{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T03:20:24Z","timestamp":1761708024893},"publisher-location":"Berlin, Heidelberg","reference-count":37,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540687948"},{"type":"electronic","value":"9783540687955"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11957959_2","type":"book-chapter","created":{"date-parts":[[2007,1,25]],"date-time":"2007-01-25T00:00:09Z","timestamp":1169683209000},"page":"29-48","source":"Crossref","is-referenced-by-count":119,"title":["Dataset Issues in Object Recognition"],"prefix":"10.1007","author":[{"given":"J.","family":"Ponce","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"T. L.","family":"Berg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Everingham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D. A.","family":"Forsyth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Hebert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Lazebnik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Marszalek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.","family":"Schmid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"B. C.","family":"Russell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.","family":"Torralba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C. K. I.","family":"Williams","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J.","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.","family":"Zisserman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"2_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/3-540-47979-1_8","volume-title":"Computer Vision - ECCV 2002","author":"S. Agarwal","year":"2002","unstructured":"Agarwal, S., Roth, D.: Learning a Sparse Representation for Object Detection. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol.\u00a02353, pp. 113\u2013127. Springer, Heidelberg (2002)"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Barnard, K., Duyguly, P., Forsyth, D.: Clustering art. In: Proc. IEEE Conf. Comp. Vision Patt. Recog., vol.\u00a0II, pp. 435\u2013439 (2001)","DOI":"10.1109\/CVPR.2001.990994"},{"key":"2_CR3","doi-asserted-by":"publisher","first-page":"1107","DOI":"10.1162\/153244303322533214","volume":"3","author":"K. Barnard","year":"2003","unstructured":"Barnard, K., Duygulu, P., Forsyth, D., de Freitas, N., Blei, D., Jordan, M.: Matching words and pictures. Journal of Machine Learning Research\u00a03, 1107\u20131135 (2003)","journal-title":"Journal of Machine Learning Research"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Berg, A., Berg, T.L., Malik, J.: Shape matching and object recognition using low distortion correspondence. In: Proc. IEEE Conf. Comp. Vision Patt. Recog., vol.\u00a0II, pp. 435\u2013439 (2005)","DOI":"10.1109\/CVPR.2005.320"},{"key":"2_CR5","unstructured":"Berg, A.C.: Ph.D thesis (to appear)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Berg, T.L., Berg, A.C., Edwards, J., Forsyth, D.: Who\u2019s in the picture? In: Proc. Neural Inf. Proc. Syst. (2004)","DOI":"10.2175\/193864704784107335"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Berg, T.L., Forsyth, D.: Animals on the Web. In: Proc. IEEE Conf. Comp. Vision Patt. Recog. (2006)","DOI":"10.1109\/CVPR.2006.57"},{"key":"2_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/11736790_8","volume-title":"Machine Learning Challenges. Evaluating Predictive Uncertainty, Visual Object Classification, and Recognising Tectual Entailment","author":"M. Everingham","year":"2006","unstructured":"Everingham, M., Zisserman, A., Williams, C., Van Gool, L., Allan, M., Bishop, C., Chapelle, O., Dalal, N., Deselaers, T., Dorko, G., Duffner, S., Eichhorn, J., Farquhar, J., Fritz, M., Garcia, C., Griffiths, T., Jurie, F., Keysers, D., Koskela, M., Laaksonen, J., Larlus, D., Leibe, B., Meng, H., Ney, H., Schiele, B., Schmid, C., Seemann, E., Shawe-Taylor, J., Storkey, A., Szedmak, S., Triggs, B., Ulusoy, I., Viitaniemi, V., Zhang, J.: The 2005 PASCAL visual object classes challenge. In: Qui\u00f1onero-Candela, J., Dagan, I., Magnini, B., d\u2019Alch\u00e9-Buc, F. (eds.) MLCW 2005. LNCS, vol.\u00a03944, pp. 117\u2013176. Springer, Heidelberg (2006)"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: Proc. IEEE Conf. Comp. Vision Patt. Recog. Workshop on Generative-Model Based Vision (2004)","DOI":"10.1109\/CVPR.2004.383"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proc. IEEE Conf. Comp. Vision Patt. Recog., vol.II, pp. 264\u2013271 (2003)","DOI":"10.1109\/CVPR.2003.1211479"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Fergus, R., Perona, P., Zisserman, A.: A visual category filter for Google images. In: Proc. Europ. Conf. Comp. Vision (2004)","DOI":"10.1007\/978-3-540-24670-1_19"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Fergus, R., Fei-Fei, L., Perona, P., Zisserman, A.: Learning object categories from Google\u2019s image search. In: Proc. Int. Conf. Comp. Vision (2005)","DOI":"10.1109\/ICCV.2005.142"},{"key":"2_CR13","unstructured":"Giridharan, I., Duygulu, P., Feng, S., Ircing, P., Khudanpur, S., Klakow, D., Krause, M., Manmatha, R., Nock, H., Petkova, D., Pytlik, B., Virga, P.: Joint visual-text modeling for automatic retrieval of multimedia documents. In: Proc. ACM Multimedia Conference (2005)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Grauman, K., Darrell, T.: The pyramid match kernel: Discriminative classification with sets of image features.MIT-CSAIL-TR-2006-020 (2006) Updated version of the ICCV 2005 paper with the same title, featuring the improved results shown in Fig. 4","DOI":"10.1109\/ICCV.2005.239"},{"key":"2_CR15","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1023\/A:1007617005950","volume":"43","author":"T. Hofmann","year":"2001","unstructured":"Hofmann, T.: