{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T13:02:08Z","timestamp":1775134928437,"version":"3.50.1"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,3,9]],"date-time":"2022-03-09T00:00:00Z","timestamp":1646784000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,9]],"date-time":"2022-03-09T00:00:00Z","timestamp":1646784000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s11263-022-01586-9","type":"journal-article","created":{"date-parts":[[2022,3,9]],"date-time":"2022-03-09T09:02:47Z","timestamp":1646816567000},"page":"1127-1144","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":58,"title":["Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling"],"prefix":"10.1007","volume":"130","author":[{"given":"Lixiang","family":"Ru","sequence":"first","affiliation":[]},{"given":"Bo","family":"Du","sequence":"additional","affiliation":[]},{"given":"Yibing","family":"Zhan","sequence":"additional","affiliation":[]},{"given":"Chen","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,3,9]]},"reference":[{"issue":"6","key":"1586_CR1","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1109\/34.295913","volume":"16","author":"R Adams","year":"1994","unstructured":"Adams, R., & Bischof, L. (1994). Seeded region growing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(6), 641\u2013647.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1586_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":"1586_CR3","doi-asserted-by":"crossref","unstructured":"Ahn, J., Cho, S., & Kwak, S. (2019). 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.","DOI":"10.1109\/CVPR.2019.00231"},{"issue":"6","key":"1586_CR4","doi-asserted-by":"publisher","first-page":"1437","DOI":"10.1109\/TPAMI.2017.2711011","volume":"40","author":"R Arandjelovi\u0107","year":"2017","unstructured":"Arandjelovi\u0107, R., Gronat, P., Torii, A., Pajdla, T., & Sivic, J. (2017). Netvlad: Cnn architecture for weakly supervised place recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6), 1437\u20131451.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1586_CR5","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"},{"issue":"12","key":"1586_CR6","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017). Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12), 2481\u20132495.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1586_CR7","doi-asserted-by":"crossref","unstructured":"Bearman, A., Russakovsky, O., Ferrari, V., & Fei-Fei, L. (2016). What\u2019s the point: Semantic segmentation with point supervision. In: European conference on computer vision, Springer, pp 549\u2013565.","DOI":"10.1007\/978-3-319-46478-7_34"},{"key":"1586_CR8","doi-asserted-by":"crossref","unstructured":"Chang, Y. T., Wang, Q., Hung, W. C., Piramuthu, R., Tsai, Y. H., & Yang, M. H. (2020a). Mixup-cam: Weakly-supervised semantic segmentation via uncertainty regularization. In: British Machine Vision Conference (BMVC).","DOI":"10.1109\/CVPR42600.2020.00901"},{"key":"1586_CR9","doi-asserted-by":"crossref","unstructured":"Chang, Y. T., Wang, Q., Hung, W. C., Piramuthu, R., Tsai, Y. H., & Yang, M. H. (2020b). 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"},{"key":"1586_CR10","unstructured":"Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2015). Semantic image segmentation with deep convolutional nets and fully connected crfs. In: International Conference on Learning Representations."},{"issue":"4","key":"1586_CR11","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., 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":"1586_CR12","unstructured":"Cogswell, M., Ahmed, F., Girshick, R., Zitnick, L., & Batra, D. (2017). Reducing overfitting in deep networks by decorrelating representations. In: International Conference on Learning Representations."},{"key":"1586_CR13","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, pp 3213\u20133223.","DOI":"10.1109\/CVPR.2016.350"},{"issue":"2","key":"1586_CR14","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge. International Journal of Computer Vision, 88(2), 303\u2013338.","journal-title":"International Journal of Computer Vision"},{"key":"1586_CR15","doi-asserted-by":"publisher","first-page":"10762","DOI":"10.1609\/aaai.v34i07.6705","volume":"34","author":"J Fan","year":"2020","unstructured":"Fan, J., Zhang, Z., Tan, T., Song, C., & Xiao, J. (2020). Cian: Cross-image affinity net for weakly supervised semantic segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 10762\u201310769.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"2","key":"1586_CR16","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","volume":"43","author":"SH Gao","year":"2021","unstructured":"Gao, S. H., Cheng, M. M., Zhao, K., Zhang, X. Y., Yang, M. H., & Torr, P. (2021). Res2net: A new multi-scale backbone architecture. