{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T04:18:30Z","timestamp":1744345110001,"version":"3.40.4"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819784929"},{"type":"electronic","value":"9789819784936"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-97-8493-6_7","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T20:02:16Z","timestamp":1730404936000},"page":"93-106","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-class Token-Guided End-to-End Weakly Supervised Image Semantic Segmentation Method"],"prefix":"10.1007","author":[{"given":"Yifan","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijun","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Wang, H., Ma, J., Chi, H.: Unmanned driving system based on deepLabV3+ semantic segmentation. In: 2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC), pp. 800\u2013803. IEEE (2021)","DOI":"10.1109\/YAC53711.2021.9486651"},{"key":"7_CR2","doi-asserted-by":"publisher","first-page":"103875","DOI":"10.1109\/ACCESS.2021.3099936","volume":"9","author":"M Kim","year":"2021","unstructured":"Kim, M., Lee, B.-D.: A simple generic method for effective boundary extraction in medical image segmentation. IEEE Access 9, 103875\u2013103884 (2021)","journal-title":"IEEE Access"},{"key":"7_CR3","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":"7_CR4","doi-asserted-by":"crossref","unstructured":"Lee, S., Lee, M., Lee, J., Shim, H.: 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":"7_CR5","first-page":"27408","volume":"34","author":"J Lee","year":"2021","unstructured":"Lee, J., Choi, J., Mok, J., Yoon, S.: Reducing information bottleneck for weakly supervised semantic segmentation. Adv. Neural. Inf. Process. Syst. 34, 27408\u201327421 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR6","unstructured":"Zhu, L., Li, Y., Fang, J., Liu, Y., Xin, H., Liu, W., Wang, X.: Weaktr: exploring plain vision transformer for weakly-supervised semantic segmentation. arXiv preprint arXiv:2304.01184 (2023)"},{"issue":"4","key":"7_CR7","doi-asserted-by":"publisher","first-page":"1127","DOI":"10.1007\/s11263-022-01586-9","volume":"130","author":"R Lixiang","year":"2022","unstructured":"Lixiang, R., Bo, D., Zhan, Y., Chen, W.: Weakly-supervised semantic segmentation with visual words learning and hybrid pooling. Int. J. Comput. Vision 130(4), 1127\u20131144 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"7_CR8","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: 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)","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Gao, W., Wan, F., Pan, X., Peng, Z., Tian, Q., Han, Z., Zhou, B., Ye, Q.: Ts-cam: token semantic coupled attention map for weakly supervised object localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2886\u20132895 (2021)","DOI":"10.1109\/ICCV48922.2021.00288"},{"key":"7_CR12","unstructured":"Sun, W., Zhang, J., Liu, Z., Zhong, Y., Barnes, N.: Getam: gradient-weighted element-wise transformer attention map for weakly-supervised semantic segmentation. arXiv preprint arXiv:2112.02841 (2021)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Xu, L., Ouyang, W., Bennamoun, M., Boussaid, F., Xu, D.: Multi-class token transformer for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 4310\u20134319 (2022)","DOI":"10.1109\/CVPR52688.2022.00427"},{"key":"7_CR14","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers. Adv. Neural Inf. process. syst. 34, 12077\u201312090 (2021)"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Yangyang, X., Yang, Y., Zhang, L.: Demt: deformable mixer transformer for multi-task learning of dense prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 3072\u20133080 (2023)","DOI":"10.1609\/aaai.v37i3.25411"},{"key":"7_CR16","unstructured":"Park, N., Kim, S.: How do vision transformers work? arXiv preprint arXiv:2202.06709 (2022)"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Ru, L., Zheng, H., Zhan, Y., Du, B.: 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":"7_CR18","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, 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":"7_CR19","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"7_CR20","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"7_CR21","unstructured":"van\u00a0den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Everingham, M., Van\u00a0Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88, 303\u2013338 (2010)","DOI":"10.1007\/s11263-009-0275-4"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: 2011 International Conference on Computer Vision, pp. 991\u2013998. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"7_CR24","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8493-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T19:10:34Z","timestamp":1744312234000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8493-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819784929","9789819784936"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8493-6_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}