Unsupervised learning by probabilistic latent semantic analysis. Machine Learning\u00a043, 177\u2013196 (2001)","journal-title":"Machine Learning"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Hoiem, D., Efros, A., Hebert, M.: Geometric context from a single image. In: Proc. Int. Conf. Comp. Vision (2005)","DOI":"10.1109\/ICCV.2005.107"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Holub, A., Welling, M., Perona, P.: Combining generative models and fisher kernels for object class recognition. In: Proc. Int. Conf. Comp. Vision (2005)","DOI":"10.1109\/ICCV.2005.56"},{"key":"2_CR18","unstructured":"Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: Proc. IEEE Conf. Comp. Vision Patt. Recog. (2005)"},{"issue":"9","key":"2_CR19","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1109\/TPAMI.2003.1227984","volume":"25","author":"J. Li","year":"2003","unstructured":"Li, J., Wang, J.: Automatic linguistic indexing of pictures by a statistical modeling approach. PAMI\u00a025(9), 1075\u20131088 (2003)","journal-title":"PAMI"},{"key":"2_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/3-540-45479-9_5","volume-title":"Image and Video Retrieval","author":"H. M\u00fcller","year":"2002","unstructured":"M\u00fcller, H., Marchand-Maillet, S., Pun, T.: The Truth about Corel - Evaluation in Image Retrieval. In: Lew, M., Sebe, N., Eakins, J.P. (eds.) CIVR 2002. LNCS, vol.\u00a02383, p. 38. Springer, Heidelberg (2002)"},{"key":"2_CR21","unstructured":"Mutch, J., Lowe, D.: Multiclass object recognition using sparse, localized features. In: Proc. IEEE Conf. Comp. Vision Patt. Recog. (2006)"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Ommer, B., Buhmann, J.M.: Learning compositional categorization models. In: Proc. Europ. Conf. Comp. Vision (2006)","DOI":"10.1007\/11744078_25"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Philips, P., Newton, E.: Meta-analysis of face recognition algorithms. In: Int. Conf. on Automatic Face and Gesture Recognition (2002)","DOI":"10.1109\/AFGR.2002.1004160"},{"issue":"2","key":"2_CR24","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1023\/A:1026543900054","volume":"40","author":"Y. Rubner","year":"2000","unstructured":"Rubner, Y., Tomasi, C., Guibas, L.: The Earth Mover\u2019s distance as a metric for image retrieval. International Journal of Computer Vision\u00a040(2), 99\u2013121 (2000)","journal-title":"International Journal of Computer Vision"},{"key":"2_CR25","unstructured":"Russell, B.C., Torralba, A., Murphy, K.P., Freeman, W.T.: LabelMe: a database and web-based tool for image annotation. Technical report. MIT, AI Lab Memo AIM-2005-025 (2005)"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Serre, T., Wolf, L., Poggio, T.: Object recognition with features inspired by visual cortex. In: Proc. IEEE Conf. Comp. Vision Patt. Recog. (2005)","DOI":"10.1109\/CVPR.2005.254"},{"issue":"3","key":"2_CR27","first-page":"19","volume":"14","author":"D. Stork","year":"1999","unstructured":"Stork, D.: The open mind initiative. IEEE Intelligent Systems and Their Applications\u00a014(3), 19\u201320 (1999)","journal-title":"IEEE Intelligent Systems and Their Applications"},{"issue":"2","key":"2_CR28","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1023\/A:1023052124951","volume":"53","author":"A. Torralba","year":"2003","unstructured":"Torralba, A.: Contextual priming for object detection. International Journal of Computer Vision\u00a053(2), 153\u2013167 (2003)","journal-title":"International Journal of Computer Vision"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"von Ahn, L., Dabbish, L.: Labeling images with a computer game. In: Proc. ACM Conf. Hum. Factors Comp. Syst. (CHI) (2004)","DOI":"10.1145\/985692.985733"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"von\u00a0Ahn, L., Liu, R., Blum, M.: Peekaboom: A game for locating objects in images. In: Proc. ACM Conf. Hum. Factors Comp. Syst. (CHI) (2006)","DOI":"10.1145\/1124772.1124782"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Wang, G., Zhang, Y., Fei-Fei, L.: Using dependent regions for object categorization in a generative framework. In: Proc. IEEE Conf. Comp. Vision Patt. Recog. (2006)","DOI":"10.1109\/CVPR.2006.324"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Yanai, K., Barnard, K.: Probabilistic web image gathering. In: Workshop on MIR (2005)","DOI":"10.1145\/1101826.1101838"},{"key":"2_CR33","unstructured":"Zhang, H., Berg, A.C., Maire, M., Malik, J.: SVM-KNN: Discriminative nearest neighbor classification for visual category recognition. In: Proc. IEEE Conf. Comp. Vision Patt. Recog. (2006)"},{"key":"2_CR34","unstructured":"Zhang, J., Marszalek, M., Lazebnik, S., Schmid, C.: Local features and kernels for classification of texture and object categories: An in-depth study.Technical Report RR-5737, INRIA Rh\u00f4ne-Alpes (2005)"},{"key":"2_CR35","unstructured":"http:\/\/www.vision.ethz.ch\/projects\/cogvis\/CogVis-images\/image-samples.html"},{"key":"2_CR36","unstructured":"http:\/\/www1.cs.columbia.edu\/CAVE\/research\/softlib\/coil-100.html"},{"key":"2_CR37","unstructured":"http:\/\/www.flickr.com"}],"container-title":["Lecture Notes in Computer Science","Toward Category-Level Object Recognition"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11957959_2.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,8]],"date-time":"2021-08-08T02:52:00Z","timestamp":1628391120000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11957959_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540687948","9783540687955"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/11957959_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}