Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes

Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes (2003)

Cached

Download Links

by Kevin Murphy , Antonio Torralba , William T. Freeman

Citations:

BibTeX

@MISC{Murphy03usingthe,
    author = {Kevin Murphy and Antonio Torralba and William T. Freeman},
    title = {Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes},
    year = {2003}
}

Years of Citing Articles

Bookmark

OpenURL

Abstract

Standard approaches to object detection focus on local patches of the image, and try to classify them as background or not. We propose to use the scene context (image as a whole) as an extra source of (global) information, to help resolve local ambiguities. We present a conditional random field for jointly solving the tasks of object detection and scene classification.

Citations

2093	Conditional random fields: Probabilistic models for segmenting and labeling sequence data - Lafferty, McCallum, et al. - 2001
1791	Rapid object detection using a boosted cascade of simple features - Viola, Jones - 2001
1108	R.: Additive logistic regression: A statistical view of boosting. The Annals of Statistics 38 - Friedman, Hastie, et al. - 2000
786	Object class recognition by unsupervised scale-invariant learning - Fergus, Perona, et al. - 2003
643	Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods:advances in large margin classifiers - Platt - 1999
562	Relations between the Statistics of Natural Images and the Response Properties of Cortical Cells - Field - 1987
496	Greedy function approximation: A gradient boosting machine - Friedman - 2001
442	BoosTexter: a boosting-based system for text categorization - Schapire, Singer - 2000
399	Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary - Duygulu, Barnard, et al. - 2002
293	The boosting approach to machine learning: an overview - Schapire - 2002
231	Learning a sparse representation for object detection - Agarwal, Roth - 2002
212	Context-based vision system for place and object recognition - Torralba, Murphy, et al. - 2003
200	A trainable system for object detection - Papageorgiou, Poggio
176	Contextual Priming for Object Detection - Torralba - 2003
167	Discriminative random fields: a discriminative framework for contextual interaction in classification - Kumar, Hebert - 2003
116	Empirical analysis of detection cascades of boosted classi ers for rapid object detection - Lienhart, Kuranov, et al. - 2003
68	Probabilistic spatial context models for scene content understanding - Singhal, Luo, et al. - 2003
68	Context-based vision: recognizing objects using information from both 2D and 3D - Start, Fischler - 1991
57	On the semantics of a glance at a scene - Biederman - 1981
21	Decision making in context - Haralick - 1983
14	Detecting faces in impoverished images - Torralba - 2001
13	before trees: The precedence of global features in visual perception - Forest - 1977
8	Multi-label semantic scene classification - Boutell, Luo - 2004
5	Mutual boosting for contextual influence - Fink, Perona - 2003
4	Robust real-time object detection, International Journal of Computer Vision (2004) 137–154. Please cite this article in press as: N.A. Thacker et al., Performance characterization in computer vision: A guide ..., Comput. Vis. Image Understand - Viola, Jones - 2007