{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:27:36Z","timestamp":1783099656675,"version":"3.54.6"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2014,4,7]],"date-time":"2014-04-07T00:00:00Z","timestamp":1396828800000},"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":[[2014,12]]},"DOI":"10.1007\/s11263-014-0713-9","type":"journal-article","created":{"date-parts":[[2014,4,5]],"date-time":"2014-04-05T23:46:10Z","timestamp":1396741570000},"page":"328-348","source":"Crossref","is-referenced-by-count":108,"title":["ImageNet Auto-Annotation with Segmentation Propagation"],"prefix":"10.1007","volume":"110","author":[{"given":"Matthieu","family":"Guillaumin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"K\u00fcttel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vittorio","family":"Ferrari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2014,4,7]]},"reference":[{"key":"713_CR1","unstructured":"The PASCAL Visual Object Classes. http:\/\/pascallin.ecs.soton.ac.uk\/challenges\/VOC\/"},{"key":"713_CR2","unstructured":"Alexe, B., Deselaers, T., & Ferrari, V. (2010). ClassCut for unsupervised class segmentation. In: Proceedings of the European Conference on Computer Vision."},{"key":"713_CR3","doi-asserted-by":"crossref","unstructured":"Alexe, B., Deselaers, T., & Ferrari, V. (2010). What is an object? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR.2010.5540226"},{"key":"713_CR4","unstructured":"Arora, H., Loeff, N., Forsyth, D., & Ahuja, N. (2007). Unsupervised segmentation of objects using efficient learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis."},{"key":"713_CR5","unstructured":"Aytar, Y., & Zisserman, A. (2011). Tabula rasa: Model transfer for object category detection. In: Proceedings of the International Conference on Computer Vision."},{"key":"713_CR6","unstructured":"Aytar, Y., & Zisserman, A. (2012). Enhancing exemplar svms using part level transfer regularization. In: Proceedings of the British Machine Vision Conference."},{"key":"713_CR7","unstructured":"Batra, D., Kowdle, A., Parikh, D., Luo, J., & Chen, T. (2010). iCoseg: Interactive co-segmentation with intelligent scribble guidance. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 3169\u20133176)."},{"key":"713_CR8","doi-asserted-by":"crossref","unstructured":"Batra, D., Kowdle, A., Parikh, D., Luo, J., Chen, T. (2011). Interactively co-segmentating topically related images with intelligent scribble guidance. International Journal of Computer Vision, 93(3) 273\u2013292","DOI":"10.1007\/s11263-010-0415-x"},{"key":"713_CR9","unstructured":"Bertelli, L., Yu, T., Vu, D., & Gokturk, S. (2011). Kernelized structural SVM learning for supervised object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR10","unstructured":"Blake, A., Rother, C., Brown, M., Perez, P., & Torr, P. (2004). Interactive image segmentation using an adaptive GMMRF model. In: Proceedings of the 8th European Conference on Computer Vision, Prague, Czech Republic."},{"key":"713_CR11","unstructured":"Borenstein, E., Sharon, E., & Ullman, S. (2004). Combining top-down and bottom-up segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC."},{"key":"713_CR12","unstructured":"Boykov, Y., & Jolly, M.P. (2001). Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: Proceedings of the 8th International Conference on Computer Vision, Vancouver, Canada."},{"key":"713_CR13","unstructured":"Carreira, J., & Sminchisescu, C. (2010). Constrained parametric min cuts for automatic object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR14","unstructured":"Chai, Y., Lempitsky, V., & Zisserman, A. (2011).Bicos: A bi-level co-segmentation method for image classification. In: Proceedings of the International Conference on Computer Vision (pp. 2579\u20132586)."},{"key":"713_CR15","doi-asserted-by":"crossref","unstructured":"Chai, Y., Rahtu, E., Lempitsky, V., Gool, L.V., & Zisserman, A. (2012). Tricos: A tri-level class-discriminative co-segmentation method for image classification. In: Proceedings of the European Conference on Computer Vision","DOI":"10.1007\/978-3-642-33718-5_57"},{"key":"713_CR16","first-page":"886","volume":"2","author":"N Dalal","year":"2005","unstructured":"Dalal, N., & Triggs, B. (2005). Histogram of oriented gradients for human detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2, 886\u2013893.","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"713_CR17","unstructured":"Deng, J., Berg, A., Satheesh, S., Su, H., Khosla, A., & Fei-Fei, L. ImageNet Large Scale Visual Recognition Challenge 2012 (ILSVRC2012). http:\/\/www.image-net.org\/challenges\/LSVRC\/2012\/"},{"key":"713_CR18","doi-asserted-by":"crossref","unstructured":"Deng, J., Berg, A.C., Li, K., & Fei-Fei, L. (2010). What does classifying more than 10,000 image categories tell us? In: Proceedings of the European Conference on Computer Vision.","DOI":"10.1007\/978-3-642-15555-0_6"},{"key":"713_CR19","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., & Fei-fei, L. (2009). ImageNet: A large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR20","unstructured":"Deng, J., Krause, J., Berg, A., & Fei-Fei, L. (2012). Hedging your bets: Optimizing accuracy-specificity trade-offs in large scale visual recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR21","unstructured":"Deng, J., Satheesh, S., Berg, A., & Fei-Fei, L. (2011). Fast and balanced: Efficient label tree learning for large scale object recognition. In: Advances in Neural Information Processing Systems."