{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T11:27:15Z","timestamp":1786966035342,"version":"build-2736575974"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006041"],"award-info":[{"award-number":["62006041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"General Program of Nantong Natural Science Foundation","award":["JC2025058"],"award-info":[{"award-number":["JC2025058"]}]},{"name":"Research Fund for Advanced Ocean Institute of Southeast University","award":["MP202404"],"award-info":[{"award-number":["MP202404"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s00530-026-02496-3","type":"journal-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:45:37Z","timestamp":1784180737000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Self-visual prompting for training-free recursive weakly supervised semantic segmentation"],"prefix":"10.1007","volume":"32","author":[{"given":"Congwei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhibin","family":"Quan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuncong","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wankou","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"key":"2496_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, J., Kwak, S.: Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4981\u20134990 (2018)","DOI":"10.1109\/CVPR.2018.00523"},{"key":"2496_CR2","doi-asserted-by":"crossref","unstructured":"Ahn, J., Cho, S., Kwak, S.: Weakly supervised learning of instance segmentation with inter-pixel relations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2209\u20132218 (2019)","DOI":"10.1109\/CVPR.2019.00231"},{"key":"2496_CR3","unstructured":"Bahng, H., Jahanian, A., Sankaranarayanan, S., et al. Exploring visual prompts for adapting large-scale models (2022a). arXiv preprint arXiv:2203.17274"},{"key":"2496_CR4","unstructured":"Bahng, H., Jahanian, A., Sankaranarayanan, S., et al. Visual prompting: Modifyingpixel space to adapt pre-trained models 3(11-12):3 (2022b). arXiv preprint arXiv:2203.17274"},{"key":"2496_CR5","doi-asserted-by":"crossref","unstructured":"Bearman, A., Russakovsky, O., Ferrari, V.: What\u2019s the point: Semantic segmentation with point supervision. In: European Conference on Computer Vision, pp. 549\u2013565. Springer (2016)","DOI":"10.1007\/978-3-319-46478-7_34"},{"key":"2496_CR6","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"2496_CR7","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., et al.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2496_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Q., Yang, L., Lai, J.H.: Self-supervised image-specific prototype exploration for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4288\u20134298 (2022)","DOI":"10.1109\/CVPR52688.2022.00425"},{"key":"2496_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Qiao, P., Li, K.: Out-of-candidate rectification for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23673\u201323684 (2023)","DOI":"10.1109\/CVPR52729.2023.02267"},{"issue":"1","key":"2496_CR10","doi-asserted-by":"publisher","first-page":"2262","DOI":"10.1038\/s41467-025-56505-6","volume":"16","author":"Y Chu","year":"2025","unstructured":"Chu, Y., Luo, G., Zhou, L., et al.: Deep learning-driven pulmonary artery and vein segmentation reveals demography-associated vasculature anatomical differences. Nat. Commun. 16(1), 2262 (2025)","journal-title":"Nat. Commun."},{"key":"2496_CR11","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: Boxsup: Exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1635\u20131643 (2015)","DOI":"10.1109\/ICCV.2015.191"},{"key":"2496_CR12","doi-asserted-by":"crossref","unstructured":"Du, Y., Fu, Z., Liu, Q.: Weakly supervised semantic segmentation by pixel-to-prototype contrast. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4320\u20134329 (2022)","DOI":"10.1109\/CVPR52688.2022.00428"},{"key":"2496_CR13","unstructured":"Everingham, M., Van Gool, L., Williams, C., et al.: The pascal visual object classes challenge 2012 (voc2012) results.http:\/\/www.pascal-network.org\/challenges. In: VOC\/voc2012\/workshop\/index. html. (2012)"},{"key":"2496_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2024.104168","volume":"101","author":"Y Fu","year":"2024","unstructured":"Fu, Y., Wang, W., Zhu, L., et al.: Weakly supervised semantic segmentation based on superpixel affinity. J. Vis. Commun. Image Represent. 