{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T02:19:06Z","timestamp":1783477146172,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":63,"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":[{"name":"Jiangsu Natural Science Foundation","award":["BK20210224"],"award-info":[{"award-number":["BK20210224"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["020214380120"],"award-info":[{"award-number":["020214380120"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"State Key Laboratory Fund","award":["ZZKT2024A14"],"award-info":[{"award-number":["ZZKT2024A14"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222604, 62206052, 62192783"],"award-info":[{"award-number":["62222604, 62206052, 62192783"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M750424"],"award-info":[{"award-number":["2024M750424"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2023ZD0120700, 2023ZD0120701"],"award-info":[{"award-number":["2023ZD0120700, 2023ZD0120701"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680860","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"9397-9406","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["PC\n            <sup>2<\/sup>\n            : Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4131-7146","authenticated-orcid":false,"given":"Yue","family":"Duan","sequence":"first","affiliation":[{"name":"Nanjing University &amp; Ant Group, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2102-2693","authenticated-orcid":false,"given":"Zhangxuan","family":"Gu","sequence":"additional","affiliation":[{"name":"Ant Group, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9624-3776","authenticated-orcid":false,"given":"Zhenzhe","family":"Ying","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7091-0702","authenticated-orcid":false,"given":"Lei","family":"Qi","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8992-9833","authenticated-orcid":false,"given":"Changhua","family":"Meng","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0722-9744","authenticated-orcid":false,"given":"Yinghuan","family":"Shi","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_2_2_1","volume-title":"International Conference on Machine Learning.","author":"Arpit Devansh","year":"2017","unstructured":"Devansh Arpit, Stanis\u0142aw Jastrzkebski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, et al. 2017. A closer look at memorization in deep networks. In International Conference on Machine Learning."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00833"},{"key":"e_1_3_2_2_5_1","unstructured":"James Betker Gabriel Goh Li Jing Tim Brooks Jianfeng Wang Linjie Li Long Ouyang Juntang Zhuang Joyce Lee Yufei Guo Wesam Manassra Prafulla Dhariwal Casey Chu and Yunxin Jiao. 2023. Improving Image Generation with Better Captions. OpenAI. https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf"},{"key":"e_1_3_2_2_6_1","unstructured":"Mathilde Caron Ishan Misra Julien Mairal Priya Goyal Piotr Bojanowski and Armand Joulin. 2020. Unsupervised learning of visual features by contrasting cluster assignments. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29018"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_2_11_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Conference of the North American","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 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"e_1_3_2_2_13_1","volume-title":"Mutexmatch: semi-supervised learning with mutex-based consistency regularization","author":"Duan Yue","year":"2022","unstructured":"Yue Duan, Zhen Zhao, Lei Qi, Lei Wang, Luping Zhou, Yinghuan Shi, and Yang Gao. 2022. Mutexmatch: semi-supervised learning with mutex-based consistency regularization. IEEE Transactions on Neural Networks and Learning Systems (2022)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01477"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29068"},{"key":"e_1_3_2_2_16_1","volume-title":"Jamie Ryan Kiros, and Sanja Fidler","author":"Faghri Fartash","year":"2017","unstructured":"Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2017. Vse: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108777"},{"key":"e_1_3_2_2_18_1","volume-title":"International Conference on Neural Information Processing Systems.","author":"Grandvalet Yves","year":"2004","unstructured":"Yves Grandvalet and Yoshua Bengio. 2004. Semi-supervised learning by entropy minimization. In International Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_2_19_1","volume-title":"Mobile User Interface Element Detection Via Adaptively Prompt Tuning. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Gu Zhangxuan","year":"2023","unstructured":"Zhangxuan Gu, Zhuoer Xu, Haoxing Chen, Jun Lan, Changhua Meng, and Weiqiang Wang. 2023. Mobile User Interface Element Detection Via Adaptively Prompt Tuning. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_2_20_1","volume-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in Neural Information Processing Systems","author":"Han Bo","year":"2018","unstructured":"Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, and Masashi Sugiyama. 2018. Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in Neural Information Processing Systems (2018)."},{"key":"e_1_3_2_2_21_1","volume-title":"Noisy Correspondence Learning with Meta Similarity Correction. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Han Haochen","year":"2023","unstructured":"Haochen Han, Kaiyao Miao, Qinghua Zheng, and Minnan Luo. 2023. Noisy Correspondence Learning with Meta Similarity Correction. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02519"},{"key":"e_1_3_2_2_23_1","unstructured":"Hsiang-Chih Hsu. 2016. Jieba chinese text segmentation. https:\/\/github.com\/fxsjy\/jieba."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00536"},{"key":"e_1_3_2_2_25_1","unstructured":"Zhenyu Huang Guocheng Niu Xiao Liu Wenbiao Ding Xinyan Xiao Hua Wu and Xi Peng. 2021. Learning with noisy correspondence for cross-modal matching. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_26_1","volume-title":"International Conference on Machine Learning.","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."