{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:10:23Z","timestamp":1765339823913,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755288","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:51Z","timestamp":1761377211000},"page":"8106-8115","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Text as Any-Modality for Zero-Shot Classification by Consistent Prompt Tuning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5689-3818","authenticated-orcid":false,"given":"Xiangyu","family":"Wu","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6097-4556","authenticated-orcid":false,"given":"Feng","family":"Yu","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5245-3584","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9190-507X","authenticated-orcid":false,"given":"Jianfeng","family":"Lu","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"120496","article-title":"MFFCG-Multi feature fusion for hyperspectral image classification using graph attention network","volume":"229","author":"Bhatti Uzair Aslam","year":"2023","unstructured":"Uzair Aslam Bhatti, Mengxing Huang, Harold Neira-Molina, Shah Marjan, Mehmood Baryalai, Hao Tang, Guilu Wu, and Sibghat Ullah Bazai. 2023. MFFCG-Multi feature fusion for hyperspectral image classification using graph attention network. ESWA, Vol. 229 (2023), 120496.","journal-title":"ESWA"},{"key":"e_1_3_2_1_2_1","first-page":"646","article-title":"HTS-AT","author":"Chen Ke","year":"2022","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. In ICASSP. 646-650.","journal-title":"In ICASSP."},{"key":"e_1_3_2_1_3_1","first-page":"2818","article-title":"Reproducible scaling laws for contrastive language-image learning","author":"Cherti Mehdi","year":"2023","unstructured":"Mehdi Cherti, Romain Beaumont, Ross Wightman, Mitchell Wortsman, Gabriel Ilharco, Cade Gordon, Christoph Schuhmann, Ludwig Schmidt, and Jenia Jitsev. 2023. Reproducible scaling laws for contrastive language-image learning. In CVPR. 2818-2829.","journal-title":"CVPR."},{"key":"e_1_3_2_1_4_1","first-page":"4171","article-title":"BERT","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL. 4171-4186.","journal-title":"Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL."},{"key":"e_1_3_2_1_5_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR."},{"key":"e_1_3_2_1_6_1","volume-title":"NeurIPS","volume":"36","author":"Duan Haoyi","year":"2024","unstructured":"Haoyi Duan, Yan Xia, Zhou Mingze, Li Tang, Jieming Zhu, and Zhou Zhao. 2024. Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks. NeurIPS, Vol. 36 (2024)."},{"key":"e_1_3_2_1_7_1","first-page":"200","article-title":"X3D","author":"Feichtenhofer Christoph","year":"2020","unstructured":"Christoph Feichtenhofer. 2020. X3D: Expanding Architectures for Efficient Video Recognition. In CVPR. 200-210.","journal-title":"Expanding Architectures for Efficient Video Recognition. In CVPR."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29097"},{"key":"e_1_3_2_1_9_1","first-page":"12356","author":"Garg Shefali","year":"2024","unstructured":"Shefali Garg, Zhouyuan Huo, Khe Chai Sim, Suzan Schwartz, Mason Chua, Al\u00ebna Aks\u00ebnova, Tsendsuren Munkhdalai, Levi King, Darryl Wright, Zion Mengesha, et al., 2024. Improving Speech Recognition for African American English with Audio Classification. In ICASSP. 12356-12360.","journal-title":"In ICASSP."},{"key":"e_1_3_2_1_10_1","volume-title":"Glass","author":"Gong Yuan","year":"2021","unstructured":"Yuan Gong, Yu-An Chung, and James R. Glass. 2021. AST: Audio Spectrogram Transformer. In ISCA. 571-575."