{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T15:57:08Z","timestamp":1774627028215,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2017,10,17]],"date-time":"2017-10-17T00:00:00Z","timestamp":1508198400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["Starting Grant VisCul"],"award-info":[{"award-number":["Starting Grant VisCul"]}],"id":[{"id":"10.13039\/501100000781","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":[[2018,5]]},"DOI":"10.1007\/s11263-017-1048-0","type":"journal-article","created":{"date-parts":[[2017,10,17]],"date-time":"2017-10-17T03:33:06Z","timestamp":1508211186000},"page":"476-494","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":78,"title":["Do Semantic Parts Emerge in Convolutional Neural Networks?"],"prefix":"10.1007","volume":"126","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9334-6646","authenticated-orcid":false,"given":"Abel","family":"Gonzalez-Garcia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Davide","family":"Modolo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vittorio","family":"Ferrari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,10,17]]},"reference":[{"key":"1048_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, P., Girshick, R., & Malik, J. (2014). Analyzing the performance of multilayer neural networks for object recognition. In ECCV.","DOI":"10.1007\/978-3-319-10584-0_22"},{"key":"1048_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., & Ferrari, V. (2015). Joint calibration for semantic segmentation. In BMVC.","DOI":"10.5244\/C.29.29"},{"key":"1048_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Mottaghi, R., Liu, X., Fidler, S., Urtasun, R., & Yuille, A. (2014). Detect what you can: Detecting and representing objects using holistic models and body parts. In CVPR.","DOI":"10.1109\/CVPR.2014.254"},{"key":"1048_CR4","doi-asserted-by":"crossref","unstructured":"Dalal, N., & Triggs, B. (2005). Histogram of oriented gradients for human detection. In CVPR.","DOI":"10.1109\/CVPR.2005.177"},{"key":"1048_CR5","unstructured":"Eigen, D., Rolfe, J., Fergus, R., & LeCun, Y. (2013). Understanding deep architectures using a recursive convolutional network. In ICLR workshop."},{"key":"1048_CR6","doi-asserted-by":"crossref","unstructured":"Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (VOC) challenge. International Journal of Computer Vision, 88(2), 303\u2013338.","DOI":"10.1007\/s11263-009-0275-4"},{"issue":"9","key":"1048_CR7","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"P Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P., Girshick, R., McAllester, D., & Ramanan, D. (2010). Object detection with discriminatively trained part based models. IEEE transactions on pattern analysis and machine intelligence, 32(9), 1627\u20131645.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"1048_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015). Fast R-CNN. In ICCV.","DOI":"10.1109\/ICCV.2015.169"},{"key":"1048_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2014.81"},{"key":"1048_CR10","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., & Malik, J. (2015). Actions and attributes from wholes and parts. In ICCV.","DOI":"10.1109\/ICCV.2015.284"},{"key":"1048_CR11","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Girshick, R., & Malik, J. (2015). Hypercolumns for object segmentation and fine-grained localization. In CVPR.","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"1048_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2014). Spatial pyramid pooling in deep convolutional networks for visual recognition. In ECCV.","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"1048_CR13","unstructured":"Jia, Y. (2013). Caffe: An open source convolutional architecture for fast feature embedding. http:\/\/caffe.berkeleyvision.org\/ ."},{"key":"1048_CR14","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In NIPS."},{"key":"1048_CR15","doi-asserted-by":"crossref","unstructured":"Lenc, K., & Vedaldi, A. (2015). Understanding image representations by measuring their equivariance and equivalence. In CVPR.","DOI":"10.1109\/CVPR.2015.7298701"},{"key":"1048_CR16","doi-asserted-by":"crossref","unstructured":"Lin, D., Shen, X., Lu, C., & Jia, J. (2015). Deep lac: Deep localization, alignment and classification for fine-grained recognition. In CVPR.","DOI":"10.1109\/CVPR.2015.7298775"},{"key":"1048_CR17","doi-asserted-by":"crossref","unstructured":"Liu, J., Li, Y., & Belhumeur, P.N. (2014). Part-pair representation for part localization. In ECCV.","DOI":"10.1007\/978-3-319-10605-2_30"},{"key":"1048_CR18","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015) Fully convolutional networks for semantic segmentation. In CVPR.","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"2","key":"1048_CR19","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D Lowe","year":"2004","unstructured":"Lowe, D. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91\u2013110.","journal-title":"International Journal of Computer Vision"},{"key":"1048_CR20","doi-asserted-by":"crossref","unstructured":"Mahendran, A., & Vedaldi, A. (2015). Understanding deep image representations by inverting them. In CVPR.","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"1048_CR21","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3927.001.0001","volume-title":"An introduction to genetic algorithms","author":"M Mitchell","year":"1998","unstructured":"Mitchell, M. (1998). An introduction to genetic algorithms. Cambridge: MIT Press."