Learning hierarchical models of scenes, objects, and parts

Learning hierarchical models of scenes, objects, and parts (2005)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Erik B. Sudderth , Antonio Torralba , William T. Freeman , Alan S. Willsky

Venue:	In IEEE Intl. Conf. on Computer Vision
Citations:	104 - 11 self

BibTeX

@INPROCEEDINGS{Sudderth05learninghierarchical,
    author = {Erik B. Sudderth and Antonio Torralba and William T. Freeman and Alan S. Willsky},
    title = {Learning hierarchical models of scenes, objects, and parts},
    booktitle = {In IEEE Intl. Conf. on Computer Vision},
    year = {2005},
    pages = {1331--1338}
}

Years of Citing Articles

Bookmark

OpenURL

Abstract

We describe a hierarchical probabilistic model for the detection and recognition of objects in cluttered, natural scenes. The model is based on a set of parts which describe the expected appearance and position, in an object centered coordinate frame, of features detected by a low-level interest operator. Each object category then has its own distribution over these parts, which are shared between objects. We learn the parameters of this model via a Gibbs sampler which uses the graphical model’s structure to analytically average over many parameters. Applied to a database of images of isolated objects, the sharing of parts among objects improves detection accuracy when few training examples are available. We also extend this hierarchical framework to scenes containing multiple objects. 1.

Citations

3104	Distinctive image features from scale invariant keypoints - Lowe
1370	Latent Dirichlet allocation - Blei, Ng, et al.
887	D: Bayesian Data Analysis - Gelman, Carlin, et al. - 1995
612	A view of the EM algorithm that justifies incremental, sparse, and other variants - Neal, Hinton - 1998
469	editor. Learning in Graphical Models - Jordan - 1998
372	Finding scientific topics - Griffiths, Steyvers - 2004
322	Bayesian hierarchical model for learning natural scene categories - Fei-Fei, Perona, et al.
305	P.: 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 - Fei-Fei, Fergus, et al. - 2004
202	The representation and matching of pictorial structures - Fischler, Elschlager - 1973
186	Sharing features: efficient boosting procedures for multiclass object detection - Torralba, Murphy, et al. - 2004
153	The author-topic model for authors and documents - Rosen-Zvi, Griffiths, et al.
137	A Bayesian approach to unsupervised one-shot learning of object categories - Fei-Fei, Fergus, et al.
125	Visual features of intermediate complexity and their use in classification - Ullman, Vidal-Naquet, et al.
118	Contextual models for object detection using boosted random fields. NIPS - Torralba, Murphy, et al. - 2004
113	S.: Image parsing: Unifying segmentation, detection, and recognition - Tu, Chen, et al. - 2005
96	Discovering object categories in image collections - Sivic, Russell, et al. - 2005
51	Multidimensional scaling, tree-fitting, and clustering - Shepard - 1980
25	Mutual Boosting for Contextual Inference - Fink, Perona - 2012
12	et al., “Matching words and pictures - Barnard - 2003
11	et al., “Visual categorization with bags of keypoints - Csurka
8	Object class recognition with many local features - Helmer, Lowe - 2004