{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:15:29Z","timestamp":1777655729654,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","funder":[{"name":"National Natural Science Foun-dation of China","award":["No.62172101"],"award-info":[{"award-number":["No.62172101"]}]},{"name":"the Science and Technology Commission of Shanghai Municipality","award":["No.24511104200"],"award-info":[{"award-number":["No.24511104200"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755316","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:17Z","timestamp":1761375257000},"page":"4117-4126","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Open-Set Image Tagging with Multi-Grained Text Supervision"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0223-2732","authenticated-orcid":false,"given":"Xinyu","family":"Huang","sequence":"first","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8320-9277","authenticated-orcid":false,"given":"Yi-Jie","family":"Huang","sequence":"additional","affiliation":[{"name":"OPPO Research Institute, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1412-2677","authenticated-orcid":false,"given":"Youcai","family":"Zhang","sequence":"additional","affiliation":[{"name":"OPPO Research Institute, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3725-8457","authenticated-orcid":false,"given":"Weiwei","family":"Tian","sequence":"additional","affiliation":[{"name":"College of Biomedical Engineering, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4747-0574","authenticated-orcid":false,"given":"Rui","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7993-7223","authenticated-orcid":false,"given":"Yuejie","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1410-7082","authenticated-orcid":false,"given":"Yanchun","family":"Xie","sequence":"additional","affiliation":[{"name":"OPPO Research Institute, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6137-0174","authenticated-orcid":false,"given":"Yaqian","family":"Li","sequence":"additional","affiliation":[{"name":"OPPO Research Institute, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6926-0538","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2023. OpenAI. ChatGPT. https:\/\/openai.com\/blog\/chatgpt\/."},{"key":"e_1_3_2_1_2_1","volume-title":"Are we done with imagenet? arXiv preprint arXiv:2006.07159","author":"Beyer Lucas","year":"2020","unstructured":"Lucas Beyer, Olivier J H\u00e9naff, Alexander Kolesnikov, Xiaohua Zhai, and A\u00e4ron van den Oord. 2020. Are we done with imagenet? arXiv preprint arXiv:2006.07159 (2020)."},{"key":"e_1_3_2_1_3_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877-1901."},{"key":"e_1_3_2_1_4_1","volume-title":"Large-scale zero-shot image classification from rich and diverse textual descriptions. arXiv preprint arXiv:2103.09669","author":"Bujwid Sebastian","year":"2021","unstructured":"Sebastian Bujwid and Josephine Sullivan. 2021. Large-scale zero-shot image classification from rich and diverse textual descriptions. arXiv preprint arXiv:2103.09669 (2021)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.122"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_3_2_1_9_1","volume-title":"Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection. arXiv preprint arXiv:2310.08027","author":"Dai Yi","year":"2023","unstructured":"Yi Dai, Hao Lang, Kaisheng Zeng, Fei Huang, and Yongbin Li. 2023. Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection. arXiv preprint arXiv:2310.08027 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.666"},{"key":"e_1_3_2_1_12_1","volume-title":"Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman.","author":"Everingham Mark","year":"2015","unstructured":"Mark Everingham, SM Ali Eslami, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman. 2015. The pascal visual object classes challenge: A retrospective. International journal of computer vision, Vol. 111 (2015), 98-136."},{"key":"e_1_3_2_1_13_1","volume-title":"WordNet: An electronic lexical database","author":"Fellbaum Christiane","unstructured":"Christiane Fellbaum. 1998. WordNet: An electronic lexical database. MIT press."},{"key":"e_1_3_2_1_14_1","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume":"33","author":"Gan Zhe","year":"2020","unstructured":"Zhe Gan, Yen-Chun Chen, Linjie Li, Chen Zhu, Yu Cheng, and Jingjing Liu. 2020. Large-scale adversarial training for vision-and-language representation learning. Advances in Neural Information Processing Systems, Vol. 33 (2020), 6616-6628.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Learning Representations.","author":"Gu Xiuye","year":"2021","unstructured":"Xiuye Gu, Tsung-Yi Lin, Weicheng Kuo, and Yin Cui. 2021. Open-vocabulary Object Detection via Vision and Language Knowledge Distillation. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25159"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.775"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16957"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548108"},{"key":"e_1_3_2_1_20_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Huang Xinyu","year":"2024","unstructured":"Xinyu Huang, Youcai Zhang, Jinyu Ma, Weiwei Tian, Rui Feng, Yuejie Zhang, Yaqian Li, Yandong Guo, and Lei Zhang. 2024. Tag2Text: Guiding Vision-Language Model via Image Tagging. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_21_1","volume-title":"International conference on machine learning. PMLR, 4904-4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International conference on machine learning. PMLR, 4904-4916."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David A Shamma et al. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision Vol. 123 1 (2017) 32-73.