{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T09:55:21Z","timestamp":1780048521506,"version":"3.53.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2016,3,1]],"date-time":"2016-03-01T00:00:00Z","timestamp":1456790400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2016,9]]},"DOI":"10.1007\/s11263-016-0884-7","type":"journal-article","created":{"date-parts":[[2016,3,1]],"date-time":"2016-03-01T05:50:57Z","timestamp":1456811457000},"page":"145-158","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Visualizing Object Detection Features"],"prefix":"10.1007","volume":"119","author":[{"given":"Carl","family":"Vondrick","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aditya","family":"Khosla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamed","family":"Pirsiavash","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomasz","family":"Malisiewicz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"Torralba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,3,1]]},"reference":[{"key":"884_CR1","doi-asserted-by":"crossref","unstructured":"Alahi, A., Ortiz, R., & Vandergheynst. P. (2012). Freak: Fast retina keypoint. In 2012 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 510\u2013517). IEEE.","DOI":"10.1109\/CVPR.2012.6247715"},{"key":"884_CR2","unstructured":"Biggio, B., Nelson, B., & Laskovl, P. (2012). Poisoning attacks against support vector machines. arXiv preprint arXiv:1206.6389 ."},{"key":"884_CR3","doi-asserted-by":"crossref","unstructured":"Bruckner, D. (2014). Ml-o-scope: a diagnostic visualization system for deep machine learning pipelines. Technical report, DTIC Document.","DOI":"10.21236\/ADA605112"},{"key":"884_CR4","doi-asserted-by":"crossref","unstructured":"Calonder, M., Lepetit, V., Strecha, C., & Fua, P. (2010). Brief: Binary robust independent elementary features. Computer vision\u2014ECCV, 2010 (pp. 778\u2013792).","DOI":"10.1007\/978-3-642-15561-1_56"},{"key":"884_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C. Y., & Grauman, K. (2014). Inferring unseen views of people. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2003\u20132010).","DOI":"10.1109\/CVPR.2014.258"},{"key":"884_CR6","doi-asserted-by":"crossref","unstructured":"Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In IEEE computer society conference on computer vision and pattern recognition 2005 (CVPR 2005) (Vol. 1, pp. 886\u2013893). IEEE.","DOI":"10.1109\/CVPR.2005.177"},{"key":"884_CR7","unstructured":"d\u2019Angelo, E., Alahi, A., & Vandergheynst, P. (2012). Beyond bits: Reconstructing images from local binary descriptors. In 2012 21st international conference on pattern recognition (ICPR) (pp. 935\u2013938). IEEE."},{"key":"884_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In IEEE conference on computer vision and pattern recognition, 2009, CVPR 2009 (pp. 248\u2013255). IEEE.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"884_CR9","doi-asserted-by":"crossref","unstructured":"Divvala, S. K., Efros, A. A., & Hebert, M. (2012). How important are deformable parts in the deformable parts model? In Computer vision\u2014ECCV 2012. Workshops and demonstrations (pp. 31\u201340). Springer.","DOI":"10.1007\/978-3-642-33885-4_4"},{"key":"884_CR10","unstructured":"Dosovitskiy, A., & Brox, T. (2015). Inverting convolutional networks with convolutional networks. arXiv preprint arXiv:1506.02753 ."},{"key":"884_CR11","unstructured":"Everingham, M., Van Gool, L., Williams, C., Winn, J., & Zisserman. A. (2005). Pascal visual object classes challenge results. Available from http:\/\/www.pascal-network.org ."},{"key":"884_CR12","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P. F., Girshick, R. B., & McAllester, D. (2010a). Cascade object detection with deformable part models. In 2010 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2241\u20132248). IEEE.","DOI":"10.1109\/CVPR.2010.5539906"},{"issue":"9","key":"884_CR13","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010b). 