{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T10:41:25Z","timestamp":1761648085095},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,6,28]],"date-time":"2013-06-28T00:00:00Z","timestamp":1372377600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2013,10]]},"DOI":"10.1007\/s11263-013-0629-9","type":"journal-article","created":{"date-parts":[[2013,6,27]],"date-time":"2013-06-27T13:19:47Z","timestamp":1372339187000},"page":"1-18","source":"Crossref","is-referenced-by-count":1,"title":["Categorization of Multiple Objects in a Scene Using a Biased Sampling Strategy"],"prefix":"10.1007","volume":"105","author":[{"given":"Lei","family":"Yang","sequence":"first","affiliation":[]},{"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Mei","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,6,28]]},"reference":[{"key":"629_CR1","doi-asserted-by":"crossref","unstructured":"Achanta, R., Hemami, S., Estrada, F., & Susstrunk, S. (2009). Frequency-tuned salient region detection. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1597\u20131604).","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"629_CR2","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, 1475\u20131490.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"12","key":"629_CR3","doi-asserted-by":"crossref","first-page":"1931","DOI":"10.1109\/TPAMI.2006.248","volume":"28","author":"Y Chen","year":"2006","unstructured":"Chen, Y., Bi, J., & Wang, J. Z. (2006). Miles: Multiple-instance learning via embedded instance selection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(12), 1931\u20131947.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"629_CR4","doi-asserted-by":"crossref","unstructured":"Choi, M., Lim, J., Torralba, A., & Willsky, A. (2010). Exploiting hierarchical context on a large database of object categories. In IEEE Conference on Computer Vision and Pattern Recogntion (CVPR) (pp. 129\u2013136).","DOI":"10.1109\/CVPR.2010.5540221"},{"key":"629_CR5","unstructured":"Chum, O., & Zisserman, A. (2007). An exemplar model for learning object classes. In: detection. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1\u20138)."},{"key":"629_CR6","unstructured":"Csurka, G., Dance, C. R., Fan, L., Willamowski, J., & Bray, C. (2004). Visual categorization with bags of keypoints. In ECCV Workshop on Statistical Learning in Computer Vision (pp. 59\u201374)."},{"key":"629_CR7","doi-asserted-by":"crossref","unstructured":"Dork\u00f3 G, & Schmid C. (2003). Selection of scale-invariant parts for object class recognition. In International Conference on Computer Vision (ICCV) (Vol. 1, pp. 634\u2013640).","DOI":"10.1109\/ICCV.2003.1238407"},{"key":"629_CR8","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-4134-6","volume-title":"Measure, topology, and fractal geometry","author":"GA Edgar","year":"1990","unstructured":"Edgar, G. A. (1990). Measure, topology, and fractal geometry. Berlin: Springer."},{"key":"629_CR9","unstructured":"Everingham, M., Gool, L. V., Williams, C. K. I., Winn, J., & Zisserman, A. (2007). The PASCAL visual object classes challenge 2007 (VOC2007) Results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2007\/workshop\/index.html . Accessed 23 Oct 2007."},{"issue":"2","key":"629_CR10","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Gool, L. V., 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.","journal-title":"International Journal of Computer Vision"},{"key":"629_CR11","doi-asserted-by":"crossref","unstructured":"Fei-Fei, L., Fergus, R., & Perona, P. (2006). One-shot learning of object categories. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(4), 594\u2013611.","DOI":"10.1109\/TPAMI.2006.79"},{"issue":"2","key":"629_CR12","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"PF Felzenszwalb","year":"2004","unstructured":"Felzenszwalb, P. F., & Huttenlocher, D. P. (2004). Efficient graph-based image segmentation. International Journal of Computer Vision, 59(2), 167\u2013181.","journal-title":"International Journal of Computer Vision"},{"key":"629_CR13","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P., McAllester, D., & Ramanan, D. (2008). A discriminatively trained, multiscale, deformable part model. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2008.4587597"},{"issue":"1","key":"629_CR14","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1109\/TPAMI.2007.1144","volume":"30","author":"V Ferrari","year":"2008","unstructured":"Ferrari, V., Fevrier, L., Jurie, F., & Schmid, C. (2008). Groups of adjacent contour segments for object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(1), 36\u201351.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"629_CR15","doi-asserted-by":"crossref","unstructured":"Fulkerson, B., Vedaldi, A., & Soatto, S. (2008). Localizing objects with smart dictionaries. European Conference on Computer Vision (ECCV), I, 179\u2013192.","DOI":"10.1007\/978-3-540-88682-2_15"},{"key":"629_CR16","doi-asserted-by":"crossref","unstructured":"Galleguillos, C., Babenko, B., Rabinovich, A., & Belongie, S. (2008). Weakly supervised object localization with stable segmentations. In European Conference on Computer Vision (ECCV) (pp. 193\u2013207).","DOI":"10.1007\/978-3-540-88682-2_16"},{"key":"629_CR17","doi-asserted-by":"crossref","unstructured":"Harzallah, H., Jurie, F., & Schmid, C. (2009). Combining efficient object localization and image classification. In International Conference on Computer Vision (ICCV) (pp. 237\u2013244).","DOI":"10.1109\/ICCV.2009.5459257"},{"key":"629_CR18","doi-asserted-by":"crossref","unstructured":"Hou, X., & Zhang, L. (2007). Saliency detection: A spectral residual approach. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1\u20138).","DOI":"10.1109\/CVPR.2007.383267"},{"key":"629_CR19","unstructured":"Hu, M. (1962). Visual pattern recognition by moment invariants. IRE Transactions on Information Theory, IT-8, 179\u2013187."},{"key":"629_CR20","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., & Niebur, E. (1998). A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20, 1254\u20131259.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"629_CR21","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1007\/s11263-009-0285-2","volume":"87","author":"H J\u00e9gou","year":"2010","unstructured":"J\u00e9gou, H., Douze, M., & Schmid, C. (2010). Improving bag-of-features for large scale image search. International Journal of Computer Vision, 87(3), 316\u2013336.","journal-title":"International Journal of Computer Vision"},{"key":"629_CR22","doi-asserted-by":"crossref","unstructured":"Kang, F., Jin, R., & Sukthankar, R. (2006). Correlated label propagation with application to multi-label learning. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1719\u20131726).","DOI":"10.1109\/CVPR.2006.90"},{"key":"629_CR23","unstructured":"Khan, F. S., van de Weijer, J., & Vanrell, M. (2009). Top-down color attention for object recognition. In International Conference on Computer Vision (ICCV) (pp. 1719\u20131726)."},{"issue":"1","key":"629_CR24","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/0031-3203(86)90030-0","volume":"19","author":"J Kittler","year":"1986","unstructured":"Kittler, J., & Illingworth, J. (1986). Minimum error thresholding. Pattern Recognition, 19(1), 41\u201347.","journal-title":"Pattern Recognition"},{"issue":"12","key":"629_CR25","doi-asserted-by":"crossref","first-page":"2129","DOI":"10.1109\/TPAMI.2009.144","volume":"31","author":"CH Lampert","year":"2009","unstructured":"Lampert, C. H., Blaschko, M. B., & Hofmann, T. (2009). Efficient subwindow search: A branch and bound framework for object localization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(12), 2129\u20132142.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"629_CR26","doi-asserted-by":"crossref","unstructured":"Lazebnik, S., Schmid, C., & Ponce, J. (2006). Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Vol. 2, pp. 2169\u20132178).","DOI":"10.1109\/CVPR.2006.68"},{"key":"629_CR27","unstructured":"Leibe, B., Leonardis, A., & Schiele, B. (2004). Combined object categorization and segmentation with an implicit shape model. In ECCV Workshop on Statistical Learning in Computer Vision (pp. 17\u201332)."