},{"key":"e_1_3_2_1_11_1","first-page":"2808","article-title":"Texts as Images in Prompt Tuning for Multi-Label Image Recognition","author":"Guo Zixian","year":"2023","unstructured":"Zixian Guo, Bowen Dong, Zhilong Ji, Jinfeng Bai, Yiwen Guo, and Wangmeng Zuo. 2023. Texts as Images in Prompt Tuning for Multi-Label Image Recognition. In CVPR. 2808-2817.","journal-title":"CVPR."},{"key":"e_1_3_2_1_12_1","volume-title":"Unsupervised learning of sparse features for scalable audio classification. ISMIR (Jan","author":"Henaff Mikael","year":"2011","unstructured":"Mikael Henaff, Kevin Jarrett, Koray Kavukcuoglu, and Yann LeCun. 2011. Unsupervised learning of sparse features for scalable audio classification. ISMIR (Jan 2011)."},{"key":"e_1_3_2_1_13_1","volume-title":"Dualcoop: Fast and effective adaptation to multi-label recognition with limited annotations. TPAMI","author":"Hu Ping","year":"2023","unstructured":"Ping Hu, Ximeng Sun, Stan Sclaroff, and Kate Saenko. 2023. Dualcoop: Fast and effective adaptation to multi-label recognition with limited annotations. TPAMI (2023)."},{"key":"e_1_3_2_1_14_1","first-page":"527","volume-title":"ACML","volume":"260","author":"Huang Longfei","year":"2024","unstructured":"Longfei Huang, Xiangyu Wu, Jingyuan Wang, Weili Guo, and Yang Yang. 2024. Refining Visual Perception for Decoration Display: A Self-Enhanced Deep Captioning Model. In ACML, Vol. 260. 527-542."},{"key":"e_1_3_2_1_15_1","first-page":"266","article-title":"A multimodal prototypical approach for unsupervised sound classification","author":"Kushwaha Saksham Singh","year":"2023","unstructured":"Saksham Singh Kushwaha and Magdalena Fuentes. 2023. A multimodal prototypical approach for unsupervised sound classification. In INTERSPEECH. 266-270.","journal-title":"INTERSPEECH."},{"key":"e_1_3_2_1_16_1","first-page":"31895","article-title":"Compressed Video Prompt Tuning","volume":"36","author":"Li Bing","year":"2023","unstructured":"Bing Li, Jiaxin Chen, Xiuguo Bao, and Di Huang. 2023a. Compressed Video Prompt Tuning. NeurIPS, Vol. 36 (2023), 31895-31907.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_17_1","first-page":"0","volume-title":"ICML","volume":"202","author":"Li Junnan","year":"1973","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven C. H. Hoi. 2023c. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In ICML, Vol. 202. 19730-19742."},{"key":"e_1_3_2_1_18_1","unstructured":"Kunchang Li Yali Wang Yinan He Yizhuo Li Yi Wang Limin Wang and Yu Qiao. 2022. UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer. In ICCV."},{"key":"e_1_3_2_1_19_1","first-page":"19891","article-title":"Unmasked Teacher","author":"Li Kunchang","year":"2023","unstructured":"Kunchang Li, Yali Wang, Yizhuo Li, Yi Wang, Yinan He, Limin Wang, and Yu Qiao. 2023d. Unmasked Teacher: Towards Training-Efficient Video Foundation Models. In ICCV. 19891-19903.","journal-title":"Towards Training-Efficient Video Foundation Models. In ICCV."},{"key":"e_1_3_2_1_20_1","first-page":"23119","article-title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","author":"Li Linjie","year":"2023","unstructured":"Linjie Li, Zhe Gan, Kevin Lin, Chung-Ching Lin, Zicheng Liu, Ce Liu, and Lijuan Wang. 2023b. LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling. In CVPR. 23119-23129.","journal-title":"CVPR."},{"key":"e_1_3_2_1_21_1","first-page":"491","article-title":"Audio-Free Prompt Tuning for Language-Audio Models","author":"Li Yiming","year":"2024","unstructured":"Yiming Li, Xiangdong Wang, and Hong Liu. 2024. Audio-Free Prompt Tuning for Language-Audio Models. In ICASSP. 491-495.","journal-title":"ICASSP."