{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T01:54:32Z","timestamp":1762998872417,"version":"3.37.3"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2012,1]]},"DOI":"10.1007\/s11263-011-0443-1","type":"journal-article","created":{"date-parts":[[2011,5,9]],"date-time":"2011-05-09T15:10:20Z","timestamp":1304953820000},"page":"46-63","source":"Crossref","is-referenced-by-count":19,"title":["The Visual Extent of an Object"],"prefix":"10.1007","volume":"96","author":[{"given":"J. R. R.","family":"Uijlings","sequence":"first","affiliation":[]},{"given":"A. W. M.","family":"Smeulders","sequence":"additional","affiliation":[]},{"given":"R. J. H.","family":"Scha","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2011,5,10]]},"reference":[{"issue":"11","key":"443_CR1","doi-asserted-by":"crossref","first-page":"1475","DOI":"10.1109\/TPAMI.2004.108","volume":"26","author":"S. Agarwal","year":"2004","unstructured":"Agarwal, S., Awan, A., & Roth, D. (2004). Learning to detect objects in images via a sparse, part-based representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(11), 1475\u20131490.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"443_CR2","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1038\/nrn1476","volume":"5","author":"M. Bar","year":"2004","unstructured":"Bar, M. (2004). Visual objects in context. Nature Reviews. Neuroscience, 5, 617\u2013629.","journal-title":"Nature Reviews. Neuroscience"},{"key":"443_CR3","first-page":"213","volume-title":"Perceptual organization","author":"I. Biederman","year":"1981","unstructured":"Biederman, I. (1981). On the semantics of a glance at a scene. In Perceptual organization (pp. 213\u2013263). Hillsdale: Lawrence Erlbaum."},{"key":"443_CR4","volume-title":"Pattern recognition and machine intelligence","author":"C. M. Bishop","year":"2006","unstructured":"Bishop, C. M. (2006). Pattern recognition and machine intelligence. Berlin: Springer."},{"key":"443_CR5","volume-title":"British machine vision conference","author":"M. B. Blaschko","year":"2009","unstructured":"Blaschko, M. B., & Lampert, C. H. (2009). Object localization with global and local context kernels. In British machine vision conference."},{"key":"443_CR6","volume-title":"European conference on computer vision","author":"M. C. Burl","year":"1998","unstructured":"Burl, M. C., Weber, M., & Perona, P. (1998). A probabilistic approach to object recognition using local photometry and global geometry. In European conference on computer vision."},{"key":"443_CR7","volume-title":"European conference on computer vision","author":"P. Carbonetto","year":"2004","unstructured":"Carbonetto, P., de Freitas, N., & Barnard, K. (2004). A statistical model for general contextual object recognition. In European conference on computer vision. Berlin: Springer."},{"key":"443_CR8","volume-title":"ECCV international workshop on statistical learning in computer vision","author":"G. Csurka","year":"2004","unstructured":"Csurka, G., Dance, C. R., Fan, L., Willamowski, J., & Bray, C. (2004). Visual categorization with bags of keypoints. In ECCV international workshop on statistical learning in computer vision, Prague."},{"key":"443_CR9","volume-title":"IEEE conference on computer vision and pattern recognition","author":"N. Dalal","year":"2005","unstructured":"Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In IEEE conference on computer vision and pattern recognition."},{"key":"443_CR10","volume-title":"IEEE conference on computer vision and pattern recognition","author":"S. K. Divvala","year":"2009","unstructured":"Divvala, S. K., Hoiem, D., Hays, J. H., Efros, A. A., & Herbert, M. (2009). An empirical study of context in object detection. In IEEE conference on computer vision and pattern recognition."},{"key":"443_CR11","doi-asserted-by":"crossref","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. I., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge. International Journal of Computer Vision, 88, 303\u2013338.","journal-title":"International Journal of Computer Vision"},{"key":"443_CR12","volume-title":"IEEE conference on computer vision and pattern recognition","author":"R. Fergus","year":"2003","unstructured":"Fergus, R., Perona, P., & Zisserman, A. (2003). Object class recognition by unsupervised scale-invariant learning. In IEEE conference on computer vision and pattern recognition."},{"key":"443_CR13","volume-title":"IEEE international conference on computer vision","author":"B. Fulkerson","year":"2009","unstructured":"Fulkerson, B., Vedaldi, A., & Soatto, S. (2009). Class segmentation and object localization with superpixel neighborhoods. In IEEE international conference on computer vision."},{"issue":"1","key":"443_CR14","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"P. Geurts","year":"2006","unstructured":"Geurts, P., Ernst, D., & Wehenkel, L. (2006). Extremely randomized trees. Machine Learning, 63(1), 3\u201342.","journal-title":"Machine Learning"},{"key":"443_CR15","volume-title":"IEEE international conference on computer vision","author":"S. Gould","year":"2009","unstructured":"Gould, S., Fulton, R., & Koller, D. (2009). Decomposing a scene into geometric and semantically consistent regions. In IEEE international conference on computer vision."