{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T09:05:48Z","timestamp":1784279148504,"version":"3.55.0"},"reference-count":41,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113851","type":"journal-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T06:30:54Z","timestamp":1777271454000},"page":"113851","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["CDSP: Enhancing CLIP-based weakly supervised semantic segmentation with dataset-specific prototypes"],"prefix":"10.1016","volume":"179","author":[{"given":"Yujie","family":"Diao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiguo","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuewei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113851_b1","doi-asserted-by":"crossref","unstructured":"B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, A. Torralba, Learning deep features for discriminative localization, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2921\u20132929.","DOI":"10.1109\/CVPR.2016.319"},{"key":"10.1016\/j.patcog.2026.113851_b2","doi-asserted-by":"crossref","unstructured":"R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, D. Batra, Grad-cam: Visual explanations from deep networks via gradient-based localization, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"key":"10.1016\/j.patcog.2026.113851_b3","doi-asserted-by":"crossref","unstructured":"J. Ahn, S. Cho, S. Kwak, Weakly supervised learning of instance segmentation with inter-pixel relations, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 2209\u20132218.","DOI":"10.1109\/CVPR.2019.00231"},{"key":"10.1016\/j.patcog.2026.113851_b4","doi-asserted-by":"crossref","unstructured":"Y. Lin, M. Chen, W. Wang, B. Wu, K. Li, B. Lin, H. Liu, X. He, Clip is also an efficient segmenter: A text-driven approach for weakly supervised semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 15305\u201315314.","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"10.1016\/j.patcog.2026.113851_b5","doi-asserted-by":"crossref","unstructured":"Z. Yang, K. Fu, M. Duan, L. Qu, S. Wang, Z. Song, Separate and conquer: Decoupling co-occurrence via decomposition and representation for weakly supervised semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 3606\u20133615.","DOI":"10.1109\/CVPR52733.2024.00346"},{"key":"10.1016\/j.patcog.2026.113851_b6","doi-asserted-by":"crossref","unstructured":"B. Zhang, S. Yu, Y. Wei, Y. Zhao, J. Xiao, Frozen clip: A strong backbone for weakly supervised semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 3796\u20133806.","DOI":"10.1109\/CVPR52733.2024.00364"},{"key":"10.1016\/j.patcog.2026.113851_b7","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113851_b8","doi-asserted-by":"crossref","unstructured":"J. Xie, X. Hou, K. Ye, L. Shen, Clims: Cross language image matching for weakly supervised semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4483\u20134492.","DOI":"10.1109\/CVPR52688.2022.00444"},{"key":"10.1016\/j.patcog.2026.113851_b9","doi-asserted-by":"crossref","unstructured":"P. Vernaza, M. Chandraker, Learning random-walk label propagation for weakly-supervised semantic segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 7158\u20137166.","DOI":"10.1109\/CVPR.2017.315"},{"key":"10.1016\/j.patcog.2026.113851_b10","doi-asserted-by":"crossref","unstructured":"Z. Yang, Y. Meng, K. Fu, F. Tang, S. Wang, Z. Song, Exploring CLIP\u2019s Dense Knowledge for Weakly Supervised Semantic Segmentation, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 20223\u201320232.","DOI":"10.1109\/CVPR52734.2025.01883"},{"key":"10.1016\/j.patcog.2026.113851_b11","series-title":"European Conference on Computer Vision","first-page":"441","article-title":"Knowledge transfer with simulated inter-image erasing for weakly supervised semantic segmentation","author":"Chen","year":"2024"},{"key":"10.1016\/j.patcog.2026.113851_b12","doi-asserted-by":"crossref","unstructured":"J. Lee, E. Kim, S. Yoon, Anti-adversarially manipulated attributions for weakly and semi-supervised semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 4071\u20134080.","DOI":"10.1109\/CVPR46437.2021.00406"},{"key":"10.1016\/j.patcog.2026.113851_b13","doi-asserted-by":"crossref","unstructured":"Z. Chen, T. Wang, X. Wu, X.-S. Hua, H. Zhang, Q. Sun, Class re-activation maps for weakly-supervised semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 969\u2013978.","DOI":"10.1109\/CVPR52688.2022.00104"},{"key":"10.1016\/j.patcog.2026.113851_b14","doi-asserted-by":"crossref","unstructured":"Z. Chen, Q. Sun, Extracting class activation maps from non-discriminative features as well, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 3135\u20133144.","DOI":"10.1109\/CVPR52729.2023.00306"},{"key":"10.1016\/j.patcog.2026.113851_b15","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.patcog.2026.113851_b16","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2024.3404422","article-title":"Mctformer+: Multi-class token transformer for weakly supervised semantic segmentation","author":"Xu","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113851_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110922","article-title":"Complementary branch fusing class and semantic knowledge for robust weakly supervised semantic segmentation","volume":"157","author":"Han","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113851_b18","doi-asserted-by":"crossref","unstructured":"Y. Wang, J. Zhang, M. Kan, S. Shan, X. Chen, Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 12275\u201312284.","DOI":"10.1109\/CVPR42600.2020.01229"},{"issue":"2","key":"10.1016\/j.patcog.2026.113851_b19","doi-asserted-by":"crossref","first-page":"876","DOI":"10.1214\/aoms\/1177703591","article-title":"A relationship between arbitrary positive matrices and doubly stochastic matrices","volume":"35","author":"Sinkhorn","year":"1964","journal-title":"Ann. Math. Stat."