},{"key":"e_1_3_2_1_22_1","first-page":"740","article-title":"Microsoft COCO: Common Objects in Context","volume":"8693","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge J. Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. In ECCV, Vol. 8693. 740-755.","journal-title":"ECCV"},{"key":"e_1_3_2_1_23_1","first-page":"1","article-title":"Cat: causal audio transformer for audio classification","author":"Liu Xiaoyu","year":"2023","unstructured":"Xiaoyu Liu, Hanlin Lu, Jianbo Yuan, and Xinyu Li. 2023b. Cat: causal audio transformer for audio classification. In ICASSP. 1-5.","journal-title":"ICASSP."},{"key":"e_1_3_2_1_24_1","first-page":"1446","article-title":"Audio Prompt Tuning for Universal Sound Separation","author":"Liu Yuzhuo","year":"2024","unstructured":"Yuzhuo Liu, Xubo Liu, Yan Zhao, Yuanyuan Wang, Rui Xia, Pingchuan Tain, and Yuxuan Wang. 2024. Audio Prompt Tuning for Universal Sound Separation. In ICASSP. 1446-1450.","journal-title":"ICASSP."},{"key":"e_1_3_2_1_25_1","unstructured":"Yongcheng Liu Lu Sheng Jing Shao Junjie Yan Shiming Xiang and Chunhong Pan. 2018. Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection. In ACM MM."},{"key":"e_1_3_2_1_26_1","volume-title":"Towards unbiased multi-label zero-shot learning with pyramid and semantic attention. TMM","author":"Liu Ziming","year":"2022","unstructured":"Ziming Liu, Song Guo, Jingcai Guo, Yuanyuan Xu, and Fushuo Huo. 2022a. Towards unbiased multi-label zero-shot learning with pyramid and semantic attention. TMM (2022)."},{"key":"e_1_3_2_1_27_1","first-page":"23859","article-title":"(mathrmML)^2 P-Encoder","author":"Liu Ziming","year":"2023","unstructured":"Ziming Liu, Song Guo, Xiaocheng Lu, Jingcai Guo, Jiewei Zhang, Yue Zeng, and Fushuo Huo. 2023a. (mathrmML)^2 P-Encoder: On Exploration of Channel-Class Correlation for Multi-Label Zero-Shot Learning. In CVPR. 23859-23868.","journal-title":"In CVPR."},{"key":"e_1_3_2_1_28_1","first-page":"3202","article-title":"Video swin transformer","author":"Liu Ze","year":"2022","unstructured":"Ze Liu, Jia Ning, Yue Cao, Yixuan Wei, Zheng Zhang, Stephen Lin, and Han Hu. 2022b. Video swin transformer. In CVPR. 3202-3211.","journal-title":"CVPR."},{"key":"e_1_3_2_1_29_1","first-page":"49","volume-title":"PRL","volume":"88","author":"Nanni L.","year":"2017","unstructured":"L. Nanni, Y.M.G. Costa, D.R. Lucio, C.N. Silla, and S. Brahnam. 2017. Combining visual and acoustic features for audio classification tasks. PRL, Vol. 88 (Mar 2017), 49-56."},{"key":"e_1_3_2_1_30_1","volume-title":"Pro-tuning: Unified Prompt Tuning for Vision Tasks. TCSVT","author":"Nie Xing","year":"2023","unstructured":"Xing Nie, Bolin Ni, Jianlong Chang, Gaofeng Meng, Chunlei Huo, Shiming Xiang, and Qi Tian. 2023. Pro-tuning: Unified Prompt Tuning for Vision Tasks. TCSVT (2023), 1-1."},{"key":"e_1_3_2_1_31_1","first-page":"1015","article-title":"ESC: Dataset for environmental sound classification","author":"Piczak Karol J","year":"2015","unstructured":"Karol J Piczak. 2015. ESC: Dataset for environmental sound classification. In ACM MM. 1015-1018.","journal-title":"ACM MM."},{"key":"e_1_3_2_1_32_1","first-page":"8748","volume-title":"ICML","volume":"139","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In ICML, Vol. 139. 8748-8763."},{"key":"e_1_3_2_1_33_1","first-page":"1041","article-title":"A dataset and taxonomy for urban sound research","author":"Salamon Justin","year":"2014","unstructured":"Justin Salamon, Christopher Jacoby, and Juan Pablo Bello. 2014. A dataset and taxonomy for urban sound research. In ACM MM. 1041-1044.","journal-title":"ACM MM."