{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T00:05:38Z","timestamp":1768694738909,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976217, 62306320"],"award-info":[{"award-number":["61976217, 62306320"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20231063"],"award-info":[{"award-number":["BK20231063"]}],"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":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658107","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"561-569","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Prompt Expending for Single Positive Multi-Label Learning with Global Unannotated Categories"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3364-8703","authenticated-orcid":false,"given":"Zhongnian","family":"Li","sequence":"first","affiliation":[{"name":"China University of Mining and Technology, Xuzhou, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8007-5583","authenticated-orcid":false,"given":"Peng","family":"Ying","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology, Xuzhou, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3836-6487","authenticated-orcid":false,"given":"Meng","family":"Wei","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology, Xuzhou, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8344-2597","authenticated-orcid":false,"given":"Tongfeng","family":"Sun","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology, Xuzhou, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6973-799X","authenticated-orcid":false,"given":"Xinzheng","family":"Xu","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology, Xuzhou, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00099"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00131"},{"key":"e_1_3_2_1_4_1","volume-title":"Openprompt: An open-source framework for prompt-learning. arXiv preprint arXiv:2111.01998","author":"Ding Ning","year":"2021","unstructured":"Ning Ding, Shengding Hu, Weilin Zhao, Yulin Chen, Zhiyuan Liu, Hai-Tao Zheng, and Maosong Sun. 2021. Openprompt: An open-source framework for prompt-learning. arXiv preprint arXiv:2111.01998 (2021)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"e_1_3_2_1_6_1","volume-title":"Joao FG de Freitas, and David A Forsyth","author":"Duygulu Pinar","year":"2002","unstructured":"Pinar Duygulu, Kobus Barnard, Joao FG de Freitas, and David A Forsyth. 2002. Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary. In Computer Vision-ECCV 2002: 7th European Conference on Computer Vision Copenhagen, Denmark, May 28--31, 2002 Proceedings, Part IV 7. Springer, 97--112."},{"key":"e_1_3_2_1_7_1","unstructured":"Mark Everingham and John Winn. 2012. The PASCAL visual object classes challenge 2012 (VOC2012) development kit. Pattern Anal. Stat. Model. Comput. Learn. Tech. Rep Vol. 2007 1--45 (2012) 5."},{"key":"e_1_3_2_1_8_1","volume-title":"Clip-adapter: Better vision-language models with feature adapters. International Journal of Computer Vision","author":"Gao Peng","year":"2023","unstructured":"Peng Gao, Shijie Geng, Renrui Zhang, Teli Ma, Rongyao Fang, Yongfeng Zhang, Hongsheng Li, and Yu Qiao. 2023. Clip-adapter: Better vision-language models with feature adapters. International Journal of Computer Vision (2023), 1--15."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20628"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-022-01658-9"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.655313"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01376"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13. Springer, 740--755."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290797"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501825"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119334"},{"key":"e_1_3_2_1_17_1","first-page":"2824","article-title":"Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models","volume":"2022","author":"Ivana Robert Logan IV","year":"2022","unstructured":"Robert Logan IV, Ivana Balavz evi\u0107, Eric Wallace, Fabio Petroni, Sameer Singh, and Sebastian Riedel. 2022. Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models. In Findings of the Association for Computational Linguistics: ACL 2022. 2824--2835.","journal-title":"Findings of the Association for Computational Linguistics: ACL"},{"key":"e_1_3_2_1_18_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2018","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_19_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems , Vol. 32 (2019)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"e_1_3_2_1_21_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_22_1","volume-title":"Classifier chains for multi-label classification. Machine learning","author":"Read Jesse","year":"2011","unstructured":"Jesse Read, Bernhard Pfahringer, Geoff Holmes, and Eibe Frank. 2011. Classifier chains for multi-label classification. Machine learning , Vol. 85 (2011), 333--359."