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(2), 652\u2013662.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1586_CR17","doi-asserted-by":"crossref","unstructured":"Gidaris, S., Bursuc, A., Komodakis, N., P\u00e9rez, P., & Cord, M. (2020). Learning representations by predicting bags of visual words. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 6928\u20136938.","DOI":"10.1109\/CVPR42600.2020.00696"},{"key":"1586_CR18","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Bourdev, L., Maji, S., & Malik, J. (2011). Semantic contours from inverse detectors. In: 2011 International Conference on Computer Vision, IEEE, pp 991\u2013998.","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"1586_CR19","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":"1586_CR20","doi-asserted-by":"crossref","unstructured":"Hou, Q., Cheng, M. M., Hu, X., Borji, A., Tu, Z., & Torr, P. H. (2017). Deeply supervised salient object detection with short connections. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3203\u20133212.","DOI":"10.1109\/CVPR.2017.563"},{"key":"1586_CR21","first-page":"549","volume":"31","author":"Q Hou","year":"2018","unstructured":"Hou, Q., Jiang, P., Wei, Y., & Cheng, M. M. (2018). Self-erasing network for integral object attention. Advances in Neural Information Processing Systems, 31, 549\u2013559.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1586_CR22","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":"1586_CR23","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":"1586_CR24","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.","DOI":"10.1109\/ICIP42928.2021.9506058"},{"key":"1586_CR25","unstructured":"Ke, T. W., Hwang, J. J., & Yu, S. X. (2021). Universal weakly supervised segmentation by pixel-to-segment contrastive learning. In: International Conference on Learning Representations."},{"key":"1586_CR26","doi-asserted-by":"crossref","first-page":"1754","DOI":"10.1609\/aaai.v35i2.16269","volume":"35","author":"B Kim","year":"2021","unstructured":"Kim, B., Han, S., & Kim, J. (2021). Discriminative region suppression for weakly-supervised semantic segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 1754\u20131761.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"1586_CR27","doi-asserted-by":"crossref","unstructured":"Kolesnikov, A., & Lampert, C. H. (2016). Seed, expand and constrain: Three principles for weakly-supervised image segmentation. In: European conference on computer vision, Springer, pp 695\u2013711.","DOI":"10.1007\/978-3-319-46493-0_42"},{"key":"1586_CR28","first-page":"109","volume":"24","author":"P Kr\u00e4henb\u00fchl","year":"2011","unstructured":"Kr\u00e4henb\u00fchl, P., & Koltun, V. (2011). Efficient inference in fully connected crfs with gaussian edge potentials. Advances in Neural Information Processing Systems, 24, 109\u2013117.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1586_CR29","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25, 1097\u20131105.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1586_CR30","doi-asserted-by":"crossref","unstructured":"Lee J, Kim, E., & Yoon, S. (2021a). Anti-adversarially manipulated attributions for weakly and semi-supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 4071\u20134080.","DOI":"10.1109\/CVPR46437.2021.00406"},{"key":"1586_CR31","doi-asserted-by":"crossref","unstructured":"Lee, J., Yi, J., Shin, C., & Yoon, S. (2021b). Bbam: Bounding box attribution map for weakly supervised semantic and instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 2643\u20132652.","DOI":"10.1109\/CVPR46437.2021.00267"},{"key":"1586_CR32","doi-asserted-by":"crossref","unstructured":"Lee, S., Lee, M., Lee, J., & Shim, H. (2021c). 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.","DOI":"10.1109\/CVPR46437.2021.00545"},{"key":"1586_CR33","doi-asserted-by":"crossref","first-page":"1984","DOI":"10.1609\/aaai.v35i3.16294","volume":"35","author":"X Li","year":"2021","unstructured":"Li, X., Zhou, T., Li, J., Zhou, Y., & Zhang, Z. (2021). Group-wise semantic mining for weakly supervised semantic segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 1984\u20131992.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"1586_CR34","doi-asserted-by":"crossref","unstructured":"Li, Y., Kuang, Z., Liu, L., Chen, Y., & Zhang, W. (2021b). Pseudo-mask matters in weakly-supervised semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 6964\u20136973.","DOI":"10.1109\/ICCV48922.2021.00688"},{"key":"1586_CR35","doi-asserted-by":"crossref","unstructured":"Lin, D., Dai, J., Jia, J., He, K., & Sun, J. (2016). Scribblesup: Scribble-supervised convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3159\u20133167.","DOI":"10.1109\/CVPR.2016.344"},{"key":"1586_CR36","doi-asserted-by":"crossref","unstructured":"Lin, H., Upchurch, P., & Bala, K. (2019). Block annotation: Better image annotation with sub-image decomposition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV).","DOI":"10.1109\/ICCV.2019.00539"},{"key":"1586_CR37","unstructured":"Lin, M., Chen, Q., & Yan, S. (2013). Network in network. arXiv preprint arXiv:13124400."