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26162"},{"key":"e_1_3_2_1_35_1","first-page":"2165","article-title":"Masked vision transformers for hyperspectral image classification","author":"Scheibenreif Linus","year":"2023","unstructured":"Linus Scheibenreif, Michael Mommert, and Damian Borth. 2023. Masked vision transformers for hyperspectral image classification. In CVPR. 2165-2175.","journal-title":"CVPR."},{"key":"e_1_3_2_1_36_1","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, et al., 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. NeurIPS, Vol. 35 (2022), 25278-25294.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_37_1","first-page":"3951","article-title":"Meta-learning for multi-label few-shot classification","author":"Simon Christian","year":"2022","unstructured":"Christian Simon, Piotr Koniusz, and Mehrtash Harandi. 2022. Meta-learning for multi-label few-shot classification. In CVPR. 3951-3960.","journal-title":"CVPR."},{"key":"e_1_3_2_1_38_1","first-page":"30569","article-title":"Dualcoop: Fast adaptation to multi-label recognition with limited annotations","volume":"35","author":"Sun Ximeng","year":"2022","unstructured":"Ximeng Sun, Ping Hu, and Kate Saenko. 2022. Dualcoop: Fast adaptation to multi-label recognition with limited annotations. In NeurIPS, Vol. 35. 30569-30582.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_39_1","volume-title":"LLaMA: Open and Efficient Foundation Language Models. CoRR","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, Aur\u00e9lien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. CoRR, Vol. abs\/2302.13971 (2023)."},{"key":"e_1_3_2_1_40_1","first-page":"6450","article-title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","author":"Tran Du","year":"2018","unstructured":"Du Tran, Heng Wang, Lorenzo Torresani, Jamie Ray, Yann LeCun, and Manohar Paluri. 2018. A Closer Look at Spatiotemporal Convolutions for Action Recognition. In CVPR. 6450-6459.","journal-title":"CVPR."},{"key":"e_1_3_2_1_41_1","first-page":"2579","volume-title":"JMLR","volume":"9","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. JMLR, Vol. 9, 86 (2008), 2579-2605."},{"key":"e_1_3_2_1_42_1","first-page":"5998","article-title":"Attention is All you Need","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In NeurIPS. 5998-6008.","journal-title":"NeurIPS."},{"key":"e_1_3_2_1_43_1","first-page":"1","article-title":"CoVLR","author":"Wan Fengqiang","year":"2024","unstructured":"Fengqiang Wan, Xiangyu Wu, Zhihao Guan, and Yang Yang. 2024. CoVLR: Coordinating Cross-Modal Consistency and Intra-Modal Relations for Vision-Language Retrieval. In ICME. 1-6.","journal-title":"In ICME."},{"key":"e_1_3_2_1_44_1","first-page":"5372","article-title":"LION","author":"Wang Haixin","year":"2024","unstructured":"Haixin Wang, Jianlong Chang, Yihang Zhai, Xiao Luo, Jinan Sun, Zhouchen Lin, and Qi Tian. 2024a. LION: Implicit Vision Prompt Tuning. In AAAI. 5372-5380.","journal-title":"Implicit Vision Prompt Tuning. In AAAI."},{"key":"e_1_3_2_1_45_1","unstructured":"Junke Wang Dongdong Chen Zuxuan Wu Chong Luo Luowei Zhou Yucheng Zhao Yujia Xie Ce Liu Yu-Gang Jiang and Lu Yuan. 2022. OmniVL: One Foundation Model for Image-Language and Video-Language Tasks. In NeurIPS."},{"key":"e_1_3_2_1_46_1","first-page":"12","article-title":"Beyond Object Proposals","volume":"25","author":"Wang Meng","year":"2016","unstructured":"Meng Wang, Changzhi Luo, Richang Hong, Jinhui Tang, and Jiashi Feng. 2016a. Beyond Object Proposals: Random Crop Pooling for Multi-Label Image Recognition. TIP, Vol. 25, 12 (Dec 2016), 5678-5688.","journal-title":"Random Crop Pooling for Multi-Label Image Recognition. TIP"},{"key":"e_1_3_2_1_47_1","unstructured":"Yi Wang Yinan He Yizhuo Li Kunchang Li Jiashuo Yu Xin Ma Xinyuan Chen Yaohui Wang Ping Luo Ziwei Liu Yali Wang Limin Wang and Yu Qiao. 2024b. InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation. In ICLR."