{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T17:46:41Z","timestamp":1769190401181,"version":"3.49.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T00:00:00Z","timestamp":1730678400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T00:00:00Z","timestamp":1730678400000},"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":["No.U20B2062"],"award-info":[{"award-number":["No.U20B2062"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62227801"],"award-info":[{"award-number":["No.62227801"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62376024"],"award-info":[{"award-number":["No.62376024"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s11263-024-02275-5","type":"journal-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T19:03:57Z","timestamp":1730747037000},"page":"2096-2110","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Few Annotated Pixels and Point Cloud Based Weakly Supervised Semantic Segmentation of Driving Scenes"],"prefix":"10.1007","volume":"133","author":[{"given":"Huimin","family":"Ma","sequence":"first","affiliation":[]},{"given":"Sheng","family":"Yi","sequence":"additional","affiliation":[]},{"given":"Shijie","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Jiansheng","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,4]]},"reference":[{"issue":"11","key":"2275_CR1","doi-asserted-by":"crossref","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","volume":"34","author":"R Achanta","year":"2012","unstructured":"Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., & S\u00fcsstrunk, S. (2012). Slic superpixels compared to state-of-the-art superpixel methods. IEEE transactions on pattern analysis and machine intelligence, 34(11), 2274\u20132282.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"2275_CR2","doi-asserted-by":"crossref","unstructured":"Ahn, J., & Kwak, S. (2018). 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.","DOI":"10.1109\/CVPR.2018.00523"},{"key":"2275_CR3","doi-asserted-by":"crossref","unstructured":"Araslanov, N., & Roth, S. (2020). Single-stage semantic segmentation from image labels. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4253\u20134262.","DOI":"10.1109\/CVPR42600.2020.00431"},{"key":"2275_CR4","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-319-46478-7_34","volume-title":"Computer Vision \u2013 ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part VII","author":"Amy Bearman","year":"2016","unstructured":"Bearman, Amy, Russakovsky, Olga, Ferrari, Vittorio, & Fei-Fei, Li. (2016). What\u2019s the Point: Semantic Segmentation with Point Supervision. In Bastian Leibe, Jiri Matas, Nicu Sebe, & Max Welling (Eds.), Computer Vision \u2013 ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part VII (pp. 549\u2013565). Cham: Springer. https:\/\/doi.org\/10.1007\/978-3-319-46478-7_34"},{"key":"2275_CR5","doi-asserted-by":"crossref","unstructured":"Chang, Y. T., Wang, Q., Hung, W. C., Piramuthu, R., Tsai, Y. H., & Yang, M. H. (2020). Weakly-supervised semantic segmentation via sub-category exploration. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8991\u20139000.","DOI":"10.1109\/CVPR42600.2020.00901"},{"issue":"4","key":"2275_CR6","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2017). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, 40(4), 834\u2013848.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"2275_CR7","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., & Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv preprint[SPACE]arXiv:1706.05587 ."},{"key":"2275_CR8","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B. (2016). The cityscapes dataset for semantic urban scene understanding. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2016.350"},{"key":"2275_CR9","unstructured":"Doll\u00e1r, P., & Zitnick, C. L. (2014). Fast edge detection using structured forests. ArXiv ."},{"key":"2275_CR10","unstructured":"Ester, M., peter Kriegel, H., Sander, J., & Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. pp. 226\u2013231. AAAI Press."},{"issue":"12","key":"2275_CR11","doi-asserted-by":"crossref","first-page":"3252","DOI":"10.1007\/s11263-023-01862-2","volume":"131","author":"J Fan","year":"2023","unstructured":"Fan, J., & Zhang, Z. (2023). Toward practical weakly supervised semantic segmentation via point-level supervision. International Journal of Computer Vision, 131(12), 3252\u20133271.","journal-title":"International Journal of Computer Vision"},{"key":"2275_CR12","doi-asserted-by":"crossref","unstructured":"Fan, J., Zhang, Z., Song, C., & Tan, T. (2020). Learning integral objects with intra-class discriminator for weakly-supervised semantic segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4283\u20134292.","DOI":"10.1109\/CVPR42600.2020.00434"},{"issue":"11","key":"2275_CR13","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013). Vision meets robotics: The kitti dataset. The International Journal of Robotics Research, 32(11), 1231\u20131237.","journal-title":"The International Journal of Robotics Research"},{"key":"2275_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2275_CR15","unstructured":"Hoyer, L., Munoz, M., Katiyar, P., Khoreva, A., & Fischer, V. (2019). Grid saliency for context explanations of semantic segmentation. Advances in neural information processing systems\u00a032 ."