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":"884_CR14","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 Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 580\u2013587).","DOI":"10.1109\/CVPR.2014.81"},{"issue":"5","key":"884_CR15","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1111\/1467-9280.03452","volume":"14","author":"F Gosselin","year":"2003","unstructured":"Gosselin, F., & Schyns, P. G. (2003). Superstitious perceptions reveal properties of internal representations. Psychological Science, 14(5), 505\u2013509.","journal-title":"Psychological Science"},{"key":"884_CR16","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Malik, J., & Ramanan, D. (2012). Discriminative decorrelation for clustering and classification. In Computer vision\u2014ECCV 2012 (pp. 459\u2013472). Springer.","DOI":"10.1007\/978-3-642-33765-9_33"},{"key":"884_CR17","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Chodpathumwan, Y., & Dai, Q. (2012). Diagnosing error in object detectors. In Computer vision\u2014ECCV 2012 (pp. 340\u2013353). Springer.","DOI":"10.1007\/978-3-642-33712-3_25"},{"key":"884_CR18","doi-asserted-by":"crossref","unstructured":"Huang, D. A., & Wang, Y. C. (2013). Coupled dictionary and feature space learning with applications to cross-domain image synthesis and recognition. In Proceedings of the IEEE international conference on computer vision (pp. 2496\u20132503).","DOI":"10.1109\/ICCV.2013.310"},{"key":"884_CR19","volume-title":"Fundamentals of Digital Image Processing","author":"AK Jain","year":"1989","unstructured":"Jain, A. K. (1989). Fundamentals of Digital Image Processing. Upper Saddle River: Prentice-Hall Inc."},{"key":"884_CR20","doi-asserted-by":"crossref","unstructured":"Jia, Y. (2013). Caffe: An open source convolutional architecture for fast feature embedding.","DOI":"10.1145\/2647868.2654889"},{"key":"884_CR21","doi-asserted-by":"crossref","unstructured":"Kato, H., & Harada, T. (2014). Image reconstruction from bag-of-visual-words. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 955\u2013962).","DOI":"10.1109\/CVPR.2014.127"},{"key":"884_CR22","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097\u20131105)."},{"issue":"11","key":"884_CR23","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278\u20132324.","journal-title":"Proceedings of the IEEE"},{"key":"884_CR24","doi-asserted-by":"crossref","unstructured":"Lenc, K., & Vedaldi, A. (2015). Understanding image representations by measuring their equivariance and equivalence. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 991\u2013999).","DOI":"10.1109\/CVPR.2015.7298701"},{"key":"884_CR25","unstructured":"Liu, L., & Wang, L. (2012). What has my classifier learned? Visualizing the classification rules of bag-of-feature model by support region detection. In 2012 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 3586\u20133593). IEEE."},{"key":"884_CR26","doi-asserted-by":"crossref","unstructured":"Lowe, D. G. (1999). Object recognition from local scale-invariant features. In The proceedings of the seventh IEEE international conference on computer vision, 1999 (Vol. 2, pp. 1150\u20131157). IEEE.","DOI":"10.1109\/ICCV.1999.790410"},{"key":"884_CR27","doi-asserted-by":"crossref","unstructured":"Mahendran, A., & Vedaldi, A. (2015). Understanding deep image representations by inverting them. In 2015 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 5188\u20135196). IEEE.","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"884_CR28","doi-asserted-by":"crossref","unstructured":"Mairal, J., Bach, F., Ponce, J., & Sapiro, G. (2009). Online dictionary learning for sparse coding. In Proceedings of the 26th annual international conference on machine learning (pp. 689\u2013696). ACM.","DOI":"10.1145\/1553374.1553463"},{"key":"884_CR29","doi-asserted-by":"crossref","unstructured":"Malisiewicz, T., Gupta, A., & Efros, A.A. (2011). Ensemble of exemplar-SVMs for object detection and beyond. In 2011 IEEE international conference on computer vision (ICCV) (pp. 89\u201396). IEEE.","DOI":"10.1109\/ICCV.2011.6126229"},{"key":"884_CR30","doi-asserted-by":"crossref","unstructured":"Nishimoto, S., Vu, A. T., Naselaris, T., Benjamini, Y., Yu, B., & Gallant, J. L. (2011). Reconstructing visual experiences from brain activity evoked by natural movies. Current Biology, 21(19), 1641\u20131646.","DOI":"10.1016\/j.cub.2011.08.031"},{"key":"884_CR31","doi-asserted-by":"crossref","unstructured":"Oliva, A., & Torralba, A. (2001). Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision, 42(3), 145\u2013175.","DOI":"10.1023\/A:1011139631724"},{"key":"884_CR32","unstructured":"Parikh, D., & Zitnick, C. (2011). Human-debugging of machines. In NIPS WCSSWC (Vol. 2, p. 7)."