Search For:

Displaying 1-50 out of 53 total
CompactKdt: Compact signatures for accurate large scale object recognition
Found in: Applications of Computer Vision, IEEE Workshop on
By Mohamed Aly,Mario Munich,Pietro Perona
Issue Date:January 2012
pp. 505-512
We present a novel algorithm, Compact Kd-Trees (CompactKdt), that achieves state-of-the-art performance in searching large scale object image collections. The algorithm uses an order of magnitude less storage and computations by making use of both the full...
 
Robust Face Landmark Estimation under Occlusion
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Xavier P. Burgos-Artizzu,Pietro Perona,Piotr Dollar
Issue Date:December 2013
pp. 1513-1520
Human faces captured in real-world conditions present large variations in shape and occlusions due to differences in pose, expression, use of accessories such as sunglasses and hats and interactions with objects (e.g. food). Current face landmark estimatio...
 
Object detection and segmentation from joint embedding of parts and pixels
Found in: Computer Vision, IEEE International Conference on
By Michael Maire,Stella X. Yu,Pietro Perona
Issue Date:November 2011
pp. 2142-2149
We present a new framework in which image segmentation, figure/ground organization, and object detection all appear as the result of solving a single grouping problem. This framework serves as a perceptual organization stage that integrates information fro...
 
Multiclass recognition and part localization with humans in the loop
Found in: Computer Vision, IEEE International Conference on
By Catherine Wah,Steve Branson,Pietro Perona,Serge Belongie
Issue Date:November 2011
pp. 2524-2531
We propose a visual recognition system that is designed for fine-grained visual categorization. The system is composed of a machine and a human user. The user, who is unable to carry out the recognition task by himself, is interactively asked to provide tw...
 
Strong supervision from weak annotation: Interactive training of deformable part models
Found in: Computer Vision, IEEE International Conference on
By Steve Branson,Pietro Perona,Serge Belongie
Issue Date:November 2011
pp. 1832-1839
We propose a framework for large scale learning and annotation of structured models. The system interleaves interactive labeling (where the current model is used to semi-automate the labeling of a new example) and online learning (where a newly labeled exa...
 
Unsupervised Organization of Image Collections: Taxonomies and Beyond
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Evgeniy Bart,Max Welling,Pietro Perona
Issue Date:November 2011
pp. 2302-2315
We introduce a nonparametric Bayesian model, called TAX, which can organize image collections into a tree-shaped taxonomy without supervision. The model is inspired by the Nested Chinese Restaurant Process (NCRP) and associates each image with a path throu...
 
Cascaded pose regression
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Piotr Dollar, Peter Welinder, Pietro Perona
Issue Date:June 2010
pp. 1078-1085
We present a fast and accurate algorithm for computing the 2D pose of objects in images called cascaded pose regression (CPR). CPR progressively refines a loosely specified initial guess, where each refinement is carried out by a different regressor. Each ...
 
Entropy-based active learning for object recognition
Found in: Computer Vision and Pattern Recognition Workshop
By Alex Holub, Pietro Perona, Michael C. Burl
Issue Date:June 2008
pp. 1-8
Most methods for learning object categories require large amounts of labeled training data. However, obtaining such data can be a difficult and time-consuming endeavor. We have developed a novel, entropy-based “active learning” approach which makes signifi...
 
Unsupervised learning of categorical segments in image collections
Found in: Computer Vision and Pattern Recognition Workshop
By Marco Andreetto, Lihi Zelnik-Manor, Pietro Perona
Issue Date:June 2008
pp. 1-8
Which one comes first: segmentation or recognition? We propose a probabilistic framework for carrying out the two simultaneously. The framework combines an LDA ‘bag of visual words’ model for recognition, and a hybrid parametric-nonparametric model for seg...
 
A walk through the web's video clips
Found in: Computer Vision and Pattern Recognition Workshop
By Sara Zanetti, Lihi Zelnik-Manor, Pietro Perona
Issue Date:June 2008
pp. 1-8
Approximately 105 video clips are posted every day on the web. The popularity of web-based video databases poses a number of challenges to machine vision scientists: how do we organize, index and search such large wealth of data? Content-based video search...
 
