{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T04:12:13Z","timestamp":1778731933645,"version":"3.51.4"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["252102211015"],"award-info":[{"award-number":["252102211015"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472145"],"award-info":[{"award-number":["62472145"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition Letters"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.patrec.2026.03.022","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T03:00:08Z","timestamp":1775098808000},"page":"120-126","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["ACA-ViT: Adaptive class-aware vision transformer with complementary CAMs for weakly-supervised semantic segmentation"],"prefix":"10.1016","volume":"204","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9243-5009","authenticated-orcid":false,"given":"Zhanqiang","family":"Huo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiankun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yijiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingxu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luyao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.patrec.2026.03.022_bib0001","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.neucom.2021.08.105","article-title":"Lane-DeepLab: lane semantic segmentation in automatic driving scenarios for high-definition maps","volume":"465","author":"Li","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patrec.2026.03.022_bib0002","doi-asserted-by":"crossref","first-page":"28430","DOI":"10.1109\/JSEN.2023.3321742","article-title":"SG-grasp: semantic segmentation guided robotic grasp oriented to weakly textured objects based on visual perception sensors","volume":"23","author":"Tong","year":"2023","journal-title":"IEEE Sens. J."},{"key":"10.1016\/j.patrec.2026.03.022_bib0003","unstructured":"D. Zhang, Y. Lin, H. Chen, T. Zhuotao, X. Yang, Understanding the tricks of deep learning in medical image segmentation: challenges and future directions, (2022) arXiv:abs\/2209.10307."},{"key":"10.1016\/j.patrec.2026.03.022_bib0004","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3159","article-title":"ScribbleSup: scribble-supervised convolutional networks for semantic segmentation","author":"Lin","year":"2016"},{"key":"10.1016\/j.patrec.2026.03.022_bib0005","series-title":"Computer Vision \u2013 ECCV 2016","first-page":"549","article-title":"What\u2019s the point: semantic segmentation with point supervision","author":"Bearman","year":"2016"},{"key":"10.1016\/j.patrec.2026.03.022_bib0006","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.patrec.2024.12.016","article-title":"Curriculum learning with class-label composition for weakly supervised semantic segmentation","volume":"188","author":"Hwang","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.03.022_bib0007","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.patrec.2024.04.006","article-title":"Weakly-supervised incremental learning for semantic segmentation with class hierarchy","volume":"182","author":"Kim","year":"2024","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.03.022_bib0008","unstructured":"L.-C. Chen, G. Papandreou, F. Schroff, H. Adam, Rethinking atrous convolution for semantic image segmentation, (2017) arXiv:abs\/1706.05587."},{"key":"10.1016\/j.patrec.2026.03.022_bib0009","series-title":"2018 IEEE Winter Conference on Applications of Computer Vision (WACV)","first-page":"1451","article-title":"Understanding convolution for semantic segmentation","author":"Wang","year":"2018"},{"key":"10.1016\/j.patrec.2026.03.022_bib0010","series-title":"2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4310","article-title":"Multi-class token transformer for weakly supervised semantic segmentation","author":"Xu","year":"2022"},{"key":"10.1016\/j.patrec.2026.03.022_bib0011","series-title":"International Conference on Learning Representations","article-title":"How do vision transformers work?","author":"Park","year":"2022"},{"key":"10.1016\/j.patrec.2026.03.022_bib0012","series-title":"2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3093","article-title":"Token contrast for weakly-supervised semantic segmentation","author":"Ru","year":"2023"},{"issue":"3","key":"10.1016\/j.patrec.2026.03.022_bib0013","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1109\/83.826787","article-title":"Image enhancement via adaptive unsharp masking","volume":"9","author":"Andrea","year":"2000","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patrec.2026.03.022_bib0014","series-title":"2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"7268","article-title":"Revisiting dilated convolution: a simple approach for weakly-and semi-supervised semantic segmentation","author":"Wei","year":"2018"},{"key":"10.1016\/j.patrec.2026.03.022_bib0015","series-title":"2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16765","article-title":"Embedded discriminative attention mechanism for weakly supervised semantic segmentation","author":"Wu","year":"2021"},{"key":"10.1016\/j.patrec.2026.03.022_bib0016","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2117","article-title":"Activation modulation and recalibration scheme for weakly supervised semantic segmentation","author":"Qin","year":"2022"},{"key":"10.1016\/j.patrec.2026.03.022_bib0017","series-title":"2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4981","article-title":"Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation","author":"Ahn","year":"2018"},{"key":"10.1016\/j.patrec.2026.03.022_bib0018","series-title":"2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2209","article-title":"Weakly supervised learning of instance segmentation with inter-pixel relations","author":"Ahn","year":"2019"},{"issue":"3","key":"10.1016\/j.patrec.2026.03.022_bib0019","doi-asserted-by":"crossref","first-page":"1618","DOI":"10.1109\/TPAMI.2022.3166916","article-title":"Anti-adversarially manipulated attributions for weakly supervised semantic segmentation and object localization","volume":"46","author":"Lee","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patrec.2026.03.022_bib0020","series-title":"2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16846","article-title":"Learning affinity from attention: end-to-end weakly-supervised semantic segmentation with