101, 104168 (2024)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"2496_CR15","doi-asserted-by":"crossref","unstructured":"Jia, M., Tang, L., Chen, B.C.: Visual prompt tuning. In: European Conference on Computer Vision, pp. 709\u2013727. Springer (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"2496_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, P.T., Hou, Q., Cao, Y.: Integral object mining via online attention accumulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2070\u20132079 (2019)","DOI":"10.1109\/ICCV.2019.00216"},{"key":"2496_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, P.T., Yang, Y., Hou, Q.: L2g: A simple local-to-global knowledge transfer framework for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16886\u201316896 (2022)","DOI":"10.1109\/CVPR52688.2022.01638"},{"key":"2496_CR18","doi-asserted-by":"crossref","unstructured":"Katsamenis, I., Protopapadakis, E., Bakalos, N.: A few-shot attention recurrent residual u-net for crack segmentation. In: International Symposium on Visual Computing, pp. 199\u2013209 Springer (2023)","DOI":"10.1007\/978-3-031-47969-4_16"},{"key":"2496_CR19","doi-asserted-by":"crossref","unstructured":"Kim, B., Han, S., Kim, J.: Discriminative region suppression for weakly-supervised semantic segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1754\u20131761 (2021)","DOI":"10.1609\/aaai.v35i2.16269"},{"key":"2496_CR20","unstructured":"Kumar, A., Raghunathan, A., Jones, R.: Fine-tuning can distort pretrained features and underperform out-of-distribution (2022). arXiv preprint arXiv:2202.10054"},{"key":"2496_CR21","doi-asserted-by":"crossref","unstructured":"Kweon, H., Yoon, S.H., Kim, H.: Unlocking the potential of ordinary classifier: Class-specific adversarial erasing framework for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6994\u20137003 (2021)","DOI":"10.1109\/ICCV48922.2021.00691"},{"key":"2496_CR22","doi-asserted-by":"crossref","unstructured":"Kweon, H., Yoon, S.H., Yoon, K.J.: Weakly supervised semantic segmentation via adversarial learning of classifier and reconstructor. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11329\u201311339 (2023)","DOI":"10.1109\/CVPR52729.2023.01090"},{"key":"2496_CR23","doi-asserted-by":"crossref","unstructured":"Lee, J., Oh, S.J., Yun, S.: Weakly supervised semantic segmentation using out-of-distribution data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16897\u201316906 (2022)","DOI":"10.1109\/CVPR52688.2022.01639"},{"key":"2496_CR24","doi-asserted-by":"crossref","unstructured":"Lee, S., Lee, M., Lee, J., et al.: Railroad is not a train: Saliency as pseudo-pixel supervision for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5495\u20135505 (2021)","DOI":"10.1109\/CVPR46437.2021.00545"},{"key":"2496_CR25","doi-asserted-by":"crossref","unstructured":"Li, F., Jiang, Q., Zhang, H.: Visual in-context prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12861\u201312871 (2024)","DOI":"10.1109\/CVPR52733.2024.01222"},{"key":"2496_CR26","doi-asserted-by":"crossref","unstructured":"Li J, Fan, J., Zhang, Z.: Towards noiseless object contours for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 16856\u201316865 (2022a)","DOI":"10.1109\/CVPR52688.2022.01635"},{"key":"2496_CR27","doi-asserted-by":"crossref","unstructured":"Li, Y., Duan, Y., Kuang, Z., et al.: Uncertainty estimation via response scaling for pseudo-mask noise mitigation in weakly-supervised semantic segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1447\u20131455 (2022b)","DOI":"10.1609\/aaai.v36i2.20034"},{"key":"2496_CR28","doi-asserted-by":"crossref","unstructured":"Lin, D., Dai, J., Jia, J.: Scribblesup: scribble-supervised convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3159\u20133167 (2016)","DOI":"10.1109\/CVPR.2016.344"},{"key":"2496_CR29","doi-asserted-by":"crossref","unstructured":"Lin. T.Y., Maire, M., Belongie, S., et al.: Microsoft coco: common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part V 13, Springer, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2496_CR30","doi-asserted-by":"crossref","unstructured":"Lin, Y., Chen, M., Wang, W.: 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, pp. 15305\u201315314 (2023)","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"2496_CR31","doi-asserted-by":"crossref","unstructured":"Mao, X., Xing, X., Meng, F.: One polyp identifies all: one-shot polyp segmentation with sam via cascaded priors and iterative prompt evolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 24182\u201324191 (2025)","DOI":"10.1109\/ICCV51701.2025.02241"},{"key":"2496_CR32","doi-asserted-by":"crossref","unstructured":"Murugesan, B., Hussain, R., Bhattacharya, R.: Prompting classes: Exploring the power of prompt class learning in weakly supervised semantic segmentation (2023). arXiv