},{"key":"1048_CR22","doi-asserted-by":"crossref","unstructured":"Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2015). Is object localization for free?-weakly-supervised learning with convolutional neural networks. In CVPR.","DOI":"10.1109\/CVPR.2015.7298668"},{"key":"1048_CR23","doi-asserted-by":"crossref","unstructured":"Parkhi, O., Vedaldi, A., Jawahar, C. V., & Zisserman, A. (2011). The truth about cats and dogs. In ICCV.","DOI":"10.1109\/ICCV.2011.6126398"},{"key":"1048_CR24","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., & Jawahar, C. (2012) .Cats and dogs. In CVPR.","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"1048_CR25","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1098\/rspl.1895.0041","volume":"58","author":"K Pearson","year":"1895","unstructured":"Pearson, K. (1895). Note on regression and inheritance in the case of two parents. Proceedings of the Royal Society of London, 58, 240\u2013242.","journal-title":"Proceedings of the Royal Society of London"},{"key":"1048_CR26","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., et al. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"1048_CR27","doi-asserted-by":"crossref","unstructured":"Simon, M., & Rodner, E. (2015). Neural activation constellations: Unsupervised part model discovery with convolutional networks. In ICCV.","DOI":"10.1109\/ICCV.2015.136"},{"key":"1048_CR28","unstructured":"Simon, M., Rodner, E., & Denzler, J. (2014). Part detector discovery in deep convolutional neural networks. In ACCV."},{"key":"1048_CR29","unstructured":"Simonyan, K., & Zisserman, A. (2015) Very deep convolutional networks for large-scale image recognition. In ICLR."},{"key":"1048_CR30","unstructured":"Simonyan, K., Vedaldi, A., & Zisserman, A. (2014). Deep inside convolutional networks: Visualising image classification models and saliency maps. In ICLR workshop."},{"key":"1048_CR31","doi-asserted-by":"crossref","unstructured":"Sun, M., & Savarese, S. (2011). Articulated part-based model for joint object detection and pose estimation. In ICCV.","DOI":"10.1109\/ICCV.2011.6126309"},{"key":"1048_CR32","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2014). Intriguing properties of neural networks. In ICLR."},{"key":"1048_CR33","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. In CVPR.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1048_CR34","doi-asserted-by":"crossref","unstructured":"Ukita, N. (2012). Articulated pose estimation with parts connectivity using discriminative local oriented contours. In CVPR.","DOI":"10.1109\/CVPR.2012.6248049"},{"key":"1048_CR35","doi-asserted-by":"crossref","unstructured":"Vedaldi, A., Mahendran, S., Tsogkas, S., Maji, S., Girshick, R., Kannala, J., et al. (2014). Understanding objects in detail with fine-grained attributes. In CVPR.","DOI":"10.1109\/CVPR.2014.463"},{"key":"1048_CR36","unstructured":"Xiao, T., Xu, Y., Yang, K., Zhang, J., Peng, Y., & Zhang, Z. (2015). The application of two-level attention models in deep convolutional neural network for fine-grained image classification. In CVPR."},{"key":"1048_CR37","unstructured":"Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? In NIPS."},{"key":"1048_CR38","doi-asserted-by":"crossref","unstructured":"Zeiler, M. D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. In ECCV.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"1048_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, N., Farrell, R., Iandola, F., & Darrell, T. (2013). Deformable part descriptors for fine-grained recognition and attribute prediction. In ICCV.","DOI":"10.1109\/ICCV.2013.96"},{"key":"1048_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, N., Donahue, J., Girshick, R., & Darrell, T. (2014). Part-based R-CNNS for fine-grained category detection. In ECCV.","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"1048_CR41","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., & Oliva, A. (2014). Learning deep features for scene recognition using places database. In NIPS."},{"key":"1048_CR42","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2015). Object detectors emerge in deep scene cnns. In ICLR."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-017-1048-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-017-1048-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-017-1048-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,20]],"date-time":"2020-10-20T00:56:42Z","timestamp":1603155402000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-017-1048-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,17]]},"references-count":42,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2018,5]]}},"alternative-id":["1048"],"URL":"https:\/\/doi.org\/10.1007\/s11263-017-1048-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,10,17]]},"assertion":[{"value":"5 October 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 October 2017","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2017","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}