{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T15:02:51Z","timestamp":1784646171541,"version":"3.55.0"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"8","license":[{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62076005, 61906002"],"award-info":[{"award-number":["62076005, 61906002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Dreams Foundation of Jianghuai Advance Technology Center","award":["2023ZM01Z015"],"award-info":[{"award-number":["2023ZM01Z015"]}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"crossref","award":["2508085MF157, 2008085MF191"],"award-info":[{"award-number":["2508085MF157, 2008085MF191"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Anhui Provincial University Natural Science Research Major Project","award":["2025AHGXZK20027"],"award-info":[{"award-number":["2025AHGXZK20027"]}]},{"name":"University Synergy Innovation Program of Anhui Province","award":["GXXT-2021-002"],"award-info":[{"award-number":["GXXT-2021-002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,8,31]]},"abstract":"<jats:p>\n                    The problem of Multi-Label Image Recognition with Partial Labels (MLIR-PL) is a significant challenge in computer vision, primarily due to the scarcity and high cost of complete annotations. Recent advances have leveraged large-scale vision-language models, such as CLIP, to establish rich correspondences between images and their labels, thereby improving the MLIR-PL performance. However, the existing CLIP-based methods have not fully exploited fine-grained local image features to mitigate interference from semantically irrelevant regions. Moreover, many studies have oversimplified the use of prompt contexts, limiting their ability to comprehensively capture the multi-dimensional attributes of categories. To address these limitations, this article proposes a novel MLIR-PL model with Visual\u2013Label Alignment and Attribute-Aware Prompt (VA\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\({}^{3}\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    P), which sufficiently harnesses the capabilities of large-scale pre-trained vision-language models. In the model, we design a Visual\u2013Label Alignment module to establish a mapping between local image features and category text representations, conspicuously reducing the interference from irrelevant regions. Additionally, our Attribute-Aware Prompt module offers diverse contextual information, providing a more comprehensive representation of the category\u2019s attributes. Extensive experimental results on the COCO 2014 and VOC 2007 datasets, compared with multiple state-of-the-art methods, demonstrate that our model achieves the best performance comprehensively, verifying the advantages of the proposed model in the MLIR-PL task.\n                  <\/jats:p>","DOI":"10.1145\/3828542","type":"journal-article","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T13:57:16Z","timestamp":1783346236000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual\u2013Label Alignment and Attribute-Aware Prompt for Multi-Label Image Recognition with Partial Labels"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0164-7944","authenticated-orcid":false,"given":"Dengdi","family":"Sun","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Anhui University, Hefei, China and Jianghuai Advance Technology Center, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1577-4861","authenticated-orcid":false,"given":"Hongxing","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1781-912X","authenticated-orcid":false,"given":"Zhendong","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8681-0765","authenticated-orcid":false,"given":"Leilei","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence Engineering, Hefei Institute of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5948-5055","authenticated-orcid":false,"given":"Bin","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00472"},{"key":"e_1_3_2_3_2","first-page":"2801","volume-title":"Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR \u201911)","author":"Bucak Serhat Selcuk","year":"2011","unstructured":"Serhat Selcuk Bucak, Rong Jin, and Anil K. Jain. 2011. Multi-label learning with incomplete class assignments. In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR \u201911). IEEE, 2801\u20132808."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02127-2"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19910"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00061"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"e_1_3_2_8_2","doi-asserted-by":"crossref","first-page":"130498","DOI":"10.1016\/j.neucom.2025.130498","article-title":"Category-wise fine-tuning: Resisting incorrect pseudo-labels in multi-label image classification with partial labels","author":"Chong Chak Fong","year":"2025","unstructured":"Chak Fong Chong, Xinyi Fang, Jielong Guo, Pedro Henriques Abreu, Yapeng Wang, Xu Yang, Wei Ke, and Sio-Kei Im. 2025. Category-wise fine-tuning: Resisting incorrect pseudo-labels in multi-label image classification with partial labels. Neurocomputing 647 (2025), 130498.","journal-title":"Neurocomputing"},{"key":"e_1_3_2_9_2","first-page":"248","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Deng Jia","year":"2009","unstructured":"Jia Deng, Wei Dong, R. Socher, Li Jia Li, Kai Li, and Li Fei-Fei. 2009. ImageNet: A large-scale hierarchical image database. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 248\u2013255."},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557011"},{"key":"e_1_3_2_11_2","first-page":"3398","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ding Zixuan","year":"2023","unstructured":"Zixuan Ding, Ao Wang, Hui Chen, Qiang Zhang, Pengzhang Liu, Yongjun Bao, Weipeng Yan, and Jungong Han. 2023. Exploring structured semantic prior for multi-label recognition with incomplete labels. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 3398\u20133407."},{"key":"e_1_3_2_12_2","unstructured":"Alexey Dosovitskiy. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929. Retrieved from https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00074"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.631"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_2_16_2","unstructured":"Zongyuan Ge Dwarikanath Mahapatra Suman Sedai Rahil Garnavi and Rajib Chakravorty. 2018. Chest x-rays classification: A multi-label and fine-grained problem. arXiv:1807.07247. Retrieved from https:\/\/arxiv.org\/abs\/1807.07247"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00275"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_19_2","unstructured":"Zhi-Fen He Ren-Dong Xie Bo Li Bin Liu and Jin-Yan Hu. 2025. Collaborative learning of semantic-aware feature learning and label recovery for multi-label image recognition with incomplete labels. arXiv:2510.10055v1. Retrieved from https:\/\/arxiv.org\/abs\/2510.10055v1"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3346405"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01376"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00332"},{"key":"e_1_3_2_23_2","first-page":"561","article-title":"Exploiting weakly supervised visual patterns to learn from partial annotations","volume":"33","author":"Kundu Kaustav","year":"2020","unstructured":"Kaustav Kundu and Joseph Tighe. 2020. Exploiting weakly supervised visual patterns to learn from partial annotations. Advances in Neural Information Processing Systems 33 (2020), 561\u2013572.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00654"},{"key":"e_1_3_2_26_2","first-page":"684","volume-title":"Proceedings of the 14th European Conference on Computer Vision (ECCV \u201916), Part VI","author":"Li Yining","year":"2016","unstructured":"Yining Li, Chen Huang, Chen Change Loy, and Xiaoou Tang. 2016. Human attribute recognition by deep hierarchical contexts. In Proceedings of the 14th European Conference on Computer Vision (ECCV \u201916), Part VI. Springer, 684\u2013700."},{"key":"e_1_3_2_27_2","first-page":"3618","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Li Zheng","year":"2025","unstructured":"Zheng Li, Yibing Song, Ming-Ming Cheng, Xiang Li, and Jian Yang. 2025. Advancing textual prompt learning with anchored attributes. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 3618\u20133627."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_29_2","first-page":"712","article-title":"On the optimality of classifier chain for multi-label classification","volume":"28","author":"Liu Weiwei","year":"2015","unstructured":"Weiwei Liu and Ivor Tsang. 2015. On the optimality of classifier chain for multi-label classification. Advances in Neural Information Processing Systems 28 (2015), 712\u2013720.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119334"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_32_2","first-page":"1656","volume-title":"Proceedings of the European Conference on Artificial Intelligence","author":"Ma Leilei","year":"2023","unstructured":"Leilei Ma, Dengdi Sun, Lei Wang, Haifeng Zhao, and Bin Luo. 2023. Semantic-aware dual contrastive learning for multi-label image classification. In Proceedings of the European Conference on Artificial Intelligence, 1656\u20131663."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680815"},{"key":"e_1_3_2_34_2","first-page":"25434","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"Ma Lei-Lei","year":"2025","unstructured":"Lei-Lei Ma, Shuo Xu, Ming-Kun Xie, Lei Wang, Dengdi Sun, and Haifeng Zhao. 2025. Correlative and discriminative label grouping for multi-label visual prompt tuning. In Proceedings of the Computer Vision and Pattern Recognition Conference, 25434\u201325443."},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20105"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123526"},{"key":"e_1_3_2_37_2","first-page":"8748","volume-title":"Proceedings of the International Conference on Machine Learning","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 Proceedings of the International Conference on Machine Learning. PMLR, 8748\u20138763."