preprint arXiv:2307.00097","DOI":"10.1109\/WACV57701.2024.00036"},{"key":"2496_CR33","doi-asserted-by":"crossref","unstructured":"Rong, S., Tu, B., Wang, Z.: Boundary-enhanced co-training for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19574\u201319584 (2023)","DOI":"10.1109\/CVPR52729.2023.01875"},{"key":"2496_CR34","doi-asserted-by":"crossref","unstructured":"Ru, L., Zhan, Y., Yu, B.: Learning affinity from attention: End-to-end weakly-supervised semantic segmentation with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16846\u201316855 (2022)","DOI":"10.1109\/CVPR52688.2022.01634"},{"key":"2496_CR35","doi-asserted-by":"crossref","unstructured":"Ru, L., Zheng, H., Zhan, Y.: Token contrast for weakly-supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3093\u20133102 (2023)","DOI":"10.1109\/CVPR52729.2023.00302"},{"key":"2496_CR36","doi-asserted-by":"crossref","unstructured":"Shtedritski, A., Rupprecht, C., Vedaldi, A.: What does clip know about a red circle? visual prompt engineering for vlms. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11987\u201311997 (2023)","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"2496_CR37","unstructured":"Vaswani, A., Shazeer, N., Parmar, N.: Attention is all you need. Advances in neural information processing systems 30, (2017)"},{"key":"2496_CR38","doi-asserted-by":"crossref","unstructured":"Wang, C., Xu, R., Xu, S., et al.: Treating pseudo-labels generation as image matting for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp 755\u2013765 (2023)","DOI":"10.1109\/ICCV51070.2023.00076"},{"key":"2496_CR39","doi-asserted-by":"crossref","unstructured":"Wang, S., Cheng, D., Li, J.: Diffusion prior guided deep model driven network for infrared and visible image fusion. Expert Syst Appl, 129161 (2025a)","DOI":"10.1016\/j.eswa.2025.129161"},{"issue":"2","key":"2496_CR40","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1007\/s13042-025-02851-2","volume":"17","author":"S Wang","year":"2026","unstructured":"Wang, S., Zhang, X., Ren, L., et al.: Hct-net: hybrid cnn-transformer network with multi-scale feature aggregation and progressive decode for medical image segmentation. Int. J. Mach. Learn. Cybern. 17(2), 76 (2026)","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"2496_CR41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111566","volume":"165","author":"Y Wang","year":"2025","unstructured":"Wang, Y., Schaefer, G., Liu, X., et al.: Class activation map guided level sets for weakly supervised semantic segmentation. Pattern Recogn. 165, 111566 (2025)","journal-title":"Pattern Recogn."},{"key":"2496_CR42","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chen, Z., Liu, C., et al.: Ucgm: Enhancing pseudo labels via uncertainty and cross-image gaussian mixture model for semi-supervised semantic segmentation. Expert Syst. Appl., 129120 (2025c)","DOI":"10.1016\/j.eswa.2025.129120"},{"key":"2496_CR43","doi-asserted-by":"crossref","unstructured":"Wortsman, M., Ilharco, G., Kim, J.W.: Robust fine-tuning of zero-shot models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7959\u20137971 (2022)","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"2496_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109626","volume":"139","author":"W Wu","year":"2025","unstructured":"Wu, W., Dai, T., Chen, Z., et al.: Adaptive patch contrast for weakly supervised semantic segmentation. Eng. Appl. Artif. Intell. 139, 109626 (2025)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"2496_CR45","doi-asserted-by":"crossref","unstructured":"Wu, W., Qiu, X., Song, S., et al.: Prompt categories cluster for weakly supervised semantic segmentation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp 3198\u20133207 (2025b)","DOI":"10.1109\/CVPRW67362.2025.00302"},{"key":"2496_CR46","doi-asserted-by":"crossref","unstructured":"Wu, Y., Li, X., Li, J., et al.: Dino is also a semantic guider: Exploiting class-aware affinity for weakly supervised semantic segmentation. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 1389\u20131397 (2024)","DOI":"10.1145\/3664647.3681710"},{"key":"2496_CR47","doi-asserted-by":"crossref","unstructured":"Xie, J., Hou, X., Ye, K.: Clims: Cross language image matching for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4483\u20134492 (2022)","DOI":"10.1109\/CVPR52688.2022.00444"},{"key":"2496_CR48","doi-asserted-by":"crossref","unstructured":"Xu, L., Ouyang, W., Bennamoun, M.: Leveraging auxiliary tasks with affinity learning for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6984\u20136993 (2021)","DOI":"10.1109\/ICCV48922.2021.00690"},{"key":"2496_CR49","doi-asserted-by":"crossref","unstructured":"Xu, L., Bennamoun, M., Boussaid, F., et al. Mctformer+: multi-class token transformer for weakly supervised semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3404422"},{"key":"2496_CR50","doi-asserted-by":"crossref","unstructured":"Yang, Z., Fu, K., Duan, M.: 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, pp. 3606\u20133615 (2024)","DOI":"10.1109\/CVPR52733.2024.00346"},{"key":"2496_CR51","doi-asserted-by":"crossref","unstructured":"Yang, Z., Meng, Y., Fu, K., et al.: Exploring clip\u2019s dense knowledge for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20223\u201320232 (2025a)","DOI":"10.1109\/CVPR52734.2025.01883"},{"key":"2496_CR52","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111348","volume":"162","author":"Z Yang","year":"2025","unstructured":"Yang, Z., Zhao, X., Yao, C., et al.: M-see: a multi-scale encoder enhancement framework for end-to-end weakly supervised semantic segmentation. Pattern Recogn. 162, 111348 (2025)","journal-title":"Pattern Recogn."},{"key":"2496_CR53","doi-asserted-by":"crossref","unstructured":"Yao, Y., Chen, T., Xie, G.S.: Non-salient region object mining for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2623\u20132632 (2021)","DOI":"10.1109\/CVPR46437.2021.00265"},{"key":"2496_CR54","doi-asserted-by":"crossref","unstructured":"Yin, X., Im, W., Min, D.: Fine-grained background representation for weakly supervised semantic segmentation. In: IEEE Transactions on Circuits and Systems for Video Technology (2024)","DOI":"10.1109\/TCSVT.2024.3419106"},{"key":"2496_CR55","doi-asserted-by":"crossref","unstructured":"Yu, R., Yu, W., Wang, X.: Attention prompting on image for large vision-language models. In: European Conference on Computer Vision, Springer, pp. 251\u2013268 (2024)","DOI":"10.1007\/978-3-031-73404-5_15"},{"issue":"3","key":"2496_CR56","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1007\/s11263-023-01919-2","volume":"132","author":"W Zhai","year":"2024","unstructured":"Zhai, W., Wu, P., Zhu, K., et al.: Background activation suppression for weakly supervised object localization and semantic segmentation. Int. J. Comput. Vis. 132(3), 750\u2013775 (2024)","journal-title":"Int. J. Comput. Vis."},{"key":"2496_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, B., Yu, S., Wei, Y.: Frozen clip: A strong backbone for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3796\u20133806 (2024)","DOI":"10.1109\/CVPR52733.2024.00364"},{"key":"2496_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, F., Gu, C., Zhang, C., et al.: Complementary patch for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7242\u20137251 (2021)","DOI":"10.1109\/ICCV48922.2021.00715"},{"key":"2496_CR59","doi-asserted-by":"crossref","unstructured":"Zhao, X., Tang, F., Wang, X.: Sfc: Shared feature calibration in weakly supervised semantic segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 7525\u20137533 (2024)","DOI":"10.1609\/aaai.v38i7.28584"},{"key":"2496_CR60","doi-asserted-by":"crossref","unstructured":"Zheng, M., Hao, Z., Tang, Y.: Visual prompting via partial optimal transport. In: European Conference on Computer Vision, pp. 1\u201318 Springer (2024)","DOI":"10.1007\/978-3-031-72761-0_1"},{"key":"2496_CR61","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"},{"key":"2496_CR62","doi-asserted-by":"crossref","unstructured":"Zhou, T., Zhang, M., Zhao, F.: Regional semantic contrast and aggregation for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4299\u20134309 (2022)","DOI":"10.1109\/CVPR52688.2022.00426"},{"issue":"3","key":"2496_CR63","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1007\/s11263-024-02224-2","volume":"133","author":"L Zhu","year":"2025","unstructured":"Zhu, L., Wang, X., Feng, J., et al.: Weakclip: adapting clip for weakly-supervised semantic segmentation. Int. J. Comput. Vis. 133(3), 1085\u20131105 (2025)","journal-title":"Int. J. Comput. Vis."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02496-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02496-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02496-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T11:03:10Z","timestamp":1786964590000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02496-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"references-count":63,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["2496"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02496-3","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]},"assertion":[{"value":"28 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"443"}}