},{"key":"1586_CR38","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In: European conference on computer vision, Springer, pp 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"1","key":"1586_CR39","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/s11263-018-1125-z","volume":"127","author":"L Liu","year":"2019","unstructured":"Liu, L., Chen, J., Fieguth, P., Zhao, G., Chellappa, R., & Pietik\u00e4inen, M. (2019). From bow to cnn: Two decades of texture representation for texture classification. International Journal of Computer Vision, 127(1), 74\u2013109.","journal-title":"International Journal of Computer Vision"},{"issue":"3","key":"1586_CR40","doi-asserted-by":"publisher","first-page":"1415","DOI":"10.1109\/TPAMI.2020.3023152","volume":"44","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Wu, Y. H., Wen, P. S., Shi, Y. J., Qiu, Y., & Cheng, M. M. (2020). Leveraging instance-, image-and dataset-level information for weakly supervised instance segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(3), 1415\u20131428.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1586_CR41","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1586_CR42","doi-asserted-by":"crossref","unstructured":"Oh, Y., Kim, B., & Ham, B. (2021). Background-aware pooling and noise-aware loss for weakly-supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 6913\u20136922.","DOI":"10.1109\/CVPR46437.2021.00684"},{"key":"1586_CR43","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Chen, L. C., Murphy, K. P., & Yuille, A. L. (2015). Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation. In: Proceedings of the IEEE international conference on computer vision, pp 1742\u20131750.","DOI":"10.1109\/ICCV.2015.203"},{"key":"1586_CR44","doi-asserted-by":"crossref","unstructured":"Passalis, N., & Tefas, A. (2017). Learning bag-of-features pooling for deep convolutional neural networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), IEEE, pp 5766\u20135774.","DOI":"10.1109\/ICCV.2017.614"},{"key":"1586_CR45","first-page":"8026","volume":"32","author":"A Paszke","year":"2019","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019). Pytorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems, 32, 8026\u20138037.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1586_CR46","doi-asserted-by":"crossref","unstructured":"Pinheiro, P. O., & Collobert, R. (2015). From image-level to pixel-level labeling with convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1713\u20131721.","DOI":"10.1109\/CVPR.2015.7298780"},{"key":"1586_CR47","doi-asserted-by":"crossref","unstructured":"Roy, A., & Todorovic, S. (2017). Combining bottom-up, top-down, and smoothness cues for weakly supervised image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3529\u20133538.","DOI":"10.1109\/CVPR.2017.770"},{"key":"1586_CR48","doi-asserted-by":"crossref","unstructured":"Ru, L., Du, B., & Wu, C. (2021). Learning visual words for weakly-supervised semantic segmentation. In: International Joint Conference on Artificial Intelligence.","DOI":"10.24963\/ijcai.2021\/136"},{"issue":"1","key":"1586_CR49","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1080\/24709360.2019.1670513","volume":"3","author":"DB Rubin","year":"2019","unstructured":"Rubin, D. B. (2019). Essential concepts of causal inference: A remarkable history and an intriguing future. Biostatistics & Epidemiology, 3(1), 140\u2013155.","journal-title":"Biostatistics & Epidemiology"},{"issue":"1","key":"1586_CR50","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2008","unstructured":"Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., & Monfardini, G. (2008). The graph neural network model. IEEE Transactions on Neural Networks, 20(1), 61\u201380.","journal-title":"IEEE Transactions on Neural Networks"},{"key":"1586_CR51","doi-asserted-by":"crossref","unstructured":"Sculley, D. (2010). Web-scale k-means clustering. In: Proceedings of the 19th international conference on World wide web, pp 1177\u20131178.","DOI":"10.1145\/1772690.1772862"},{"key":"1586_CR52","doi-asserted-by":"crossref","unstructured":"Song, C., Huang, Y., Ouyang, W., & Wang, L. (2019). Box-driven class-wise region masking and filling rate guided loss for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 