},{"key":"443_CR16","volume-title":"IEEE international conference on computer vision","author":"H. Harzallah","year":"2009","unstructured":"Harzallah, H., Jurie, F., & Schmid, C. (2009). Combining efficient object localization and image classification. In IEEE international conference on computer vision."},{"key":"443_CR17","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s11263-008-0137-5","volume":"80","author":"D. Hoiem","year":"2008","unstructured":"Hoiem, D., Efros, A. A., & Hebert, M. (2008). Putting objects in perspective. International Journal of Computer Vision, 80, 3\u201315.","journal-title":"International Journal of Computer Vision"},{"key":"443_CR18","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1145\/1282280.1282352","volume-title":"ACM international conference on image and video retrieval","author":"Y. G. Jiang","year":"2007","unstructured":"Jiang, Y. G., Ngo, C. W., & Yang, J. (2007). Towards optimal bag-of-features for object categorization and semantic video retrieval. In ACM international conference on image and video retrieval (pp. 494\u2013501). New York: ACM Press."},{"key":"443_CR19","volume-title":"IEEE international conference on computer vision","author":"F. Jurie","year":"2005","unstructured":"Jurie, F., & Triggs, B. (2005). Creating efficient codebooks for visual recognition. In IEEE international conference on computer vision."},{"key":"443_CR20","volume-title":"IEEE conference on computer vision and pattern recognition","author":"S. Lazebnik","year":"2006","unstructured":"Lazebnik, S., Schmid, C., & Ponce, J. (2006). Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In IEEE conference on computer vision and pattern recognition, New York."},{"key":"443_CR21","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D. G. Lowe","year":"2004","unstructured":"Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60, 91\u2013110.","journal-title":"International Journal of Computer Vision"},{"key":"443_CR22","volume-title":"IEEE conference on computer vision and pattern recognition","author":"S. Maji","year":"2008","unstructured":"Maji, S., Berg, A. C., & Malik, J. (2008). Classification using intersection kernel support vector machines is efficient. In IEEE conference on computer vision and pattern recognition."},{"key":"443_CR23","volume-title":"British machine vision conference","author":"T. Malisiewicz","year":"2007","unstructured":"Malisiewicz, T., & Efros, A. A. (2007). Improving spatial support for objects via multiple segmentations. In British machine vision conference, September 2007."},{"key":"443_CR24","volume-title":"Neural information processing systems","author":"T. Malisiewicz","year":"2009","unstructured":"Malisiewicz, T., & Efros, A. A. (2009). Beyond categories: the visual memex model for reasoning about object relationships. In Neural information processing systems."},{"key":"443_CR25","volume-title":"ICCV Pascal VOC 2007 challenge workshop","author":"M. Marsza\u0142ek","year":"2007","unstructured":"Marsza\u0142ek, M., Schmid, C., Harzallah, H., & van\u00a0de Weijer, J. (2007). Learning representations for visual object class recognition. In ICCV Pascal VOC 2007 challenge workshop."},{"issue":"10","key":"443_CR26","doi-asserted-by":"crossref","first-page":"1615","DOI":"10.1109\/TPAMI.2005.188","volume":"27","author":"K. Mikolajczyk","year":"2005","unstructured":"Mikolajczyk, K., & Schmid, C. (2005). A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(10), 1615\u20131630.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"443_CR27","first-page":"985","volume-title":"Neural information processing systems","author":"F. Moosmann","year":"2006","unstructured":"Moosmann, F., Triggs, B., & Jurie, F. (2006). Fast discriminative visual codebooks using randomized clustering forests. In Neural information processing systems (pp. 985\u2013992)."},{"key":"443_CR28","doi-asserted-by":"crossref","first-page":"1673","DOI":"10.1109\/TPAMI.2009.174","volume":"32","author":"V. Nedovi\u0107","year":"2010","unstructured":"Nedovi\u0107, V., & Smeulders, A. W. M. (2010). Stages as models of scene geometry. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32, 1673\u20131687.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"443_CR29","volume-title":"European conference on computer vision","author":"E. Nowak","year":"2006","unstructured":"Nowak, E., Jurie, F., & Triggs, B. (2006). Sampling strategies for bag-of-features image classification. In European conference on computer vision."},{"issue":"3","key":"443_CR30","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1023\/A:1011139631724","volume":"42","author":"A. Oliva","year":"2001","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.","journal-title":"International Journal of Computer Vision"},{"key":"443_CR31","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1016\/j.tics.2007.09.009","volume":"11","author":"A. Oliva","year":"2007","unstructured":"Oliva, A., & Torralba, A. (2007). The role of context in object recognition. Trends in Cognitive Sciences, 11, 520\u2013527.","journal-title":"Trends in Cognitive Sciences"},{"key":"443_CR32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICCV.2007.4408986","volume-title":"International conference on computer vision","author":"A. Rabinovich","year":"2007","unstructured":"Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., & Belongie, S. (2007). Objects in context. In International conference on computer vision (pp. 1\u20138)."