Unsupervised learning of visual taxonomies
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Evgeniy Bart, Ian Porteous, Pietro Perona, Max Welling
Issue Date:June 2008
pp. 1-8
As more images and categories become available, organizing them becomes crucial. We present a novel statistical method for organizing a collection of images into a tree-shaped hierarchy. The method employs a non-parametric Bayesian model and is completely ...
 
Incremental learning of nonparametric Bayesian mixture models
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ryan Gomes, Max Welling, Pietro Perona
Issue Date:June 2008
pp. 1-8
Clustering is a fundamental task in many vision applications. To date, most clustering algorithms work in a batch setting and training examples must be gathered in a large group before learning can begin. Here we explore incremental clustering, in which da...
 
Learning and using taxonomies for fast visual categorization
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Gregory Griffin, Pietro Perona
Issue Date:June 2008
pp. 1-8
The computational complexity of current visual categorization algorithms scales linearly at best with the number of categories. The goal of classifying simultaneously N<inf>cat</inf> = 10<sup>4</sup> − 10<sup>5</sup> vis...
 
Non-Parametric Probabilistic Image Segmentation
Found in: Computer Vision, IEEE International Conference on
By Marco Andreetto, Lihi Zelnik-Manor, Pietro Perona
Issue Date:October 2007
pp. 1-8
We propose a simple probabilistic generative model for image segmentation. Like other probabilistic algorithms (such as EM on a Mixture of Gaussians) the proposed model is principled, provides both hard and probabilistic cluster assignments, as well as the...
 
On Constructing Facial Similarity Maps
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Alex Holub, Yun-hsueh Liu, Pietro Perona
Issue Date:June 2007
pp. 1-8
Automatically determining facial similarity is a difficult and open question in computer vision. The problem is complicated both because it is unclear what facial features humans use to determine facial similarity and because facial similarity is subjectiv...
 
Fast Terrain Classification Using Variable-Length Representation for Autonomous Navigation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Anelia Angelova, Larry Matthies, Daniel Helmick, Pietro Perona
Issue Date:June 2007
pp. 1-8
We propose a method for learning using a set of feature representations which retrieve different amounts of information at different costs. The goal is to create a more efficient terrain classification algorithm which can be used in real-time, onboard an a...
 
One-Shot Learning of Object Categories
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Li Fei-Fei, Rob Fergus, Pietro Perona
Issue Date:April 2006
pp. 594-611
Learning visual models of object categories notoriously requires hundreds or thousands of training examples. We show that it is possible to learn much information about a category from just one, or a handful, of images. The key insight is that, rather than...
 
Evaluation of Features Detectors and Descriptors Based on 3D Objects
Found in: Computer Vision, IEEE International Conference on
By Pierre Moreels, Pietro Perona
Issue Date:October 2005
pp. 800-807
We explore the performance of a number of popular feature detectors and descriptors in matching 3D object features across viewpoints and lighting conditions. To this end we design a method, based on intersecting epipolar constraints, for providing ground t...
 
Combining Generative Models and Fisher Kernels for Object Recognition
Found in: Computer Vision, IEEE International Conference on
By Alex D. Holub, Max Welling, Pietro Perona
Issue Date:October 2005
pp. 136-143
Learning models for detecting and classifying object categories is a challenging problem in machine vision. While discriminative approaches to learning and classification have, in principle, superior performance, generative approaches provide many useful f...
 
Squaring the Circles in Panoramas
Found in: Computer Vision, IEEE International Conference on
By Lihi Zelnik-Manor, Gabriele Peters, Pietro Perona
Issue Date:October 2005
pp. 1292-1299
Pictures taken by a rotating camera cover the viewing sphere surrounding the center of rotation. Having a set of images registered and blended on the sphere what is left to be done, in order to obtain a flat panorama, is projecting the spherical image onto...
 
A Discriminative Framework for Modelling Object Classes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Alex Holub, Pietro Perona
Issue Date:June 2005
pp. 664-671
Here we explore a discriminative learning method on underlying generative models for the purpose of discriminating between object categories. Visual recognition algorithms learn models from a set of training examples. Generative models learn their represen...
 
