{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T20:28:09Z","timestamp":1777321689133,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","funder":[{"name":"Major Basic Research Project of Shandong Provincial Natural Science Foundation","award":["ZR2024ZD03"],"award-info":[{"award-number":["ZR2024ZD03"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176141 and 62272254"],"award-info":[{"award-number":["62176141 and 62272254"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010040","name":"Taishan Scholar Project of Shandong Province","doi-asserted-by":"publisher","award":["tsqn202103088"],"award-info":[{"award-number":["tsqn202103088"]}],"id":[{"id":"10.13039\/501100010040","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR202103010201"],"award-info":[{"award-number":["ZR202103010201"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754893","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"2939-2948","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["VLHP: Learning Discriminative Vision-Language Hybrid Prototypes for Weakly Supervised Semantic Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1184-9445","authenticated-orcid":false,"given":"Jingyuan","family":"Fang","sequence":"first","affiliation":[{"name":"School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6093-6752","authenticated-orcid":false,"given":"Yang","family":"Ning","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9644-9723","authenticated-orcid":false,"given":"Xiushan","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6480-7530","authenticated-orcid":false,"given":"Xinfeng","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1109-5028","authenticated-orcid":false,"given":"Zhiyong","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00108"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00425"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548353"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00365"},{"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 et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00428"},{"key":"e_1_3_2_1_7_1","volume-title":"Christopher KI Williams, John Winn, and Andrew Zisserman.","author":"Everingham Mark","year":"2010","unstructured":"Mark Everingham, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman. 2010. The pascal visual object classes (voc) challenge. International journal of computer vision, Vol. 88 (2010), 303-338."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6705"},{"key":"e_1_3_2_1_9_1","volume-title":"Spatial Frequency-Aware Self-Distillation for Weakly-Supervised Semantic Segmentation. In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1-5.","author":"Fang Jingyuan","year":"2025","unstructured":"Jingyuan Fang, Yang Ning, and Xiushan Nie. 2025. Spatial Frequency-Aware Self-Distillation for Weakly-Supervised Semantic Segmentation. In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1-5."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27980"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25159"},{"key":"e_1_3_2_1_13_1","volume-title":"Self-erasing network for integral object attention. Advances in neural information processing systems","author":"Hou Qibin","year":"2018","unstructured":"Qibin Hou, PengTao Jiang, Yunchao Wei, and Ming-Ming Cheng. 2018. Self-erasing network for integral object attention. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_14_1","volume-title":"DIAL: Dense Image-Text ALignment for Weakly Supervised Semantic Segmentation. In European Conference on Computer Vision. Springer, 248-266","author":"Jang Soojin","year":"2024","unstructured":"Soojin Jang, Jungmin Yun, Junehyoung Kwon, Eunju Lee, and Youngbin Kim. 2024. DIAL: Dense Image-Text ALignment for Weakly Supervised Semantic Segmentation. In European Conference on Computer Vision. Springer, 248-266."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00063"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28053"},{"key":"e_1_3_2_1_17_1","volume-title":"Efficient inference in fully connected crfs with gaussian edge potentials. Advances in neural information processing systems","author":"Kr\u00e4henb\u00fchl Philipp","year":"2011","unstructured":"Philipp Kr\u00e4henb\u00fchl and Vladlen Koltun. 2011. Efficient inference in fully connected crfs with gaussian edge potentials. Advances in neural information processing systems, Vol. 24 (2011)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.381"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00691"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01090"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01639"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3273592"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16294"},{"key":"e_1_3_2_1_24_1","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume":"35","author":"Liang Victor Weixin","year":"2022","unstructured":"Victor Weixin Liang, Yuhui Zhang, Yongchan Kwon, Serena Yeung, and James Y Zou. 2022. Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 17612-17625.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","first-page":"740","volume-title":"Switzerland","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_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548165"},{"key":"e_1_3_2_1_30_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01590-z"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681318"},{"key":"e_1_3_2_1_33_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_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01875"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_26"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01634"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00302"},{"key":"e_1_3_2_1_38_1","volume-title":"Prototypical networks for few-shot learning. Advances in neural information processing systems","author":"Snell Jake","year":"2017","unstructured":"Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_21"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00719"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00320"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02530"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681710"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00339"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00329"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00444"},{"key":"e_1_3_2_1_47_1","volume-title":"Semi-supervised semantic segmentation with prototype-based consistency regularization. Advances in neural information processing systems","author":"Xu Haiming","year":"2022","unstructured":"Haiming Xu, Lingqiao Liu, Qiuchen Bian, and Zhen Yang. 2022a. Semi-supervised semantic segmentation with prototype-based consistency regularization. Advances in neural information processing systems, Vol. 35 (2022), 26007-26020."},{"key":"e_1_3_2_1_48_1","volume-title":"Mctformer: Multi-class token transformer for weakly supervised semantic segmentation","author":"Xu Lian","year":"2024","unstructured":"Lian Xu, Mohammed Bennamoun, Farid Boussaid, Hamid Laga, Wanli Ouyang, and Dan Xu. 2024a. Mctformer: Multi-class token transformer for weakly supervised semantic segmentation. IEEE transactions on pattern analysis and machine intelligence (2024)."},{"key":"e_1_3_2_1_49_1","volume-title":"Auxiliary tasks enhanced dual-affinity learning for weakly supervised semantic segmentation","author":"Xu Lian","year":"2024","unstructured":"Lian Xu, Mohammed Bennamoun, Farid Boussaid, Wanli Ouyang, Ferdous Sohel, and Dan Xu. 2024b. Auxiliary tasks enhanced dual-affinity learning for weakly supervised semantic segmentation. IEEE Transactions on Neural Networks and Learning Systems (2024)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00427"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01877"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25408"},{"key":"e_1_3_2_1_53_1","first-page":"21969","article-title":"Attribute prototype network for zero-shot learning","volume":"33","author":"Xu Wenjia","year":"2020","unstructured":"Wenjia Xu, Yongqin Xian, Jiuniu Wang, Bernt Schiele, and Zeynep Akata. 2020. Attribute prototype network for zero-shot learning. Advances in Neural Information Processing Systems, Vol. 33 (2020), 21969-21980.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_45"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00346"},{"key":"e_1_3_2_1_56_1","volume-title":"Diffusion-Guided Weakly Supervised Semantic Segmentation. In European Conference on Computer Vision. Springer, 393-411","author":"Yoon Sung-Hoon","year":"2024","unstructured":"Sung-Hoon Yoon, Hoyong Kwon, Jaeseok Jeong, Daehee Park, and Kuk-Jin Yoon. 2024. Diffusion-Guided Weakly Supervised Semantic Segmentation. In European Conference on Computer Vision. Springer, 393-411."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00689"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475675"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28584"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387116"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00426"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681033"},{"key":"e_1_3_2_1_64_1","volume-title":"International Journal of Computer Vision","author":"Zhu Lianghui","year":"2024","unstructured":"Lianghui Zhu, Xinggang Wang, Jiapei Feng, Tianheng Cheng, Yingyue Li, Bo Jiang, Dingwen Zhang, and Junwei Han. 2024. WeakCLIP: Adapting CLIP for Weakly-Supervised Semantic Segmentation. International Journal of Computer Vision (2024), 1-21."}],"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\/3746027.3754893","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T03:58:21Z","timestamp":1765339101000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754893"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":64,"alternative-id":["10.1145\/3746027.3754893","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754893","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"}}]}}