},{"key":"e_1_3_2_1_48_1","volume-title":"Luc Van Gool, and Otmar Hilliges","author":"Wang Yifan","year":"2016","unstructured":"Yifan Wang, Jie Song, Limin Wang, Luc Van Gool, and Otmar Hilliges. 2016b. Two-Stream SR-CNNs for Action Recognition in Videos. In BMCV."},{"key":"e_1_3_2_1_49_1","volume-title":"NeurIPS","volume":"36","author":"Wu Junda","year":"2023","unstructured":"Junda Wu, Tong Yu, Rui Wang, Zhao Song, Ruiyi Zhang, Handong Zhao, Chaochao Lu, Shuai Li, and Ricardo Henao. 2023b. InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural LanguageUnderstanding. In NeurIPS, Vol. 36."},{"key":"e_1_3_2_1_50_1","volume-title":"TAI: Text as Image for Multi-Label Image Classification by Co-Learning Transferable Prompt. In IJCAI.","author":"Wu Xiangyu","year":"2024","unstructured":"Xiangyu Wu, Qing-Yuan Jiang, Yang Yang, Yi-Feng Wu, Qing-Guo Chen, and Jianfeng Lu. 2024. TAI: Text as Image for Multi-Label Image Classification by Co-Learning Transferable Prompt. In IJCAI."},{"key":"e_1_3_2_1_51_1","first-page":"4193","article-title":"Ques-to-Visual Guided Visual Question Answering","author":"Wu Xiangyu","year":"2022","unstructured":"Xiangyu Wu, Jianfeng Lu, Zhuanfeng Li, and Fengchao Xiong. 2022. Ques-to-Visual Guided Visual Question Answering. In ICIP. 4193-4197.","journal-title":"ICIP."},{"key":"e_1_3_2_1_52_1","volume-title":"Multi-Label Test-Time Adaptation with Bound Entropy Minimization. In The Thirteenth International Conference on Learning Representations, ICLR 2025","author":"Wu Xiangyu","year":"2025","unstructured":"Xiangyu Wu, Feng Yu, Yang Yang, Qing-Guo Chen, and Jianfeng Lu. 2025. Multi-Label Test-Time Adaptation with Bound Entropy Minimization. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=75PhjtbBdr"},{"key":"e_1_3_2_1_53_1","first-page":"1","article-title":"Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","author":"Wu Yusong","year":"2023","unstructured":"Yusong Wu, Ke Chen, Tianyu Zhang, Yuchen Hui, Taylor Berg-Kirkpatrick, and Shlomo Dubnov. 2023a. Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation. In ICASSP. 1-5.","journal-title":"ICASSP."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1121\/10.0018383"},{"key":"e_1_3_2_1_55_1","volume-title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment. CoRR","author":"Xue Hongwei","year":"2022","unstructured":"Hongwei Xue, Yuchong Sun, Bei Liu, Jianlong Fu, Ruihua Song, Houqiang Li, and Jiebo Luo. 2022. CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment. CoRR (2022)."},{"key":"e_1_3_2_1_56_1","first-page":"3323","article-title":"Multiview Transformers for Video Recognition","author":"Yan Shen","year":"2022","unstructured":"Shen Yan, Xuehan Xiong, Anurag Arnab, Zhichao Lu, Mi Zhang, Chen Sun, and Cordelia Schmid. 2022a. Multiview Transformers for Video Recognition. In CVPR. 3323-3333.","journal-title":"CVPR."},{"key":"e_1_3_2_1_57_1","first-page":"3333","article-title":"Multiview transformers for video recognition","author":"Yan Shen","year":"2022","unstructured":"Shen Yan, Xuehan Xiong, Anurag Arnab, Zhichao Lu, Mi Zhang, Chen Sun, and Cordelia Schmid. 2022b. Multiview transformers for video recognition. In CVPR. 3333-3343.","journal-title":"CVPR."