},{"key":"884_CR33","doi-asserted-by":"crossref","unstructured":"Parikh, D., & Zitnick, C. L. (2010). The role of features, algorithms and data in visual recognition. In 2010 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2328\u20132335). IEEE.","DOI":"10.1109\/CVPR.2010.5539920"},{"issue":"3","key":"884_CR34","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","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.","journal-title":"International Journal of Computer Vision"},{"key":"884_CR35","unstructured":"Sadeghi, M.A., & Forsyth, D. (2013). Fast template evaluation with vector quantization. In Advances in neural information processing systems (pp. 2949\u20132957)."},{"key":"884_CR36","unstructured":"Simonyan, K., Vedaldi, A., & Zisserman, A. (2013). Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 ."},{"key":"884_CR37","doi-asserted-by":"crossref","unstructured":"Tatu, A., Lauze, F., Nielsen, M., & Kimia, B. (2011). Exploring the representation capabilities of the hog descriptor. In 2011 IEEE international conference on computer vision workshops (ICCV Workshops) (pp. 1410\u20131417). IEEE.","DOI":"10.1109\/ICCVW.2011.6130416"},{"key":"884_CR38","doi-asserted-by":"crossref","unstructured":"Vondrick, C., Khosla, A., Malisiewicz, T., & Torralba. A. (2013). Hoggles: Visualizing object detection features. In Proceedings of the IEEE international conference on computer vision (pp. 1\u20138).","DOI":"10.1109\/ICCV.2013.8"},{"key":"884_CR39","unstructured":"Vondrick, C., Pirsiavash, H., Oliva, A., & Torralba, A. (2015). Learning visual biases from human imagination. In Advances in neural information processing systems (pp. 289\u2013297)."},{"key":"884_CR40","doi-asserted-by":"crossref","unstructured":"Wang, S., Zhang, L., Liang, Y., & Pan, Q. (2012). Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis. In 2012 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2216\u20132223). IEEE.","DOI":"10.1109\/CVPR.2012.6247930"},{"key":"884_CR41","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., J\u00e9gou, H., & P\u00e9rez, P. (2011). Reconstructing an image from its local descriptors. In 2011 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 337\u2013344). IEEE.","DOI":"10.1109\/CVPR.2011.5995616"},{"issue":"11","key":"884_CR42","doi-asserted-by":"crossref","first-page":"2861","DOI":"10.1109\/TIP.2010.2050625","volume":"19","author":"J Yang","year":"2010","unstructured":"Yang, J., Wright, J., Huang, T. S., & Ma, Y. (2010). Image super-resolution via sparse representation. IEEE Transactions on Image Processing, 19(11), 2861\u20132873.","journal-title":"IEEE Transactions on Image Processing"},{"key":"884_CR43","doi-asserted-by":"crossref","unstructured":"Zeiler, M. D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. In Computer vision\u2014ECCV 2014 (pp. 818\u2013833). Springer.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"884_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, L., Dibeklioglu, H., & van der Maaten, L. (2014). Speeding up tracking by ignoring features. In 2014 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1266\u20131273). IEEE.","DOI":"10.1109\/CVPR.2014.165"},{"key":"884_CR45","doi-asserted-by":"crossref","unstructured":"Zhu, X., Vondrick, C., Ramanan, D., & Fowlkes, C. (2012). Do we need more training data or better models for object detection? In: BMVC (Vol. 3, p. 5). Citeseer.","DOI":"10.5244\/C.26.80"},{"issue":"2","key":"884_CR46","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","volume":"67","author":"H Zou","year":"2005","unstructured":"Zou, H., & Hastie, T. (2005). Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 67(2), 301\u2013320.","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0884-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-016-0884-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-016-0884-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,5]],"date-time":"2019-09-05T00:15:40Z","timestamp":1567642540000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-016-0884-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3,1]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2016,9]]}},"alternative-id":["884"],"URL":"https:\/\/doi.org\/10.1007\/s11263-016-0884-7","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,3,1]]}}}