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"e_1_3_2_1_24_1","volume-title":"International Conference on Machine Learning. PMLR, 12888-12900","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 International Conference on Machine Learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_25_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_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_27_1","volume-title":"A chatgpt aided explainable framework for zero-shot medical image diagnosis. arXiv preprint arXiv:2307.01981","author":"Liu Jiaxiang","year":"2023","unstructured":"Jiaxiang Liu, Tianxiang Hu, Yan Zhang, Xiaotang Gai, Yang Feng, and Zuozhu Liu. 2023a. A chatgpt aided explainable framework for zero-shot medical image diagnosis. arXiv preprint arXiv:2307.01981 (2023)."},{"key":"e_1_3_2_1_28_1","unstructured":"Shilong Liu Zhaoyang Zeng Tianhe Ren Feng Li Hao Zhang Jie Yang Chunyuan Li Jianwei Yang Hang Su Jun Zhu et al. 2023b. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_30_1","volume-title":"Relvit: Concept-guided vision transformer for visual relational reasoning. arXiv preprint arXiv:2204.11167","author":"Ma Xiaojian","year":"2022","unstructured":"Xiaojian Ma, Weili Nie, Zhiding Yu, Huaizu Jiang, Chaowei Xiao, Yuke Zhu, Song-Chun Zhu, and Anima Anandkumar. 2022. Relvit: Concept-guided vision transformer for visual relational reasoning. arXiv preprint arXiv:2204.11167 (2022)."},{"key":"e_1_3_2_1_31_1","volume-title":"Visual classification via description from large language models. arXiv preprint arXiv:2210.07183","author":"Menon Sachit","year":"2022","unstructured":"Sachit Menon and Carl Vondrick. 2022. Visual classification via description from large language models. arXiv preprint arXiv:2210.07183 (2022)."},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference on Machine Learning. PMLR, 26342-26362","author":"Novack Zachary","year":"2023","unstructured":"Zachary Novack, Julian McAuley, Zachary Chase Lipton, and Saurabh Garg. 2023. Chils: Zero-shot image classification with hierarchical label sets. In International Conference on Machine Learning. PMLR, 26342-26362."},{"key":"e_1_3_2_1_33_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. https:\/\/arxiv.org\/abs\/2303.08774. arXiv:cs.CL\/2303.08774"},{"key":"e_1_3_2_1_34_1","volume-title":"Im2text: Describing images using 1 million captioned photographs. Advances in neural information processing systems","author":"Ordonez Vicente","year":"2011","unstructured":"Vicente Ordonez, Girish Kulkarni, and Tamara Berg. 2011. Im2text: Describing images using 1 million captioned photographs. Advances in neural information processing systems, Vol. 24 (2011)."},{"key":"e_1_3_2_1_35_1","volume-title":"Zest: Zero-shot learning from text descriptions using textual similarity and visual summarization. arXiv preprint arXiv:2010.03276","author":"Paz-Argaman Tzuf","year":"2020","unstructured":"Tzuf Paz-Argaman, Yuval Atzmon, Gal Chechik, and Reut Tsarfaty. 2020. Zest: Zero-shot learning from text descriptions using textual similarity and visual summarization. arXiv preprint arXiv:2010.03276 (2020)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00673"},{"key":"e_1_3_2_1_39_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_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"e_1_3_2_1_41_1","volume-title":"ChatGPT-Powered Hierarchical Comparisons for Image Classification. arXiv preprint arXiv:2311.00206","author":"Ren Zhiyuan","year":"2023","unstructured":"Zhiyuan Ren, Yiyang Su, and Xiaoming Liu. 2023. ChatGPT-Powered Hierarchical Comparisons for Image Classification. arXiv preprint arXiv:2311.00206 (2023)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00012"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_1_45_1","first-page":"15558","article-title":"K-lite: Learning transferable visual models with external knowledge","volume":"35","author":"Shen Sheng","year":"2022","unstructured":"Sheng Shen, Chunyuan Li, Xiaowei Hu, Yujia Xie, Jianwei Yang, Pengchuan Zhang, Zhe Gan, Lijuan Wang, Lu Yuan, Ce Liu, et al., 2022. K-lite: Learning transferable visual models with external knowledge. Advances in Neural Information Processing Systems, Vol. 35 (2022), 15558-15573.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_46_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. Advances in Neural Information Processing Systems, Vol. 35 (2022), 30569-30582.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_47_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_48_1","first-page":"9125","article-title":"Detclip: Dictionary-enriched visual-concept paralleled pre-training for open-world detection","volume":"35","author":"Yao Lewei","year":"2022","unstructured":"Lewei Yao, Jianhua Han, Youpeng Wen, Xiaodan Liang, Dan Xu, Wei Zhang, Zhenguo Li, Chunjing Xu, and Hang Xu. 2022. Detclip: Dictionary-enriched visual-concept paralleled pre-training for open-world detection. Advances in Neural Information Processing Systems, Vol. 35 (2022), 9125-9138.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"e_1_3_2_1_50_1","volume-title":"Florence: A new foundation model for computer vision. arXiv preprint arXiv:2111.11432","author":"Yuan Lu","year":"2021","unstructured":"Lu Yuan, Dongdong Chen, Yi-Ling Chen, Noel Codella, Xiyang Dai, Jianfeng Gao, Houdong Hu, Xuedong Huang, Boxin Li, Chunyuan Li, et al., 2021. Florence: A new foundation model for computer vision. arXiv preprint arXiv:2111.11432 (2021)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00237"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:42:50Z","timestamp":1765309370000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755316"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":54,"alternative-id":["10.1145\/3746027.3755316","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755316","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"}}]}}