},{"key":"443_CR33","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1007\/s11263-007-0109-1","volume":"81","author":"J. Shotton","year":"2009","unstructured":"Shotton, J., Winn, J., Rother, C., & Criminisi, A. (2009). Textonboost for image understanding: multi-class object recognition and segmentation by jointly modeling texture, layout, and context. International Journal of Computer Vision, 81, 2\u201323.","journal-title":"International Journal of Computer Vision"},{"key":"443_CR34","volume-title":"IEEE conference on computer vision and pattern recognition","author":"A. Singhal","year":"2003","unstructured":"Singhal, A., Luo, J., & Zhu, W. (2003). Probabilistic spatial context models for scene content understanding. In IEEE conference on computer vision and pattern recognition."},{"key":"443_CR35","volume-title":"IEEE international conference on computer vision","author":"J. Sivic","year":"2003","unstructured":"Sivic, J., & Zisserman, A. (2003). Video Google: a text retrieval approach to object matching in videos. In IEEE international conference on computer vision."},{"key":"443_CR36","volume-title":"ACM SIGMM international workshop on multimedia information Retrieval","author":"A. F. Smeaton","year":"2006","unstructured":"Smeaton, A. F., Over, P. & Kraaij, W. (2006). Evaluation campaigns and TRECVID. In ACM SIGMM international workshop on multimedia information Retrieval."},{"issue":"12","key":"443_CR37","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1109\/34.895972","volume":"22","author":"A. W. M. Smeulders","year":"2000","unstructured":"Smeulders, A. W. M., Worring, M., Santini, S., Gupta, A., & Jain,\u00a0R. (2000). Content-based image retrieval at the end of the early years. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(12), 1349\u20131380.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"443_CR38","volume-title":"ECCV Pascal VOC 2008 challenge workshop.","author":"M. A. Tahir","year":"2008","unstructured":"Tahir, M. A., van\u00a0de Sande, K., Uijlings, J., Yan, F., Li, X., Mikolajczyk, K., Kittler, J., Gevers, T., & Smeulders, A. (2008). UVA and surrey @ Pascal VOC 2008. In ECCV Pascal VOC 2008 challenge workshop."},{"key":"443_CR39","volume-title":"IEEE international conference on computer vision","author":"T. Tuytelaars","year":"2007","unstructured":"Tuytelaars, T., & Schmid, C. (2007). Vector quantizing feature space with a regular lattice. In IEEE international conference on computer vision."},{"key":"443_CR40","volume-title":"IEEE conference on computer vision and pattern recognition","author":"J. R. R. Uijlings","year":"2009","unstructured":"Uijlings, J. R. R., Smeulders, A. W. M., & Scha, R. J. H. (2009). What is the spatial extent of an object? In IEEE conference on computer vision and pattern recognition."},{"key":"443_CR41","doi-asserted-by":"crossref","unstructured":"Uijlings, J. R. R., Smeulders, A. W. M., & Scha, R. J. H. (2010, in press). Real-time visual concept classification. IEEE Transactions on Multimedia. http:\/\/dx.doi.org\/10.1109\/TMM.2010.2052027","DOI":"10.1109\/TMM.2010.2052027"},{"key":"443_CR42","volume-title":"British machine vision conference","author":"M. M. Ullah","year":"2010","unstructured":"Ullah, M. M., Parizi, S. N., & Laptev, I. (2010). Improving bag-of-features action recognition with non-local cues. In British machine vision conference."},{"key":"443_CR43","doi-asserted-by":"crossref","first-page":"1582","DOI":"10.1109\/TPAMI.2009.154","volume":"32","author":"K. E. A. Sande van\u00a0de","year":"2010","unstructured":"van\u00a0de Sande, K. E. A., Gevers, T., & Snoek, C. G. M. (2010). Evaluating color descriptors for object and scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32, 1582\u20131596.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"443_CR44","volume-title":"IEEE conference on computer vision and pattern recognition","author":"A. Vedaldi","year":"2010","unstructured":"Vedaldi, A., & Zisserman, A. (2010). Efficient additive kernels via explicit feature maps. In IEEE conference on computer vision and pattern recognition."},{"key":"443_CR45","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1007\/s11263-006-7538-0","volume":"69","author":"L. Wolf","year":"2006","unstructured":"Wolf, L., & Bileschi, S. (2006). A critical view of context. International Journal of Computer Vision, 69, 251\u2013261.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"443_CR46","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/s11263-006-9794-4","volume":"73","author":"J. Zhang","year":"2007","unstructured":"Zhang, J., Marsza\u0142ek, M., Lazebnik, S., & Schmid, C. (2007). Local features and Kernels for classification of texture and object categories: a comprehensive study. International Journal of Computer Vision, 73(2), 213\u2013238.","journal-title":"International Journal of Computer Vision"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.springerlink.com\/index\/pdf\/10.1007\/s11263-011-0443-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,10]],"date-time":"2019-06-10T13:05:33Z","timestamp":1560171933000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-011-0443-1"}},"subtitle":["Suppose We Know the Object Locations"],"short-title":[],"issued":{"date-parts":[[2011,5,10]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2012,1]]}},"alternative-id":["443"],"URL":"https:\/\/doi.org\/10.1007\/s11263-011-0443-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2011,5,10]]}}}