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708991"},{"key":"e_1_3_2_40_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. Retrieved from https:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2216"},{"key":"e_1_3_2_42_2","first-page":"6227","volume-title":"Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI \u201925)","author":"Tang Hao","year":"2025","unstructured":"Hao Tang, Shengfeng He, and Jing Qin. 2025. Connecting giants: Synergistic knowledge transfer of large multimodal models for few-shot learning. In Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI \u201925). International Joint Conferences on Artificial Intelligence Organization, 6227\u20136235."},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413884"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612221"},{"key":"e_1_3_2_45_2","first-page":"15770","volume-title":"Proceedings of the 40th AAAI Conference on Artificial Intelligence","author":"Tang Hao","year":"2026","unstructured":"Hao Tang, Yu Liu, Shuanglin Yan, Fei Shen, Shengfeng He, and Jing Qin. 2026. Cross-modal proxy evolving for OOD detection with vision-language models. In Proceedings of the 40th AAAI Conference on Artificial Intelligence, 15770\u201315778."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108792"},{"key":"e_1_3_2_47_2","doi-asserted-by":"crossref","first-page":"3251","DOI":"10.1109\/TMM.2025.3535387","article-title":"Splicemix: A cross-scale and semantic blending augmentation strategy for multi-label image classification","author":"Wang Lei","year":"2025","unstructured":"Lei Wang, Yibing Zhan, Leilei Ma, Dapeng Tao, Liang Ding, and Chen Gong. 2025. Splicemix: A cross-scale and semantic blending augmentation strategy for multi-label image classification. IEEE Transactions on Multimedia 27, (2025), 3251\u20133265.","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_2_48_2","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1145\/3651671.3651674","volume-title":"Proceedings of the 2024 16th International Conference on Machine Learning and Computing","author":"Wang Rui","year":"2024","unstructured":"Rui Wang, Zhengxin Pan, Fangyu Wu, Yifan Lv, and Bailing Zhang. 2024. Multi-modal contextual prompt learning for multi-label classification with partial labels. In Proceedings of the 2024 16th International Conference on Machine Learning and Computing, 517\u2013524."},{"key":"e_1_3_2_49_2","first-page":"464","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Wang Zhouxia","year":"2017","unstructured":"Zhouxia Wang, Tianshui Chen, Guanbin Li, Ruijia Xu, and Liang Lin. 2017. Multi-label image recognition by recurrently discovering attentional regions. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 464\u2013472."},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414046"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1339"},{"key":"e_1_3_2_52_2","first-page":"54576","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Xie Ming-Kun","year":"2024","unstructured":"Ming-Kun Xie, Jia-Hao Xiao, Pei Peng, Gang Niu, Masashi Sugiyama, and Sheng-Jun Huang. 2024. Counterfactual reasoning for multi-label image classification via patching-based training. In Proceedings of the International Conference on Machine Learning. PMLR, 54576\u201354589."},{"key":"e_1_3_2_53_2","first-page":"112986","article-title":"Image-free multi-label image recognition via LLM-powered hierarchical prompt tuning","author":"Yang Shuo","year":"2025","unstructured":"Shuo Yang, Zirui Shang, Yongqi Wang, Derong Deng, Hongwei Chen, Xinxiao Wu, and Qiyuan Cheng. 2025. Image-free multi-label image recognition via LLM-powered hierarchical prompt tuning. Pattern Recognition 174 (2025), 112986.","journal-title":"Pattern Recognition"},{"key":"e_1_3_2_54_2","first-page":"13440","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Oguz Yazici Vacit","year":"2020","unstructured":"Vacit Oguz Yazici, Abel Gonzalez-Garcia, Arnau Ramisa, Bartlomiej Twardowski, and Joost van de Weijer. 2020. Orderless recurrent models for multi-label classification. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 13440\u201313449."},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00927"},{"key":"e_1_3_2_56_2","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Zhou Bolei","year":"2016","unstructured":"Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. 2016. Learning deep features for discriminative localization. In Proceedings of the IEEE\/CVF International Conference on Computer Vision."}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3828542","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:20:47Z","timestamp":1784643647000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3828542"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"references-count":55,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8,31]]}},"alternative-id":["10.1145\/3828542"],"URL":"https:\/\/doi.org\/10.1145\/3828542","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,21]]},"assertion":[{"value":"2025-06-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}