity correspondence learning from long-term noisy videos. arXiv preprint arXiv:2401.16702","author":"Lin Yijie","year":"2024","unstructured":"Yijie Lin, Jie Zhang, Zhenyu Huang, Jia Liu, Zujie Wen, and Xi Peng. 2024. Multi-granularity correspondence learning from long-term noisy videos. arXiv preprint arXiv:2401.16702 (2024)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17045"},{"key":"e_1_3_2_2_27_1","volume-title":"CAT: Causal Audio Transformer for Audio Classification. In ICASSP 2023--2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1--5.","author":"Liu Xiaoyu","year":"2023","unstructured":"Xiaoyu Liu, Hanlin Lu, Jianbo Yuan, and Xinyu Li. 2023. CAT: Causal Audio Transformer for Audio Classification. In ICASSP 2023--2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1--5."},{"key":"e_1_3_2_2_28_1","volume-title":"Wavcaps: A chatgpt-assisted weakly-labelled audio captioning dataset for audio-language multimodal research. arXiv preprint arXiv:2303.17395","author":"Mei Xinhao","year":"2023","unstructured":"Xinhao Mei, Chutong Meng, Haohe Liu, Qiuqiang Kong, Tom Ko, Chengqi Zhao, Mark D Plumbley, Yuexian Zou, and Wenwu Wang. 2023. Wavcaps: A chatgpt-assisted weakly-labelled audio captioning dataset for audio-language multimodal research. arXiv preprint arXiv:2303.17395 (2023)."},{"key":"e_1_3_2_2_29_1","unstructured":"Gaspard Monge. 1781. M\u00e9moire sur la th\u00e9orie des d\u00e9blais et des remblais. Mem. Math. Phys. Acad. Royale Sci. ( 1781) 666--704."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"e_1_3_2_2_31_1","volume-title":"Volta: Vision-language transformer with weakly-supervised local-feature alignment. arXiv preprint arXiv:2210.04135","author":"Pramanick Shraman","year":"2022","unstructured":"Shraman Pramanick, Li Jing, Sayan Nag, Jiachen Zhu, Hardik Shah, Yann LeCun, and Rama Chellappa. 2022. Volta: Vision-language transformer with weakly-supervised local-feature alignment. arXiv preprint arXiv:2210.04135 (2022)."},{"key":"e_1_3_2_2_32_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_33_1","volume-title":"Prototypical networks for few-shot learning. Advances in neural information processing systems","author":"Snell Jake","year":"2017","unstructured":"Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612403"},{"key":"e_1_3_2_2_35_1","unstructured":"Oriol Vinyals Charles Blundell Timothy Lillicrap Daan Wierstra et al. 2016. Matching networks for one shot learning. Advances in neural information processing systems Vol. 29 (2016)."},{"key":"e_1_3_2_2_36_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Dongsheng","year":"2024","unstructured":"Dongsheng Wang, Miaoge Li, Xinyang Liu, MingSheng Xu, Bo Chen, and Hanwang Zhang. 2024. Tuning Multi-mode Token-level Prompt Alignment across Modalities. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632677"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"e_1_3_2_2_39_1","first-page":"4514","article-title":"Probing inter-modality: Visual parsing with self-attention for vision-and-language pre-training","volume":"34","author":"Xue Hongwei","year":"2021","unstructured":"Hongwei Xue, Yupan Huang, Bei Liu, Houwen Peng, Jianlong Fu, Houqiang Li, and Jiebo Luo. 2021. Probing inter-modality: Visual parsing with self-attention for vision-and-language pre-training. Advances in Neural Information Processing Systems, Vol. 34 (2021), 4514--4528.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_40_1","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics. 2363--2373","author":"Yu Weijie","year":"2022","unstructured":"Weijie Yu, Liang Pang, Jun Xu, Bing Su, Zhenhua Dong, and Ji-Rong Wen. 2022. Optimal partial transport based sentence selection for long-form document matching. In Proceedings of the 29th International Conference on Computational Linguistics. 2363--2373."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01222"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592025"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00974"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681389","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681389","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:44Z","timestamp":1750295864000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681389"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":46,"alternative-id":["10.1145\/3664647.3681389","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681389","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}