A Bayesian Hierarchical Model for Learning Natural Scene Categories
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Fei-Fei Li, Pietro Perona
Issue Date:June 2005
pp. 524-531
We propose a novel approach to learn and recognize natural scene categories. Unlike previous work [9, 17], it does not require experts to annotate the training set. We represent the image of a scene by a collection of local regions, denoted as codewords ob...
 
Hybrid Models for Human Motion Recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Claudio Fanti, Lihi Zelnik-Manor, Pietro Perona
Issue Date:June 2005
pp. 1166-1173
<p>Probabilistic models have been previously shown to be efficient and effective for modeling and recognition of human motion. In particular we focus on methods which represent the human motion model as a triangulated graph. Previous approaches learn...
 
Pruning Training Sets for Learning of Object Categories
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Anelia Angelova, Yaser Abu-Mostafa, Pietro Perona
Issue Date:June 2005
pp. 494-501
Training datasets for learning of object categories are often contaminated or imperfect. We explore an approach to automatically identify examples that are noisy or troublesome for learning and exclude them from the training set. The problem is relevant to...
 
Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories
Found in: Computer Vision and Pattern Recognition Workshop
By Li Fei-Fei, Rob Fergus, Pietro Perona
Issue Date:July 2004
pp. 178
Current computational approaches to learning visual object categories require thousands of training images, are slow, cannot learn in an incremental manner and cannot incorporate prior information into the learning process. In addition, no algorithm presen...
 
Is Bottom-Up Attention Useful for Object Recognition?
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ueli Rutishauser, Dirk Walther, Christof Koch, Pietro Perona
Issue Date:July 2004
pp. 37-44
A key problem in learning multiple objects from unlabeled images is that it is a priori impossible to tell which part of the image corresponds to each individual object, and which part is irrelevant clutter which is not associated to the objects. We invest...
 
A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories
Found in: Computer Vision, IEEE International Conference on
By Li Fei-Fei, Rob Fergus, Pietro Perona
Issue Date:October 2003
pp. 1134
Learning visual models of object categories notoriously requires thousands of training examples; this is due to the diversity and richness of object appearance which requires models containing hundreds of parameters. We present a method for learning object...
 
Unsupervised Learning of Human Motion
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yang Song, Luis Goncalves, Pietro Perona
Issue Date:July 2003
pp. 814-827
<p><b>Abstract</b>—An unsupervised learning algorithm that can obtain a probabilistic model of an object composed of a collection of parts (a moving human body in our examples) automatically from unlabeled training data is presented. The ...
 
Visual Identification by Signature Tracking
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Mario E. Munich, Pietro Perona
Issue Date:February 2003
pp. 200-217
<p><b>Abstract</b>—We propose a new camera-based biometric: visual signature identification. We discuss the importance of the parameterization of the signatures in order to achieve good classification results, independently of variations ...
 
Second Order Local Analysis for 3D Reconstruction of Specular Surfaces
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Silvio Savarese, Min Chen, Pietro Perona
Issue Date:June 2002
pp. 356
We analyze the problem of recovering the shape of a mirror surface. A calibrated scene composed of lines passing through a point is assumed. The lines are reflected by the mirror surface onto the image plane of a calibrated camera, where the intersection, ...
 
Implementation of a Shadow Carving System for Shape Capture
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Silvio Savarese, Holly Rushmeier, Fausto Bernardini, Pietro Perona
Issue Date:June 2002
pp. 12
We present a new technique for estimating the 3D shape of an object that combines previous ideas from shape from silhouettes and shape from shadows. We begin with a set-up for robustly extracting object silhouettes by casting a shadow of the object with a ...
 
Learning Probabilistic Structure for Human Motion Detection
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yang Song, Luis Goncalves, Pietro Perona
Issue Date:December 2001
pp. 771
Decomposable triangulated graphs have been shown to be efficient and effective for modeling the probabilistic spatio-temporal structure of brief stretches of human motion. In previous work such model structure was hand-crafted by expert human observers and...
 