},{"key":"10.1016\/j.patcog.2026.113851_b20","series-title":"ECAI 2023","first-page":"2938","article-title":"Region-specific prototype customization for weakly supervised semantic segmentation","author":"Yu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113851_b21","doi-asserted-by":"crossref","unstructured":"T. Zhou, W. Wang, E. Konukoglu, L. Van Gool, Rethinking semantic segmentation: A prototype view, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 2582\u20132593.","DOI":"10.1109\/CVPR52688.2022.00261"},{"key":"10.1016\/j.patcog.2026.113851_b22","series-title":"ECAI 2024","first-page":"218","article-title":"Pixel-wise reclassification with prototypes for enhancing weakly supervised semantic segmentation","author":"Diao","year":"2024"},{"key":"10.1016\/j.patcog.2026.113851_b23","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"4","key":"10.1016\/j.patcog.2026.113851_b24","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113851_b25","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113851_b26","series-title":"Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.patcog.2026.113851_b27","doi-asserted-by":"crossref","unstructured":"S.-H. Yoon, H. Kwon, H. Kim, K.-J. Yoon, Class tokens infusion for weakly supervised semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 3595\u20133605.","DOI":"10.1109\/CVPR52733.2024.00345"},{"key":"10.1016\/j.patcog.2026.113851_b28","doi-asserted-by":"crossref","unstructured":"F. Tang, Z. Xu, Z. Qu, W. Feng, X. Jiang, Z. Ge, Hunting attributes: Context prototype-aware learning for weakly supervised semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 3324\u20133334.","DOI":"10.1109\/CVPR52733.2024.00320"},{"key":"10.1016\/j.patcog.2026.113851_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112452","article-title":"Layerclip: A fine-grained class activation map for weakly supervised semantic segmentation","volume":"172","author":"Sun","year":"2026","journal-title":"Pattern Recognit.","ISSN":"https:\/\/id.crossref.org\/issn\/0031-3203","issn-type":"print"},{"key":"10.1016\/j.patcog.2026.113851_b30","doi-asserted-by":"crossref","unstructured":"M. Lee, D. Kim, H. Shim, Threshold matters in wsss: Manipulating the activation for the robust and accurate segmentation model against thresholds, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4330\u20134339.","DOI":"10.1109\/CVPR52688.2022.00429"},{"key":"10.1016\/j.patcog.2026.113851_b31","doi-asserted-by":"crossref","unstructured":"S. Rong, B. Tu, Z. Wang, J. Li, Boundary-enhanced co-training for weakly supervised semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19574\u201319584.","DOI":"10.1109\/CVPR52729.2023.01875"},{"key":"10.1016\/j.patcog.2026.113851_b32","article-title":"Modeling the label distributions for weakly-supervised semantic segmentation","author":"Wu","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113851_b33","doi-asserted-by":"crossref","unstructured":"X. Zhao, Z. Yang, T. Dai, B. Zhang, J. Xiao, PSDPM: Prototype-based secondary discriminative pixels mining for weakly supervised semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 3437\u20133446.","DOI":"10.1109\/CVPR52733.2024.00330"},{"key":"10.1016\/j.patcog.2026.113851_b34","doi-asserted-by":"crossref","unstructured":"L. Ru, H. Zheng, Y. Zhan, B. Du, Token contrast for weakly-supervised semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 3093\u20133102.","DOI":"10.1109\/CVPR52729.2023.00302"},{"key":"10.1016\/j.patcog.2026.113851_b35","doi-asserted-by":"crossref","unstructured":"Y. Wu, X. Ye, K. Yang, J. Li, X. Li, Dupl: Dual student with trustworthy progressive learning for robust weakly supervised semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 3534\u20133543.","DOI":"10.1109\/CVPR52733.2024.00339"},{"key":"10.1016\/j.patcog.2026.113851_b36","doi-asserted-by":"crossref","unstructured":"X. Xu, P. Zhang, W. Huang, Y. Shen, H. Chen, J. Lin, W. Li, G. He, J. Xie, S. Lin, Weakly Supervised Semantic Segmentation via Progressive Confidence Region Expansion, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 9829\u20139838.","DOI":"10.1109\/CVPR52734.2025.00918"},{"key":"10.1016\/j.patcog.2026.113851_b37","first-page":"9400","article-title":"More: Class patch attention needs regularization for weakly supervised semantic segmentation","volume":"vol. 39","author":"Yang","year":"2025"},{"key":"10.1016\/j.patcog.2026.113851_b38","doi-asserted-by":"crossref","unstructured":"Z. Yang, X. Zhao, X. Wang, Q. Zhang, J. Xiao, FFR: Frequency Feature Rectification for Weakly Supervised Semantic Segmentation, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 30261\u201330270.","DOI":"10.1109\/CVPR52734.2025.02817"},{"key":"10.1016\/j.patcog.2026.113851_b39","series-title":"European Conference on Computer Vision","first-page":"248","article-title":"DIAL: Dense image-text alignment for weakly supervised semantic segmentation","author":"Jang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113851_b40","doi-asserted-by":"crossref","unstructured":"J. Fang, Y. Ning, X. Nie, X. Liu, Z. Cheng, VLHP: Learning Discriminative Vision-Language Hybrid Prototypes for Weakly Supervised Semantic Segmentation, in: Proceedings of the 33rd ACM International Conference on Multimedia, 2025, pp. 2939\u20132948.","DOI":"10.1145\/3746027.3754893"},{"key":"10.1016\/j.patcog.2026.113851_b41","article-title":"BACF: Boundary-aware collaborative framework for weakly supervised semantic segmentation","author":"Lu","year":"2025","journal-title":"Pattern Recognit."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326008162?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326008162?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T08:29:57Z","timestamp":1784276997000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326008162"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":41,"alternative-id":["S0031320326008162"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113851","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CDSP: Enhancing CLIP-based weakly supervised semantic segmentation with dataset-specific prototypes","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113851","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113851"}}