},{"key":"629_CR28","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1023\/A:1011126920638","volume":"43","author":"T Leung","year":"2001","unstructured":"Leung, T., & Malik, J. (2001). Representing and recognizing the visual appearance of materials using three-dimensional textons. International Journal of Computer Vision, 43, 29\u201344.","journal-title":"International Journal of Computer Vision"},{"issue":"6","key":"629_CR29","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1109\/TPAMI.2007.70847","volume":"30","author":"J Li","year":"2008","unstructured":"Li, J., & Wang, J. Z. (2008). Real-time computerized annotation of pictures. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(6), 985\u20131002.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"629_CR30","unstructured":"Li, L. J., Socher, R., & Fei-Fei, L. (2009). Towards total scene understanding:classification, annotation and segmentation in an automatic framework. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"issue":"2","key":"629_CR31","doi-asserted-by":"crossref","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":"629_CR32","doi-asserted-by":"crossref","unstructured":"Mairal, J., Leordeanu, M., Bach, F., Ponce, J., & Hebert, M. (2008). Discriminative sparse image models for class-specific edge detection and image interpretation. In European Conference on Computer Vision (ECCV) (Vol. 3, pp. 43\u201356).","DOI":"10.1007\/978-3-540-88690-7_4"},{"key":"629_CR33","doi-asserted-by":"crossref","unstructured":"Marsza\u0142ek, M., & Schmid, C. (2006). Spatial weighting for bag-of-features. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Vol. 2, pp. 2118\u20132125).","DOI":"10.1109\/CVPR.2006.288"},{"key":"629_CR34","unstructured":"Marsza\u0142ek, M., Schmid, C., Harzallah, H., & van de Weijer, J. (2007). Learning object representations for visual object class recognition. In Visual Recognition Challenge Workshop."},{"key":"629_CR35","doi-asserted-by":"crossref","unstructured":"Martin, D., Fowlkes, C., Tal, D., & Malik, J. (2001). A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In International Conference on Computer Vision (ICCV) (Vol. 2, pp. 416\u2013423).","DOI":"10.1109\/ICCV.2001.937655"},{"issue":"1","key":"629_CR36","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1023\/B:VISI.0000027790.02288.f2","volume":"60","author":"K Mikolajczyk","year":"2004","unstructured":"Mikolajczyk, K., & Schmid, C. (2004). Scale and affine invariant interest point detectors. International Journal of Computer Vision, 60(1), 63\u201386.","journal-title":"International Journal of Computer Vision"},{"issue":"9","key":"629_CR37","doi-asserted-by":"crossref","first-page":"1632","DOI":"10.1109\/TPAMI.2007.70822","volume":"30","author":"F Moosmann","year":"2008","unstructured":"Moosmann, F., Nowak, E., & Jurie, F. (2008). Randomized clustering forests for image classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(9), 1632\u20131646.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"629_CR38","volume-title":"An introduction to digital image processing","author":"W Niblack","year":"1986","unstructured":"Niblack, W. (1986). An introduction to digital image processing. Englewood Cliffs, NJ: Prentice\/Hall International."},{"key":"629_CR39","doi-asserted-by":"crossref","unstructured":"Nist\u00e9r, D., & Stew\u00e9nius, H. (2006). Scalable recognition with a vocabulary tree. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2161\u20132168).","DOI":"10.1109\/CVPR.2006.264"},{"key":"629_CR40","doi-asserted-by":"crossref","unstructured":"Nowak, E., Jurie, F., & Triggs, B. (2006). Sampling strategies for bag-of-features images classification. In European Conference on Computer Vision (ECCV) (Vol. 4, pp. 490\u2013503).","DOI":"10.1007\/11744085_38"},{"issue":"1","key":"629_CR41","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics SMC, 9(1), 62\u201366.