{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T06:11:56Z","timestamp":1759385516903},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,5,10]],"date-time":"2021-05-10T00:00:00Z","timestamp":1620604800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,10]],"date-time":"2021-05-10T00:00:00Z","timestamp":1620604800000},"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":["Multidim Syst Sign Process"],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1007\/s11045-021-00778-9","type":"journal-article","created":{"date-parts":[[2021,5,10]],"date-time":"2021-05-10T09:03:32Z","timestamp":1620637412000},"page":"1185-1197","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Simple feature pyramid network for weakly supervised object localization using multi-scale information"],"prefix":"10.1007","volume":"32","author":[{"given":"Bongyeong","family":"Koo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han-Soo","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Myungjoo","family":"Kang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,10]]},"reference":[{"key":"778_CR1","doi-asserted-by":"crossref","unstructured":"Choe, J., & Shim, H. (2019). Attention-based dropout layer for weakly supervised object localization. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2219\u20132228.","DOI":"10.1109\/CVPR.2019.00232"},{"key":"778_CR2","doi-asserted-by":"crossref","unstructured":"Cubuk, E.\u00a0D, Zoph, B., Mane, D., Vasudevan, V., & Le, Q.\u00a0V. (2019). Autoaugment: Learning augmentation strategies from data. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 113\u2013123.","DOI":"10.1109\/CVPR.2019.00020"},{"key":"778_CR3","unstructured":"Dabkowski, P., & Gal, Y. (2017). Real time image saliency for black box classifiers. In Advances in neural information processing systems (pp. 6967\u20136976)."},{"key":"778_CR4","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pp. 2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"},{"key":"778_CR5","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":"778_CR6","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167."},{"key":"778_CR7","unstructured":"Jaderberg, M., Simonyan, K., & Zisserman, A., et\u00a0al. (2015). Spatial transformer networks. In Advances in neural information processing systems (pp. 2017\u20132025)."},{"key":"778_CR8","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"778_CR9","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"778_CR10","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A.\u00a0C. (2016). Ssd: Single shot multibox detector. In European conference on computer vision (pp. 21\u201337). Springer.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"778_CR11","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":"778_CR12","doi-asserted-by":"crossref","unstructured":"Luo, L., Yuan, C., Zhang, K., Jiang, Y., Zhang, Y., & Zhang, H. (2020). Double shot: Preserve and erase based class attention networks for weakly supervised localization (peca-net). In 2020 IEEE international conference on multimedia and expo (ICME) (pp. 1\u20136). IEEE.","DOI":"10.1109\/ICME46284.2020.9102801"},{"key":"778_CR13","doi-asserted-by":"crossref","unstructured":"Mai, J., Yang, M., & Luo, W. (2020). Erasing integrated learning: A simple yet effective approach for weakly supervised object localization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 8766\u20138775.","DOI":"10.1109\/CVPR42600.2020.00879"},{"key":"778_CR14","unstructured":"Meethal, A., Pedersoli, M., Belharbi, S., & Granger, E. (2019). Convolutional stn for weakly supervised object localization and beyond. arXiv preprint arXiv:1912.01522."},{"key":"778_CR15","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., & DeVito, Z. (2017). Zeming Lin. Alban Desmaison: Luca Antiga, and Adam Lerer. Automatic differentiation (in pytorch)."},{"key":"778_CR16","unstructured":"Ren, S., He, K., Girshick, K., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems, pp. 91\u201399."},{"key":"778_CR17","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International conference on medical image computing and computer-assisted intervention (pp. 234\u2013241). Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"3","key":"778_CR18","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Hao, S., Krause, J., Satheesh, S., Ma, S., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"778_CR19","doi-asserted-by":"crossref","unstructured":"Singh, K.\u00a0K., & Lee, Y.\u00a0J. (2017). Hide-and-seek: Forcing a network to be meticulous for weakly-supervised object and action localization. In 2017 IEEE international conference on computer vision (ICCV) (pp. 3544\u20133553). IEEE.","DOI":"10.1109\/ICCV.2017.381"},{"key":"778_CR20","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2818\u20132826.","DOI":"10.1109\/CVPR.2016.308"},{"key":"778_CR21","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., & Belongie, S. (2011). The Caltech-UCSD Birds-200-2011 Dataset. Technical Report CNS-TR-2011-001, California Institute of Technology."},{"key":"778_CR22","doi-asserted-by":"crossref","unstructured":"Xue, H., Liu, C., Wan, F., Jiao, J., Ji, X., & Ye, Q. (2019). Danet: Divergent activation for weakly supervised object localization. In Proceedings of the IEEE international conference on computer vision, pp. 6589\u20136598.","DOI":"10.1109\/ICCV.2019.00669"},{"key":"778_CR23","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.\u00a0J., Chun, S., Choe, J., & Yoo, Y. (2019) Cutmix: Regularization strategy to train strong classifiers with localizable features. In Proceedings of the IEEE international conference on computer vision, pp. 6023\u20136032.","DOI":"10.1109\/ICCV.2019.00612"},{"key":"778_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wei, Y., Feng, J., Yang, Y., & Huang, T.\u00a0S. (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":"778_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wei, Y., Kang, G., Yang, Y., & Huang, T. (2018). Self-produced guidance for weakly-supervised object localization. In Proceedings of the European conference on computer vision (ECCV), pp. 597\u2013613.","DOI":"10.1007\/978-3-030-01258-8_37"},{"key":"778_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, S., Wen, L., Bian, X., Lei, Z., & Li, S.\u00a0Z. (2018). Single-shot refinement neural network for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4203\u20134212.","DOI":"10.1109\/CVPR.2018.00442"},{"key":"778_CR27","doi-asserted-by":"publisher","first-page":"9259","DOI":"10.1609\/aaai.v33i01.33019259","volume":"33","author":"Q Zhao","year":"2019","unstructured":"Zhao, Q., Sheng, T., Wang, Y., Tang, Z., Chen, Y., Cai, L., & Ling, H. (2019). M2det: A single-shot object detector based on multi-level feature pyramid network. Proceedings of the AAAI Conference on Artificial Intelligence, 33, 9259\u20139266.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"778_CR28","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"}],"container-title":["Multidimensional Systems and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11045-021-00778-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11045-021-00778-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11045-021-00778-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,27]],"date-time":"2021-08-27T21:09:33Z","timestamp":1630098573000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11045-021-00778-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,10]]},"references-count":28,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,10]]}},"alternative-id":["778"],"URL":"https:\/\/doi.org\/10.1007\/s11045-021-00778-9","relation":{},"ISSN":["0923-6082","1573-0824"],"issn-type":[{"value":"0923-6082","type":"print"},{"value":"1573-0824","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,10]]},"assertion":[{"value":"12 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}