1
Multiscale fields of patterns
Pedro F. Felzenszwalb,
John G. Oberlin
December 2014
NIPS'14: Proceedings of the 27th International Conference on Neural Information Processing Systems
Publisher: MIT Press
Bibliometrics:
Citation Count: 1
Downloads (6 Weeks): 0, Downloads (12 Months): 0, Downloads (Overall): 0
Full text available:
PDF
We describe a framework for defining high-order image models that can be used in a variety of applications. The approach involves modeling local patterns in a multiscale representation of an image. Local properties of a coarsened image reflect non-local properties of the original image. In the case of binary images ...
2
TPAMI CVPR Special Section
Pedro F. Felzenszwalb,
David A. Forsyth,
Pascal Fua,
Terrance E. Boult
December 2013
IEEE Transactions on Pattern Analysis and Machine Intelligence: Volume 35 Issue 12, December 2013
Publisher: IEEE Computer Society
The articles in this special issue include papers from the CVPR'11 conference which was held in Colorado Spring, CO, June 2011.
3
Pedro Felzenszwalb,
Ross Girshick,
David McAllester,
Deva Ramanan
September 2013
Communications of the ACM: Volume 56 Issue 9, September 2013
Publisher: ACM
Bibliometrics:
Citation Count: 2
Downloads (6 Weeks): 18, Downloads (12 Months): 179, Downloads (Overall): 1,936
Full text available:
Html
PDF
We describe a state-of-the-art system for finding objects in cluttered images. Our system is based on deformable models that represent objects using local part templates and geometric constraints on the locations of parts. We reduce object detection to classification with latent variables. The latent variables introduce invariances that make it ...
4
Sparselet models for efficient multiclass object detection
Hyun Oh Song,
Stefan Zickler,
Tim Althoff,
Ross Girshick,
Mario Fritz,
Christopher Geyer,
Pedro Felzenszwalb,
Trevor Darrell
October 2012
ECCV'12: Proceedings of the 12th European conference on Computer Vision - Volume Part II
Publisher: Springer-Verlag
We develop an intermediate representation for deformable part models and show that this representation has favorable performance characteristics for multi-class problems when the number of classes is high. Our model uses sparse coding of part filters to represent each filter as a sparse linear combination of shared dictionary elements. This ...
Keywords:
object detection, deformable part models, sparse coding
5
Sparselet Models for Efficient Multiclass Object Detection
Hyun Oh Song,
Stefan Zickler,
Tim Althoff,
Ross Girshick,
Mario Fritz,
Christopher Geyer,
Pedro Felzenszwalb,
Trevor Darrell
October 2012
Proceedings, Part II, of the 12th European Conference on Computer Vision --- ECCV 2012 - Volume 7573
Publisher: Springer-Verlag New York, Inc.
We develop an intermediate representation for deformable part models and show that this representation has favorable performance characteristics for multi-class problems when the number of classes is high. Our model uses sparse coding of part filters to represent each filter as a sparse linear combination of shared dictionary elements. This ...
Keywords:
Sparse Coding, Deformable Part Models, Object Detection
6
Object detection with grammar models
Ross B. Girshick,
Pedro F. Felzenszwalb,
David McAllester
December 2011
NIPS'11: Proceedings of the 24th International Conference on Neural Information Processing Systems
Publisher: Curran Associates Inc.
Bibliometrics:
Citation Count: 8
Downloads (6 Weeks): 0, Downloads (12 Months): 0, Downloads (Overall): 0
Full text available:
PDF
Compositional models provide an elegant formalism for representing the visual appearance of highly variable objects. While such models are appealing from a theoretical point of view, it has been difficult to demonstrate that they lead to performance advantages on challenging datasets. Here we develop a grammar model for person detection ...
7
Fast Inference with Min-Sum Matrix Product
Pedro F. Felzenszwalb,
Julian J. McAuley
December 2011
IEEE Transactions on Pattern Analysis and Machine Intelligence: Volume 33 Issue 12, December 2011
Publisher: IEEE Computer Society
The MAP inference problem in many graphical models can be solved efficiently using a fast algorithm for computing min-sum products of n \times n matrices. The class of models in question includes cyclic and skip-chain models that arise in many applications. Although the worst-case complexity of the min-sum product operation ...
Keywords:
Graphical models, MAP inference, min-sum matrix product.
8
Dynamic Programming and Graph Algorithms in Computer Vision
Pedro F. Felzenszwalb,
Ramin Zabih
April 2011
IEEE Transactions on Pattern Analysis and Machine Intelligence: Volume 33 Issue 4, April 2011
Publisher: IEEE Computer Society
Optimization is a powerful paradigm for expressing and solving problems in a wide range of areas, and has been successfully applied to many vision problems. Discrete optimization techniques are especially interesting since, by carefully exploiting problem structure, they often provide nontrivial guarantees concerning solution quality. In this paper, we review ...
Keywords:
Combinatorial algorithms, vision and scene understanding, artificial intelligence, computing methodologies., Combinatorial algorithms, artificial intelligence, computing methodologies., vision and scene understanding
9
Object Detection with Discriminatively Trained Part-Based Models
Pedro F. Felzenszwalb,
Ross B. Girshick,
David McAllester,
Deva Ramanan
September 2010
IEEE Transactions on Pattern Analysis and Machine Intelligence: Volume 32 Issue 9, September 2010
Publisher: IEEE Computer Society
We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges. While deformable part models have become quite popular, their value had not been demonstrated on difficult ...