},{"key":"713_CR22","unstructured":"Deselaers, T., Alexe, B., & Ferrari, V. (2010). Localizing objects while learning their appearance. In: Proceedings of the European Conference on Computer Vision."},{"key":"713_CR23","unstructured":"Deselaers, T., & Ferrari, V. (2011). Visual and semantic similarity in imagenet. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR24","unstructured":"Endres, I. & Hoiem, D. (2010). Category independent object proposals. In: Proceedings of the European Conference on Computer Vision."},{"key":"713_CR25","unstructured":"Fei-Fei, L., Fergus, R. & Perona, P. (2004). Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. In: CVPR Workshop of Generative Model Based Vision."},{"issue":"2","key":"713_CR26","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":"713_CR27","unstructured":"Gong, Y. & Lazebnik, S. (2011). Iterative quantization: A procrustean approach to learning binary codes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR28","unstructured":"Guillaumin, M. & Ferrari, V. (2012). Large-scale knowledge transfer for object localization in imagenet. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR29","unstructured":"Guillaumin, M., Mensink, T., Verbeek, J. & Schmid, C. (2009). TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation. In: Proceedings of the International Conference on Computer Vision."},{"key":"713_CR30","unstructured":"Hays, J., & Efros, A. (2007). Scene completion using millions of photographs. In: Proceedings of the ACM SIGGRAPH Conference on Computer Graphics."},{"key":"713_CR31","unstructured":"Jiang, H. (2009). Human pose estimation using consistent max-covering. In: roceedings of the International Conference on Computer Vision."},{"key":"713_CR32","unstructured":"Jojic, N., Perina, A., Cristani, M., Murino, V. & Frey, B. (2009). Stel component analysis: Modeling spatial correlations in image class structure. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR33","unstructured":"Joulin, A., Bach, F. & Ponce, J. (2010). Discriminative clustering for image co-segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 1943\u20131950)."},{"key":"713_CR34","unstructured":"Kim, G., Xing, E., Fei-Fei, L. & Kanade, T. (2011). Distributed cosegmentation via submodular optimization on anisotropic diffusion. In: Proceedings of the International Conference on Computer Vision (pp. 169\u2013176)."},{"key":"713_CR35","unstructured":"Krizhevsky, A., Sutskever, I. & Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems."},{"key":"713_CR36","unstructured":"Kuettel, D., & Ferrari, V. (2012). Figure-ground segmentation by transferring window masks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR37","unstructured":"Kuettel, D., Guillaumin, M. & Ferrari, V. (2012). Segmentation Propagation in ImageNet. In: Proceedings of the European Conference on Computer Vision."},{"key":"713_CR38","unstructured":"Ladicky, L., Russell, C. & Kohli, P. (2009). Associative hierarchical crfs for object class image segmentation. In: Proceedings of the International Conference on Computer Vision."},{"key":"713_CR39","unstructured":"Lampert, C., Nickisch, H. & Harmeling, S. (2009). Learning to detect unseen object classes by between-class attribute transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR40","unstructured":"Li, f., Carreira, J., & Sminchisescu, C. (2010). Object recogntion as ranking holistic figure-ground hypotheses. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR41","unstructured":"Lin, Y., Lv, F., Zhu, S., Yang, M., Cour, T., Yu, K., Cao L., & Huang, C. (2011). Large-scale image classification: fast feature extraction and SVM training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR42","unstructured":"Liu, C., Yuen, J., & Torralba, A. (2009). Nonparametric scene parsing: Label transfer via dense scene alignment. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR43","unstructured":"Malisiewicz, T., Gupta, A., & Efros, A.A. (2011). Ensemble of exemplar-svms for object detection and beyond. In: Proceedings of the International Conference on Computer Vision."},{"key":"713_CR44","unstructured":"Mukherjee, L., Singh, V., Xu, J., & Collins, M.D. (2012). Analyzing the subspace structure of related images: Concurrent segmentation of image sets. In: Proceedings of the European Conference on Computer Vision."},{"key":"713_CR45","unstructured":"Norouzi, M., Punjani, A., & Fleet, D.J. (2012). Fast search in hamming space with multi-index hashing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"issue":"3","key":"713_CR46","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":"713_CR47","unstructured":"Ott, P., & Everingham, M. (2011). Shared parts for deformable part-based models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR48","unstructured":"Quattoni, A., Collins, M., & Darrell, T. (2008). Transfer learning for image classification with sparse prototype representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR49","unstructured":"Rohrbach, M., Stark, M., Szarvas, G., Gurevych, I., & Schiele, B. (2010). What helps where and why? Semantic relatedness for knowledge transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR50","unstructured":"Rosenfeld, A., & Weinshall, D. (2011). Extracting foreground masks towards object recognition. In: Proceedings of the International Conference on Computer Vision."