},{"key":"e_1_3_2_2_27_1","volume-title":"International Conference on Learning Representations.","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_28_1","volume-title":"Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539","author":"Kiros Ryan","year":"2014","unstructured":"Ryan Kiros, Ruslan Salakhutdinov, and Richard S Zemel. 2014. Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)."},{"key":"e_1_3_2_2_29_1","volume-title":"International Conference on Machine Learning. PMLR, 17283--17300","author":"Koh Jing Yu","year":"2023","unstructured":"Jing Yu Koh, Ruslan Salakhutdinov, and Daniel Fried. 2023. Grounding language models to images for multimodal inputs and outputs. In International Conference on Machine Learning. PMLR, 17283--17300."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00316"},{"key":"e_1_3_2_2_31_1","unstructured":"Kuang-Huei Lee Xi Chen Gang Hua Houdong Hu and Xiaodong He. 2018. Stacked cross attention for image-text matching. In European Cconference on Computer Vision."},{"key":"e_1_3_2_2_32_1","volume-title":"International Conference on Learning Representations.","author":"Li Junnan","year":"2020","unstructured":"Junnan Li, Richard Socher, and Steven CH Hoi. 2020. Dividemix: Learning with noisy labels as semi-supervised learning. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_35_1","unstructured":"Nagarajan Natarajan Inderjit S Dhillon Pradeep K Ravikumar and Ambuj Tewari. 2013. Learning with noisy labels. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2482228"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547922"},{"key":"e_1_3_2_2_38_1","volume-title":"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 International Conference on Machine Learning."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"e_1_3_2_2_40_1","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"e_1_3_2_2_43_1","volume-title":"A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation. arXiv preprint arXiv:2310.16656","author":"Segalis Eyal","year":"2023","unstructured":"Eyal Segalis, Dani Valevski, Danny Lumen, Yossi Matias, and Yaniv Leviathan. 2023. A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation. arXiv preprint arXiv:2310.16656 (2023)."},{"key":"e_1_3_2_2_44_1","volume-title":"Neural Machine Translation of Rare Words with Subword Units. In Annual Meeting of the Association for Computational Linguistics.","author":"Sennrich Rico","year":"2016","unstructured":"Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Neural Machine Translation of Rare Words with Subword Units. In Annual Meeting of the Association for Computational Linguistics."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_2_46_1","volume-title":"Improving Image Captioning with Better Use of Caption. In Annual Meeting of the Association for Computational Linguistics.","author":"Shi Zhan","year":"2020","unstructured":"Zhan Shi, Xu Zhou, Xipeng Qiu, and Xiaodan Zhu. 2020. Improving Image Captioning with Better Use of Caption. In Annual Meeting of the Association for Computational Linguistics."},{"key":"e_1_3_2_2_47_1","unstructured":"Kihyuk Sohn David Berthelot Chun-Liang Li Zizhao Zhang Nicholas Carlini Ekin D. Cubuk Alex Kurakin Han Zhang and Colin Raffel. 2020. FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152527"},{"key":"e_1_3_2_2_49_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Yonghui Wu Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_16"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"e_1_3_2_2_52_1","volume-title":"A comprehensive survey on cross-modal retrieval. arXiv preprint arXiv:1607.06215","author":"Wang Kaiye","year":"2016","unstructured":"Kaiye Wang, Qiyue Yin, Wei Wang, Shu Wu, and Liang Wang. 2016. A comprehensive survey on cross-modal retrieval. arXiv preprint arXiv:1607.06215 (2016)."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"e_1_3_2_2_54_1","unstructured":"Ziyang Wang Heba Elfardy Markus Dreyer Kevin Small and Mohit Bansal. 2024. Unified embeddings for multimodal retrieval via frozen LLMs. In Findings of the Association for Computational Linguistics: EACL."},{"key":"e_1_3_2_2_55_1","volume-title":"Transformers: State-of-the-Art Natural Language Processing. In Conference on Empirical Methods in Natural Language Processing: System Demonstrations.","author":"Wolf Thomas","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush. 2020. Transformers: State-of-the-Art Natural Language Processing. In Conference on Empirical Methods in Natural Language Processing: System Demonstrations."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506421"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01904"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"e_1_3_2_2_59_1","volume-title":"From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Transactions of the Association for Computational Linguistics","author":"Young Peter","year":"2014","unstructured":"Peter Young, Alice Lai, Micah Hodosh, and Julia Hockenmaier. 2014. From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Transactions of the Association for Computational Linguistics (2014)."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01061"},{"key":"e_1_3_2_2_62_1","volume-title":"Weaktr: Exploring plain vision transformer for weakly-supervised semantic segmentation. arXiv preprint arXiv:2304.01184","author":"Zhu Lianghui","year":"2023","unstructured":"Lianghui Zhu, Yingyue Li, Jiemin Fang, Yan Liu, Hao Xin, Wenyu Liu, and Xinggang Wang. 2023. Weaktr: Exploring plain vision transformer for weakly-supervised semantic segmentation. arXiv preprint arXiv:2304.01184 (2023)."},{"key":"e_1_3_2_2_63_1","volume-title":"WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition. arXiv preprint arXiv:2402.14812","author":"Zhu Lianghui","year":"2024","unstructured":"Lianghui Zhu, Junwei Zhou, Yan Liu, Xin Hao, Wenyu Liu, and Xinggang Wang. 2024. WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition. arXiv preprint arXiv:2402.14812 (2024). n"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680860","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680860","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:08Z","timestamp":1750295888000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680860"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":63,"alternative-id":["10.1145\/3664647.3680860","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680860","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"}}]}}