transformers","author":"Ru","year":"2022"},{"key":"10.1016\/j.patrec.2026.03.022_bib0021","series-title":"2021 IEEE International Conference on Computer Vision (ICCV)","first-page":"6984","article-title":"Leveraging auxiliary tasks with affinity learning for weakly supervised semantic segmentation","author":"Xu","year":"2021"},{"key":"10.1016\/j.patrec.2026.03.022_bib0022","doi-asserted-by":"crossref","unstructured":"L. Ru, B. Du, Y. Zhan, C. Wu, Weakly-supervised semantic segmentation with visual words learning and hybrid pooling, (2022) arXiv:abs\/2202.04812.","DOI":"10.1007\/s11263-022-01586-9"},{"key":"10.1016\/j.patrec.2026.03.022_bib0023","series-title":"2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5495","article-title":"Railroad is not a train: saliency as pseudo-pixel supervision for weakly supervised semantic segmentation","author":"Lee","year":"2021"},{"key":"10.1016\/j.patrec.2026.03.022_bib0024","series-title":"2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16897","article-title":"Weakly supervised semantic segmentation using out-of-distribution data","author":"Lee","year":"2022"},{"key":"10.1016\/j.patrec.2026.03.022_bib0025","series-title":"2021 IEEE International Conference on Computer Vision (ICCV)","first-page":"9650","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"key":"10.1016\/j.patrec.2026.03.022_bib0026","unstructured":"L. Zhu, L. Zhu, J. Fang, Y. Liu, H. Xin, W. Liu, X. Wang, WeakTr: exploring plain vision transformer for weakly-supervised semantic segmentation, (2023) arXiv:abs\/2304.01184."},{"key":"10.1016\/j.patrec.2026.03.022_bib0027","series-title":"International Conference on Learning Representations","article-title":"Anti-oversmoothing in deep vision transformers via the fourier domain analysis: from theory to practice","author":"Wang","year":"2022"},{"key":"10.1016\/j.patrec.2026.03.022_bib0028","article-title":"PatchSkip: a lightweight technique for effectively alleviating over-smoothing in vision transformers","volume":"600","author":"Jiafeng","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patrec.2026.03.022_bib0029","series-title":"Advances in Neural Information Processing Systems","first-page":"80233","article-title":"Mitigating over-smoothing in transformers via regularized nonlocal functionals","volume":"36","author":"Nguyen","year":"2023"},{"key":"10.1016\/j.patrec.2026.03.022_bib0030","series-title":"Computer Vision \u2013 ECCV 2016","first-page":"695","article-title":"Seed, expand and constrain: three principles for weakly-supervised image segmentations","author":"Kolesnikov","year":"2016"},{"key":"10.1016\/j.patrec.2026.03.022_bib0031","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.patrec.2026.03.022_bib0032","series-title":"Computer Vision \u2013 ECCV 2014","first-page":"740","article-title":"Microsoft CoCo: common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.patrec.2026.03.022_bib0033","series-title":"2011 IEEE International Conference on Computer Vision (ICCV)","first-page":"991","article-title":"Semantic contours from inverse detectors","author":"Hariharan","year":"2011"},{"key":"10.1016\/j.patrec.2026.03.022_bib0034","series-title":"2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"12275","article-title":"Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation","author":"Wang","year":"2020"},{"key":"10.1016\/j.patrec.2026.03.022_bib0035","series-title":"International Conference on Neural Information Processing Systems","first-page":"109","article-title":"Efficient inference in fully connected crfs with gaussian edge potentials","author":"Kr\u00e4henb\u00fchl","year":"2011"},{"key":"10.1016\/j.patrec.2026.03.022_bib0036","series-title":"Computer Vision \u2013 ECCV 2022","first-page":"446","article-title":"Max pooling with vision transformers reconciles class and shape in weakly supervised semantic segmentation","author":"Rossetti","year":"2022"},{"key":"10.1016\/j.patrec.2026.03.022_bib0037","series-title":"2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"969","article-title":"Class re-activation maps for weakly-supervised semantic segmentation","author":"Chen","year":"2022"},{"key":"10.1016\/j.patrec.2026.03.022_bib0038","series-title":"2021 IEEE International Conference on Computer Vision (ICCV)","first-page":"7283","article-title":"ECS-Net: improving weakly supervised semantic segmentation by using connections between class activation maps","author":"Sun","year":"2021"},{"key":"10.1016\/j.patrec.2026.03.022_bib0039","series-title":"2023 IEEE International Conference on Computer Vision (ICCV)","first-page":"826","article-title":"All-pairs consistency learning forweakly supervised semantic segmentation","author":"Sun","year":"2023"},{"key":"10.1016\/j.patrec.2026.03.022_bib0040","series-title":"2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16886","article-title":"L2G: a simple local-to-global knowledge transfer framework for weakly supervised semantic segmentation","author":"Jiang","year":"2022"},{"key":"10.1016\/j.patrec.2026.03.022_bib0041","series-title":"2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4071","article-title":"Anti-adversarially manipulated attributions for weakly and semi-supervised semantic segmentation","author":"Lee","year":"2021"},{"key":"10.1016\/j.patrec.2026.03.022_bib0042","series-title":"2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4288","article-title":"Self-supervised image-specific prototype exploration for weakly supervised semantic segmentation","author":"Chen","year":"2022"}],"container-title":["Pattern Recognition Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526001212?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526001212?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T03:31:45Z","timestamp":1778729505000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167865526001212"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":42,"alternative-id":["S0167865526001212"],"URL":"https:\/\/doi.org\/10.1016\/j.patrec.2026.03.022","relation":{},"ISSN":["0167-8655"],"issn-type":[{"value":"0167-8655","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ACA-ViT: Adaptive class-aware vision transformer with complementary CAMs for weakly-supervised semantic segmentation","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition Letters","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patrec.2026.03.022","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}