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics SMC"},{"key":"629_CR42","doi-asserted-by":"crossref","unstructured":"Pantofaru, C., Dorko, G., Schmid, C., & Hebert, M. (2006). Combining regions and patches for object class localization. In CVPR Workshop on Beyond Patches (pp. 23\u201330).","DOI":"10.1109\/CVPRW.2006.57"},{"key":"629_CR43","doi-asserted-by":"crossref","unstructured":"Parikh, D., Zitnick, L., & Chen, T. (2008). Determining patch saliency using low-level context. In European Conference on Computer Vision (ECCV) (Vol. 2, pp. 446\u2013459).","DOI":"10.1007\/978-3-540-88688-4_33"},{"key":"629_CR44","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Senchez, J., & Liu, Y. (2010). Large-scale image categorization with explicit data embedding. In IEEE Conference on Computer Vision and Pattern Recogntion (CVPR) (pp. 2297\u20132304).","DOI":"10.1109\/CVPR.2010.5539914"},{"key":"629_CR45","doi-asserted-by":"crossref","unstructured":"Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., & Belongie, S. (2007). Objects in context. In International Conference on Computer Vision (ICCV) (pp. 1\u20138).","DOI":"10.1109\/ICCV.2007.4408986"},{"key":"629_CR46","doi-asserted-by":"crossref","unstructured":"Shotton, J., & Cipolla, R. (2008). Semantic texton forests for image categorization and segmentation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2008.4587503"},{"issue":"1","key":"629_CR47","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(1), 2\u201323.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"629_CR48","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1007\/s11263-005-6642-x","volume":"63","author":"Z Tu","year":"2005","unstructured":"Tu, Z., Chen, X., Yuille, A. L., & Zhu, S. C. (2005). Image parsing: Unifying segmentation, detection, and recognition. International Journal of Computer Vision, 63(2), 113\u2013140.","journal-title":"International Journal of Computer Vision"},{"key":"629_CR49","doi-asserted-by":"crossref","unstructured":"van de Sande, K. E. A., Gevers, T., & Snoek, C. G. M. (2008). A comparison of color features for visual concept classification. In ACM International Conference on Image and Video Retrieval (CIVR) (pp. 141\u2013150).","DOI":"10.1145\/1386352.1386376"},{"key":"629_CR50","doi-asserted-by":"crossref","unstructured":"van de Weijer, J., & Schmid, C. (2006). Coloring local feature extraction. In European Conference on Computer Vision (ECCV) (Vol. 2, pp. 334\u2013348).","DOI":"10.1007\/11744047_26"},{"key":"629_CR51","unstructured":"Walther, D., Rutishauser, U., Hoch, C., & Perona, P. (2004). On the usefulness of attention for object recognition. In European Conference on Computer Vision (ECCV) (pp. 96\u2013103)."},{"key":"629_CR52","unstructured":"Wang, C., Blei, D. M., & Li, F. F. (2009). Simultaneous image classification and annotation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1903\u20131910)."},{"key":"629_CR53","unstructured":"Yang, L., Zheng, N., Chen, M., Yang, Y., & Yang, J. (2009a). Categorization of multiple objects in a scene without semantic segmentation. In Asian Conference of Computer Vision."},{"key":"629_CR54","unstructured":"Yang, L., Zheng, N., Yang, J., Chen, M., & Chen, H. (2009b). A biased sampling strategy for object categorization. In International Conference on Computer Vision (ICCV)."},{"key":"629_CR55","unstructured":"Zha, Z., Hua, X., Mei, T., Wang, J., Qi, G., & Wang, Z. (2008). Joint multi-label multi-instance learning for image classification. In IEEE Conference on Computer Vision and Pattern Recogntion (CVPR) (pp. 1\u20138)."},{"issue":"2","key":"629_CR56","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"},{"key":"629_CR57","unstructured":"Zhang, M., & Zhou, Z. (2007). Multi-label learning by instance differentiation. In AAAI Conference on Artificial Intelligence (pp. 669\u2013674)."},{"key":"629_CR58","doi-asserted-by":"crossref","unstructured":"Zhou, Z., & Zhang, M. (2007). Multi-instance multi-label learning with application to scene classification. In Advances in Neural Information Processing Systems (pp. 1609\u20131616).","DOI":"10.7551\/mitpress\/7503.003.0206"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-013-0629-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-013-0629-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-013-0629-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,2]],"date-time":"2023-07-02T17:41:18Z","timestamp":1688319678000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-013-0629-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,6,28]]},"references-count":58,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,10]]}},"alternative-id":["629"],"URL":"https:\/\/doi.org\/10.1007\/s11263-013-0629-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,6,28]]}}}