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"e_1_3_2_1_24_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_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108839"},{"key":"e_1_3_2_1_26_1","volume-title":"Random k-labelsets for multilabel classification","author":"Tsoumakas Grigorios","year":"2010","unstructured":"Grigorios Tsoumakas, Ioannis Katakis, and Ioannis Vlahavas. 2010. Random k-labelsets for multilabel classification. IEEE transactions on knowledge and data engineering, Vol. 23, 7 (2010), 1079--1089."},{"key":"e_1_3_2_1_27_1","unstructured":"Catherine Wah Steve Branson Peter Welinder Pietro Perona and Serge Belongie. 2011. The caltech-ucsd birds-200--2011 dataset. (2011)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Deng-Bao Wang Lei Feng and Min-Ling Zhang. 2021. Learning from Complementary Labels via Partial-Output Consistency Regularization.. In IJCAI. 3075--3081.","DOI":"10.24963\/ijcai.2021\/423"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6089"},{"key":"e_1_3_2_1_30_1","volume-title":"Are the BERT Family Zero-Shot Learners? A Study on Their Potential and Limitations. Artificial Intelligence","author":"Wang Yue","year":"2023","unstructured":"Yue Wang, Lijun Wu, Juntao Li, Xiaobo Liang, and Min Zhang. 2023. Are the BERT Family Zero-Shot Learners? A Study on Their Potential and Limitations. Artificial Intelligence (2023), 103953."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.58"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"e_1_3_2_1_33_1","first-page":"3676","article-title":"Partial multi-label learning with noisy label identification","volume":"44","author":"Xie Ming-Kun","year":"2021","unstructured":"Ming-Kun Xie and Sheng-Jun Huang. 2021. Partial multi-label learning with noisy label identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 7 (2021), 3676--3687.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_34_1","first-page":"18430","article-title":"Label-aware global consistency for multi-label learning with single positive labels","volume":"35","author":"Xie Ming-Kun","year":"2022","unstructured":"Ming-Kun Xie, Jiahao Xiao, and Sheng-Jun Huang. 2022. Label-aware global consistency for multi-label learning with single positive labels. Advances in Neural Information Processing Systems , Vol. 35 (2022), 18430--18441.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","volume-title":"Vision-Language Pseudo-Labels for Single-Positive Multi-Label Learning. arXiv preprint arXiv:2310.15985","author":"Xing Xin","year":"2023","unstructured":"Xin Xing, Zhexiao Xiong, Abby Stylianou, Srikumar Sastry, Liyu Gong, and Nathan Jacobs. 2023. Vision-Language Pseudo-Labels for Single-Positive Multi-Label Learning. arXiv preprint arXiv:2310.15985 (2023)."},{"key":"e_1_3_2_1_36_1","first-page":"21765","article-title":"One positive label is sufficient: Single-positive multi-label learning with label enhancement","volume":"35","author":"Xu Ning","year":"2022","unstructured":"Ning Xu, Congyu Qiao, Jiaqi Lv, Xin Geng, and Min-Ling Zhang. 2022. One positive label is sufficient: Single-positive multi-label learning with label enhancement. Advances in Neural Information Processing Systems , Vol. 35 (2022), 21765--21776.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","volume-title":"International conference on machine learning. PMLR, 593--601","author":"Yu Hsiang-Fu","year":"2014","unstructured":"Hsiang-Fu Yu, Prateek Jain, Purushottam Kar, and Inderjit Dhillon. 2014. Large-scale multi-label learning with missing labels. In International conference on machine learning. PMLR, 593--601."},{"key":"e_1_3_2_1_38_1","volume-title":"ML-KNN: A lazy learning approach to multi-label learning. Pattern recognition","author":"Zhang Min-Ling","year":"2007","unstructured":"Min-Ling Zhang and Zhi-Hua Zhou. 2007. ML-KNN: A lazy learning approach to multi-label learning. Pattern recognition, Vol. 40, 7 (2007), 2038--2048."},{"key":"e_1_3_2_1_39_1","volume-title":"Simple and robust loss design for multi-label learning with missing labels. arXiv preprint arXiv:2112.07368","author":"Zhang Youcai","year":"2021","unstructured":"Youcai Zhang, Yuhao Cheng, Xinyu Huang, Fei Wen, Rui Feng, Yaqian Li, and Yandong Guo. 2021. Simple and robust loss design for multi-label learning with missing labels. arXiv preprint arXiv:2112.07368 (2021)."},{"key":"e_1_3_2_1_40_1","volume-title":"Recognize Anything: A Strong Image Tagging Model. arXiv preprint arXiv:2306.03514","author":"Zhang Youcai","year":"2023","unstructured":"Youcai Zhang, Xinyu Huang, Jinyu Ma, Zhaoyang Li, Zhaochuan Luo, Yanchun Xie, Yuzhuo Qin, Tong Luo, Yaqian Li, Shilong Liu, et al. 2023. Recognize Anything: A Strong Image Tagging Model. arXiv preprint arXiv:2306.03514 (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_25"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","location":"Phuket Thailand","acronym":"ICMR '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658107","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:50:35Z","timestamp":1755766235000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658107"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":42,"alternative-id":["10.1145\/3652583.3658107","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658107","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}