3136\u20133145.","DOI":"10.1109\/CVPR.2019.00325"},{"key":"1586_CR53","doi-asserted-by":"crossref","unstructured":"Sun, G., Wang, W., Dai, J., & Van\u00a0Gool, L. (2020). Mining cross-image semantics for weakly supervised semantic segmentation. In: European Conference on Computer Vision, Springer, pp 347\u2013365.","DOI":"10.1007\/978-3-030-58536-5_21"},{"issue":"1","key":"1586_CR54","first-page":"3221","volume":"15","author":"L Van Der Maaten","year":"2014","unstructured":"Van Der Maaten, L. (2014). Accelerating t-sne using tree-based algorithms. The Journal of Machine Learning Research, 15(1), 3221\u20133245.","journal-title":"The Journal of Machine Learning Research"},{"key":"1586_CR55","doi-asserted-by":"crossref","unstructured":"Vernaza, P., & Chandraker, M. (2017). Learning random-walk label propagation for weakly-supervised semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7158\u20137166.","DOI":"10.1109\/CVPR.2017.315"},{"issue":"6","key":"1586_CR56","doi-asserted-by":"publisher","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":"1586_CR57","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, J., Kan, M., Shan, S., & Chen, X. (2020b). 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":"1586_CR58","doi-asserted-by":"crossref","unstructured":"Wei, Y., Feng, J., Liang, X., Cheng, M. M., Zhao, Y., & Yan, S. (2017). Object region mining with adversarial erasing: A simple classification to semantic segmentation approach. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1568\u20131576.","DOI":"10.1109\/CVPR.2017.687"},{"key":"1586_CR59","doi-asserted-by":"crossref","unstructured":"Wu, T., Huang, J., Gao, G., Wei, X., Wei, X., Luo, X., & Liu, C. H. (2021). Embedded discriminative attention mechanism for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 16765\u201316774.","DOI":"10.1109\/CVPR46437.2021.01649"},{"key":"1586_CR60","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S. X., Lin, D. (2018). Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3733\u20133742.","DOI":"10.1109\/CVPR.2018.00393"},{"key":"1586_CR61","doi-asserted-by":"crossref","unstructured":"Xu, L., Ouyang, W., Bennamoun, M., Boussaid, F., Sohel, F., & Xu, D. (2021). 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.","DOI":"10.1109\/ICCV48922.2021.00690"},{"key":"1586_CR62","doi-asserted-by":"crossref","unstructured":"Yao, Y., Chen, T., Xie, G. S., Zhang, C., Shen, F., Wu, Q., Tang, Z., & Zhang, J. (2021). 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.","DOI":"10.1109\/CVPR46437.2021.00265"},{"key":"1586_CR63","doi-asserted-by":"publisher","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. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 12765\u201312772.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"1586_CR64","first-page":"655","volume":"33","author":"D Zhang","year":"2020","unstructured":"Zhang, D., Zhang, H., Tang, J., Hua, X. S., & Sun, Q. (2020). Causal intervention for weakly-supervised semantic segmentation. Advances in Neural Information Processing Systems, 33, 655\u2013666.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1586_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wei, Y., Feng, J., Yang, Y., & Huang, T. S. (2018). Adversarial complementary learning for weakly supervised object localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1325\u20131334.","DOI":"10.1109\/CVPR.2018.00144"},{"key":"1586_CR66","doi-asserted-by":"crossref","unstructured":"Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., & Torr, P. H. (2015). Conditional random fields as recurrent neural networks. In: Proceedings of the IEEE international conference on computer vision, pp 1529\u20131537.","DOI":"10.1109\/ICCV.2015.179"},{"key":"1586_CR67","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2921\u20132929.","DOI":"10.1109\/CVPR.2016.319"},{"key":"1586_CR68","doi-asserted-by":"crossref","unstructured":"Zhuang, C., Zhai, A. L., Yamins, D. (2019). Local aggregation for unsupervised learning of visual embeddings. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 6002\u20136012.","DOI":"10.1109\/ICCV.2019.00610"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01586-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-022-01586-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01586-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T17:53:09Z","timestamp":1674928389000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-022-01586-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,9]]},"references-count":68,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["1586"],"URL":"https:\/\/doi.org\/10.1007\/s11263-022-01586-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,9]]},"assertion":[{"value":"6 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}