},{"key":"713_CR51","unstructured":"Rother, C., Kolmogorov, V., & Blake, A. (2004). Grabcut: Interactive foreground extraction using iterated graph cuts. In: Proceedings of the ACM SIGGRAPH Conference on Computer Graphics."},{"key":"713_CR52","unstructured":"Rother, C., Kolmogorov, V., Minka, T., & Blake, A. (2006). Cosegmentation of image pairs by histogram matching - incorporating a global constraint into MRFs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR53","unstructured":"Russel, B., Torralba, A., Liu, C., & Fergus, R. (2007). Object recognition by scene alignment. In: Advances in Neural Information Processing Systems."},{"key":"713_CR54","unstructured":"Salakhutdinov, R., Torralba, A., & Tenenbaum, J. (2011). Learning to share visual appearance for multiclass object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR55","unstructured":"Van de Sande, K., J.R.R., U., Gevers, T., & Smeulders, A. (2011). Segmentation as selective search for object recognition. In: Proceedings of the International Conference on Computer Vision."},{"key":"713_CR56","unstructured":"Schoenemann, T., & Cremers, D. (2007). Introducing curvature into globally optimal image segmentation: Minimum ratio cycles on product graphs. In: Proceedings of the 11th International Conference on Computer Vision. Rio de Janeiro, Brazil."},{"key":"713_CR57","unstructured":"Shotton, J., Blake, A., & Cipolla, R. (2005). Contour-based learning for object detection. In: Proceedings of the International Conference on Computer Vision."},{"key":"713_CR58","unstructured":"Shotton, J., Winn, J., Rother, C., & Criminisi, A. (2006). TextonBoost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation. In: Proceedings of the European Conference on Computer Vision."},{"key":"713_CR59","unstructured":"Stark, M., Goesele, M., & Schiele, B. (2009). A shape-based object class model for knowledge transfer. In: Proceedings of the International Conference on Computer Vision."},{"key":"713_CR60","unstructured":"Szummer, M., Kohli, P., & Hoiem, D. (2008). Learning CRFs using graph cuts. In: Proceedings of the European Conference on Computer Vision."},{"key":"713_CR61","unstructured":"Tighe, J., & Lazebnik, S. (2010). Superparsing: Scalable nonparametric image parsing with superpixels. In: Proceedings of the European Conference on Computer Vision."},{"key":"713_CR62","unstructured":"Tommasi, T., Orabona, F., & Caputo, B. (2010). Safety in numbers: Learning categories from few examples with multi model knowledge transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR63","unstructured":"Torralba, A., Fergus, R., & Weiss, Y. (2008). Small codes and large image databases for recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR64","first-page":"1453","volume":"6","author":"I Tsochantaridis","year":"2005","unstructured":"Tsochantaridis, I., Joachims, T., Hofmann, T., & Altun, Y. (2005). Large margin methods for structured and interdependent output variables. Journal of Machine Learning Research, 6, 1453\u20131484.","journal-title":"Journal of Machine Learning Research"},{"issue":"2","key":"713_CR65","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., & Zhu, S. (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":"713_CR66","unstructured":"Veksler, O., Boykov, Y., & Mehrani, P. (2010). Superpixels and supervoxels in an energy optimization framework. In: Proceedings of the European Conference on Computer Vision (pp. 211\u2013224)."},{"issue":"3","key":"713_CR67","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1007\/s10618-005-0033-3","volume":"13","author":"J Verbeek","year":"2006","unstructured":"Verbeek, J., Nunnink, J., & Vlassis, N. (2006). Accelerated EM-based clustering of large data sets. Data Mining and Knowledge Discovery, 13(3), 291\u2013307.","journal-title":"Data Mining and Knowledge Discovery"},{"key":"713_CR68","unstructured":"Verbeek, J., & Triggs, B. (2007). Region classification with Markov field aspect models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"713_CR69","unstructured":"Vicente, S., Kolmogorov, V., & Rother, C. (2008). Graph cut based image segmentation with connectivity priors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, Alaska."},{"key":"713_CR70","unstructured":"Vicente, S., Rother, C., & Kolmogorov, V. (2011). Object cosegmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2217\u20132224)."},{"key":"713_CR71","unstructured":"Wang, J., & Cohen, M. (2005). An iterative optimization approach for unified image segmentation and matting. In: Proceedings of the 10th International Conference on Computer Vision. Beijing, China."},{"key":"713_CR72","unstructured":"Winn, J., & Jojic, N. (2005). LOCUS: Learning object classes with unsupervised segmentation. In: Proceedings of the International Conference on Computer Vision."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-014-0713-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-014-0713-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-014-0713-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T08:19:14Z","timestamp":1559377154000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-014-0713-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4,7]]},"references-count":72,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,12]]}},"alternative-id":["713"],"URL":"https:\/\/doi.org\/10.1007\/s11263-014-0713-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,4,7]]}}}