},{"key":"2275_CR16","unstructured":"Huang, L., Yuan, Y., Guo, J., Zhang, C., Chen, X., & Wang, J. (2019). Interlaced sparse self-attention for semantic segmentation. arXiv preprint[SPACE]arXiv:1907.12273 ."},{"key":"2275_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Wang, J., Liu, W., & Wang, J. (2018). Weakly-supervised semantic segmentation network with deep seeded region growing. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7014\u20137023.","DOI":"10.1109\/CVPR.2018.00733"},{"key":"2275_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, H., Wang, J., Yuan, Z., Wu, Y., Zheng, N., & Li, S. (2013). Salient object detection: A discriminative regional feature integration approach. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2083\u20132090.","DOI":"10.1109\/CVPR.2013.271"},{"key":"2275_CR19","doi-asserted-by":"crossref","unstructured":"Jiang, P. T., Hou, Q., Cao, Y., Cheng, M. M., Wei, Y., & Xiong, H. K. (2019). Integral object mining via online attention accumulation. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 2070\u20132079.","DOI":"10.1109\/ICCV.2019.00216"},{"key":"2275_CR20","doi-asserted-by":"crossref","unstructured":"Jo, S., & Yu, I. J. (2021). Puzzle-cam: Improved localization via matching partial and full features. In 2021 IEEE International Conference on Image Processing (ICIP), pp. 639\u2013643. IEEE.","DOI":"10.1109\/ICIP42928.2021.9506058"},{"key":"2275_CR21","unstructured":"Kr\u00e4henb\u00fchl, P., & Koltun, V. (2011). Efficient inference in fully connected crfs with gaussian edge potentials. Advances in neural information processing systems\u00a024 ."},{"key":"2275_CR22","first-page":"30499","volume":"35","author":"H Kweon","year":"2022","unstructured":"Kweon, H., & Yoon, K. J. (2022). Joint learning of 2d\u20133d weakly supervised semantic segmentation. Advances in Neural Information Processing Systems, 35, 30499\u201330511.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2275_CR23","doi-asserted-by":"crossref","unstructured":"Lee, M., Kim, D., & Shim, H. (2022). 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, pp. 4330\u20134339.","DOI":"10.1109\/CVPR52688.2022.00429"},{"key":"2275_CR24","doi-asserted-by":"crossref","unstructured":"Li, Qizhu, Arnab, Anurag, & Torr, Philip H. S. (2018). Weakly- and Semi-supervised Panoptic Segmentation. In Proceedings European Conference on Computer Vision (ECCV), pp. 102\u2013118.","DOI":"10.1007\/978-3-030-01267-0_7"},{"key":"2275_CR25","volume":"116","author":"X Li","year":"2021","unstructured":"Li, X., Ma, H., Yi, S., Chen, Y., & Ma, H. (2021). Single annotated pixel based weakly supervised semantic segmentation under driving scenes. Pattern Recognition, 116, 107979.","journal-title":"Pattern Recognition"},{"key":"2275_CR26","doi-asserted-by":"crossref","first-page":"1433","DOI":"10.1609\/aaai.v37i2.25228","volume":"37","author":"X Li","year":"2023","unstructured":"Li, X., Yin, J., Shi, B., Li, Y., Yang, R., & Shen, J. (2023). Lwsis: Lidar-guided weakly supervised instance segmentation for autonomous driving. In Proceedings of the AAAI Conference on Artificial Intelligence, 37, 1433\u20131441.","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2275_CR27","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhao, H., Qi, X., Chen, Y., Qi, L., Wang, L., Li, Z., Sun, J., & Jia, J. (2021). Fully convolutional networks for panoptic segmentation with point-based supervision. arXiv preprint[SPACE]arXiv:2108.07682 .","DOI":"10.1109\/CVPR46437.2021.00028"},{"key":"2275_CR28","doi-asserted-by":"crossref","unstructured":"Lin, Y., Chen, M., Wang, W., Wu, B., Li, K., Lin, B., Liu, H., & He, X. (2023). 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.","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"2275_CR29","doi-asserted-by":"crossref","unstructured":"Liu, P., He, Z., Yan, X., Jiang, Y., Xia, S. T., Zheng, F., & Maowei, H. (2021). Weclick: Weakly-supervised video semantic segmentation with click annotations. In Proceedings of the 29th ACM International Conference on Multimedia, pp. 2995\u20133004.","DOI":"10.1145\/3474085.3475217"},{"key":"2275_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2275_CR31","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). June. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2275_CR32","doi-asserted-by":"crossref","unstructured":"Nie, D., Xue, J., & Ren, X. (2020). November. Bidirectional pyramid networks for semantic segmentation. In Proceedings of the Asian Conference on Computer Vision (ACCV).","DOI":"10.1007\/978-3-030-69525-5_39"},{"key":"2275_CR33","doi-asserted-by":"crossref","unstructured":"Sun, W., Zhang, J., & Barnes, N. (2020). 3d guided weakly supervised semantic segmentation. In Proceedings of the Asian Conference on Computer Vision.","DOI":"10.1007\/978-3-030-69525-5_35"},{"key":"2275_CR34","unstructured":"Sun, W., Zhang, J., Liu, Z., Zhong, Y., & Barnes, N. (2021). Getam: Gradient-weighted element-wise transformer attention map for weakly-supervised semantic segmentation. arXiv preprint[SPACE]arXiv:2112.02841 ."},{"issue":"6","key":"2275_CR35","doi-asserted-by":"crossref","first-page":"1736","DOI":"10.1007\/s11263-020-01293-3","volume":"128","author":"X Wang","year":"2020","unstructured":"Wang, X., Liu, S., Ma, H., & Yang, M. H. (2020). Weakly-supervised semantic segmentation by iterative affinity learning. International Journal of Computer Vision, 128(6), 1736\u20131749.","journal-title":"International Journal of Computer Vision"},{"key":"2275_CR36","doi-asserted-by":"crossref","unstructured":"Wang, X., You, S., Li, X., & Ma, H. (2018). Weakly-supervised semantic segmentation by iteratively mining common object features. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1354\u20131362.","DOI":"10.1109\/CVPR.2018.00147"},{"key":"2275_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, J., Kan, M., Shan, S., & Chen, X. (2020). Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12275\u201312284.","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"2275_CR38","doi-asserted-by":"crossref","unstructured":"Wei, Y., Xiao, H., Shi, H., Jie, Z., Feng, J., & Huang, T. S. (2018). Revisiting dilated convolution: A simple approach for weakly-and semi-supervised semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7268\u20137277.","DOI":"10.1109\/CVPR.2018.00759"},{"key":"2275_CR39","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M., & Luo, P. (2021). Segformer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems, 34, 12077\u201312090.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2275_CR40","doi-asserted-by":"crossref","unstructured":"Xie, J., Hou, X., Ye, K., & Shen, L. (2022). 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.","DOI":"10.1109\/CVPR52688.2022.00444"},{"key":"2275_CR41","doi-asserted-by":"crossref","first-page":"12765","DOI":"10.1609\/aaai.v34i07.6971","volume":"34","author":"B Zhang","year":"2020","unstructured":"Zhang, B., Xiao, J., Wei, Y., Sun, M., & Huang, K. (2020). Reliability does matter: An end-to-end weakly supervised semantic segmentation approach. In Proceedings of the AAAI Conference on Artificial Intelligence, 34, 12765\u201312772.","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2275_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, B., Xiao, J., Wei, Y., & Zhao, Y. (2023). Credible dual-expert learning for weakly supervised semantic segmentation. International Journal of Computer Vision, 131(8), 1\u201317.","DOI":"10.1007\/s11263-023-01796-9"},{"key":"2275_CR43","doi-asserted-by":"crossref","unstructured":"Zhou, T., Zhang, M., Zhao, F., & Li, J. (2022). 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.","DOI":"10.1109\/CVPR52688.2022.00426"},{"key":"2275_CR44","doi-asserted-by":"crossref","unstructured":"Zitnick, C. Lawrence., & Doll\u00e1r, Piotr. (2014). Edge Boxes: Locating Object Proposals from Edges. In ECCV.","DOI":"10.1007\/978-3-319-10602-1_26"}],"updated-by":[{"DOI":"10.1007\/s11263-025-02366-x","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T00:00:00Z","timestamp":1737936000000}}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02275-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02275-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02275-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T21:57:18Z","timestamp":1743371838000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02275-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,4]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["2275"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02275-5","relation":{"correction":[{"id-type":"doi","id":"10.1007\/s11263-025-02366-x","asserted-by":"object"}]},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,4]]},"assertion":[{"value":"18 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 January 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The acknowledgment section has been included","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 January 2025","order":7,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":8,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":9,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s11263-025-02366-x","URL":"https:\/\/doi.org\/10.1007\/s11263-025-02366-x","order":10,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}}]}}