Keywords:
deformable models, latent SVM., Object recognition, deformable models, pictorial structures, discriminative training, latent SVM., discriminative training, Object recognition, pictorial structures
10
Discriminative latent variable models for object detection
Pedro Felzenszwalb,
Ross Girshick,
David McAllester,
Deva Ramanan
June 2010
ICML'10: Proceedings of the 27th International Conference on International Conference on Machine Learning
Publisher: Omnipress
11
Computing rank-convolutions with a mask
László Babai,
Pedro F. Felzenszwalb
December 2009
ACM Transactions on Algorithms (TALG): Volume 6 Issue 1, December 2009
Publisher: ACM
Bibliometrics:
Citation Count: 3
Downloads (6 Weeks): 2, Downloads (12 Months): 19, Downloads (Overall): 251
Full text available:
PDF
Rank-convolutions have important applications in a variety of areas such as signal processing and computer vision. We define a mask as a function taking only values zero and infinity. Rank-convolutions with masks are of special interest to image processing. We show how to compute the rank- k convolution of a ...
Keywords:
min-convolution, image processing, Signal processing
12
The generalized A* architecture
Pedro F. Felzenszwalb,
David McAllester
June 2007
Journal of Artificial Intelligence Research: Volume 29 Issue 1, May 2007
Publisher: AI Access Foundation
We consider the problem of computing a lightest derivation of a global structure using a set of weighted rules. A large variety of inference problems in AI can be formulated in this framework. We generalize A* search and heuristics derived from abstractions to a broad class of lightest derivation problems. ...
13
Efficient Belief Propagation for Early Vision
October 2006
International Journal of Computer Vision: Volume 70 Issue 1, October 2006
Publisher: Kluwer Academic Publishers
Markov random field models provide a robust and unified framework for early vision problems such as stereo and image restoration. Inference algorithms based on graph cuts and belief propagation have been found to yield accurate results, but despite recent advances are often too slow for practical use. In this paper ...
Keywords:
image restoration, stereo, Markov random fields, belief propagation, efficient algorithms
14
A Min-Cover Approach for Finding Salient Curves
Pedro Felzenszwalb,
David McAllester
June 2006
CVPRW '06: Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop
Publisher: IEEE Computer Society
We consider the problem of deriving a global interpretation of an image in terms of a small set of smooth curves. The problem is posed using a statistical model for images with multiple curves. Besides having important applications to edge detection and grouping the curve finding task is a special ...
15
Spatial Priors for Part-Based Recognition Using Statistical Models
June 2005
CVPR '05: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Publisher: IEEE Computer Society
We present a class of statistical models for part-based object recognition that are explicitly parameterized according to the degree of spatial structure they can represent. These models provide a way of relating different spatial priors that have been used for recognizing generic classes of objects, including joint Gaussian models and ...
16
Representation and Detection of Deformable Shapes
Pedro F. Felzenszwalb
February 2005
IEEE Transactions on Pattern Analysis and Machine Intelligence: Volume 27 Issue 2, February 2005
Publisher: IEEE Computer Society
We describe some techniques that can be used to represent and detect deformable shapes in images. The main difficulty with deformable template models is the very large or infinite number of possible nonrigid transformations of the templates. This makes the problem of finding an optimal match of a deformable template ...
Keywords:
deformable templates, Index Terms- Shape representation, object recognition, deformable templates, chordal graphs, dynamic programming., chordal graphs, object recognition, Index Terms- Shape representation, dynamic programming.
17
Pictorial Structures for Object Recognition
January 2005
International Journal of Computer Vision: Volume 61 Issue 1, January 2005
Publisher: Kluwer Academic Publishers
In this paper we present a computationally efficient framework for part-based modeling and recognition of objects. Our work is motivated by the pictorial structure models introduced by Fischler and Elschlager. The basic idea is to represent an object by a collection of parts arranged in a deformable configuration. The appearance ...
Keywords:
part-based object recognition, energy minimization, statistical models
18
Efficient Graph-Based Image Segmentation
September 2004
International Journal of Computer Vision: Volume 59 Issue 2, September 2004
Publisher: Kluwer Academic Publishers
This paper addresses the problem of segmenting an image into regions. We define a predicate for measuring the evidence for a boundary between two regions using a graph-based representation of the image. We then develop an efficient segmentation algorithm based on this predicate, and show that although this algorithm makes ...
Keywords:
image segmentation, graph algorithm, perceptual organization, clustering
19
Fast algorithms for large-state-space HMMs with applications to web usage analysis
December 2003
NIPS'03: Proceedings of the 16th International Conference on Neural Information Processing Systems
Publisher: MIT Press
Bibliometrics:
Citation Count: 2
Downloads (6 Weeks): 0, Downloads (12 Months): 0, Downloads (Overall): 0
Full text available:
PDF
In applying Hidden Markov Models to the analysis of massive data streams, it is often necessary to use an artificially reduced set of states; this is due in large part to the fact that the basic HMM estimation algorithms have a quadratic dependence on the size of the state set. ...
20
Representation and detection of deformable shapes
Pedro F. Felzenszwalb
June 2003
CVPR'03: Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Publisher: IEEE Computer Society
We present a new method for detecting deformable shapes in images. The main difficulty with deformable template models is the very large (or infinite) number of possible non-rigid transformations of the templates. This makes the problem of finding an optimal match of a deformable template to an image incredibly hard. ...
brown.edu
Author only