},{"key":"e_1_3_2_1_58_1","volume-title":"Data-free Multi-label Image Recognition via LLM-powered Prompt Tuning. CoRR","author":"Yang Shuo","year":"2024","unstructured":"Shuo Yang, Zirui Shang, Yongqi Wang, Derong Deng, Hongwei Chen, Qiyuan Cheng, and Xinxiao Wu. 2024a. Data-free Multi-label Image Recognition via LLM-powered Prompt Tuning. CoRR, Vol. abs\/2403.01209 (2024)."},{"key":"e_1_3_2_1_59_1","volume-title":"AIM: Adapting Image Models for Efficient Video Action Recognition. In ICLR.","author":"Yang Taojiannan","year":"2023","unstructured":"Taojiannan Yang, Yi Zhu, Yusheng Xie, Aston Zhang, Chen Chen, and Mu Li. 2023. AIM: Adapting Image Models for Efficient Video Action Recognition. In ICLR."},{"key":"e_1_3_2_1_60_1","unstructured":"Yang Yang Fengqiang Wan Qing-Yuan Jiang and Yi Xu. 2024b. Facilitating Multimodal Classification via Dynamically Learning Modality Gap. In NeurIPS."},{"key":"e_1_3_2_1_61_1","first-page":"6757","article-title":"Visual-Language Prompt Tuning with Knowledge-Guided Context Optimization","author":"Yao Hantao","year":"2023","unstructured":"Hantao Yao, Rui Zhang, and Changsheng Xu. 2023. Visual-Language Prompt Tuning with Knowledge-Guided Context Optimization. In CVPR. 6757-6767.","journal-title":"CVPR."},{"key":"e_1_3_2_1_62_1","volume-title":"TMLR","volume":"2022","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. 2022. CoCa: Contrastive Captioners are Image-Text Foundation Models. TMLR, Vol. 2022 (2022)."},{"key":"e_1_3_2_1_63_1","volume-title":"CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation. arXiv preprint arXiv:2506.23121","author":"Yu Xinlei","year":"2025","unstructured":"Xinlei Yu, Changmiao Wang, Hui Jin, Ahmed Elazab, Gangyong Jia, Xiang Wan, Changqing Zou, and Ruiquan Ge. 2025. CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation. arXiv preprint arXiv:2506.23121 (2025)."},{"key":"e_1_3_2_1_64_1","first-page":"5552","article-title":"All in One","author":"Zhang Chunhui","year":"2023","unstructured":"Chunhui Zhang, Xin Sun, Yiqian Yang, Li Liu, Qiong Liu, Xi Zhou, and Yanfeng Wang. 2023a. All in One: Exploring Unified Vision-Language Tracking with Multi-Modal Alignment. In ACM MM. 5552-5561.","journal-title":"Exploring Unified Vision-Language Tracking with Multi-Modal Alignment. In ACM MM."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26336"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_67_1","unstructured":"Bin Zhu Bin Lin Munan Ning Yang Yan Jiaxi Cui Hongfa Wang Yatian Pang Wenhao Jiang Junwu Zhang Zongwei Li Wancai Zhang Zhifeng Li Wei Liu and Li Yuan. 2024. LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment. In ICLR."},{"key":"e_1_3_2_1_68_1","volume-title":"Text as Image: Learning Transferable Adapter for Multi-Label Classification. CoRR","author":"Zhu Xuelin","year":"2023","unstructured":"Xuelin Zhu, Jiuxin Cao, Jian Liu, Dongqi Tang, Furong Xu, Weijia Liu, Jiawei Ge, Bo Liu, Qingpei Guo, and Tianyi Zhang. 2023a. Text as Image: Learning Transferable Adapter for Multi-Label Classification. CoRR, Vol. abs\/2312.04160 (2023)."},{"key":"e_1_3_2_1_69_1","first-page":"1473","article-title":"Scene-aware label graph learning for multi-label image classification","author":"Zhu Xuelin","year":"2023","unstructured":"Xuelin Zhu, Jian Liu, Weijia Liu, Jiawei Ge, Bo Liu, and Jiuxin Cao. 2023b. Scene-aware label graph learning for multi-label image classification. In ICCV. 1473-1482.","journal-title":"ICCV."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:08:21Z","timestamp":1765339701000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755288"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":69,"alternative-id":["10.1145\/3746027.3755288","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755288","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}