Local Analysis for 3D Reconstruction of Specular Surfaces
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Silvio Savarese, Pietro Perona
Issue Date:December 2001
pp. 738
We explore the geometry linking the shape of a curved mirror surface to the distortions it produces on a scene it reflects. Our analysis is local and differential. We assume a simple calibrated scene composed of lines passing through a point. We demonstrat...
 
Shadow Carving
Found in: Computer Vision, IEEE International Conference on
By Silvio Savarese, Holly Rushmeier, Fausto Bernardini, Pietro Perona
Issue Date:July 2001
pp. 190
The shape of an object may be estimated by observing the shadows on its surface. We present a method that is robust with respect to a conservative classification of shadow regions. Assuming that a conservative estimate of the object shape is available, we ...
 
Towards Detection of Human Motion
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yang Song, Xiaolin Feng, Pietro Perona
Issue Date:June 2000
pp. 1810
Detecting humans in images is a useful application of computer vision. Loose and textured clothing, occlusion and scene clutter make it a difficult problem because bottom-up segmentation and grouping do not always work. We address the problem of detecting ...
 
Monocular Perception of Biological Motion ? Detection and Labeling
Found in: Computer Vision, IEEE International Conference on
By Yang Song, Luis Goncalves, Enrico Di Bernardo, Pietro Perona
Issue Date:September 1999
pp. 805
Computer perception of biological motion is key to developing convenient and powerful human-computer inter-faces. Successful body tracking algorithms have been developed; however, initialization is done by hand.We propose a method for detecting a moving hu...
 
Continuous Dynamic Time Warping for Translation-Invariant Curve Alignment with Applications to Signature Verification
Found in: Computer Vision, IEEE International Conference on
By Mario E. Munich, Pietro Perona
Issue Date:September 1999
pp. 108
The problem of establishing correspondence and measuring the similarity of a pair of planar curves arises in many applications in computer vision and pattern recognition. This paper presents a new method for comparing planar curves and for performing match...
 
What Do Planar Shadows Tell About Scene Geometry?
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jean-Yves Bouguet, Markus Weber, Pietro Perona
Issue Date:June 1999
pp. 1514
A method for reconstructing 3D scene geometry from a set of projected shadows is presented. It is composed of two stages. First, the scene geometry is retrieved up to three scalar unknowns using only the information contained in the observed shadow edges o...
 
Correction to:
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Stefano Soatto, Pietro Perona
Issue Date:October 1998
pp. 1117
No summary available.
 
Reducing
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Stefano Soatto, Pietro Perona
Issue Date:September 1998
pp. 943-960
<p><b>Abstract</b>—A number of methods have been proposed in the literature for estimating scene-structure and ego-motion from a sequence of images using dynamical models. Despite the fact that all methods may be derived from a
 
Reducing
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Stefano Soatto, Pietro Perona
Issue Date:September 1998
pp. 933-942
<p><b>Abstract</b>—The literature on recursive estimation of structure and motion from monocular image sequences comprises a large number of apparently unrelated models and estimation techniques. We propose a framework that allows us to d...
 
Scale-Space Properties of Quadratic Feature Detectors
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Paul Kube, Pietro Perona
Issue Date:October 1996
pp. 987-999
<p><b>Abstract</b>—Feature detectors using a quadratic nonlinearity in the filtering stage are known to have some advantages over linear detectors; here, we consider their scale-space properties. In particular, we investigate whether, lik...
 
Deformable Kernels for Early Vision
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Pietro Perona
Issue Date:May 1995
pp. 488-499
<p><it>Abstract</it>—Early vision algorithms often have a first stage of linear-filtering that ’extracts’ from the image information at multiple scales of resolution and multiple orientations. A common difficulty in the design and impleme...
 
Fast Feature Pyramids for Object Detection
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Piotr Dollar,Ron Appel,Serge Belongie,Pietro Perona
Issue Date:August 2014
pp. 1532-1545
Multi-resolution image features may be approximated via extrapolation from nearby scales, rather than being computed explicitly. This fundamental insight allows us to design object detection algorithms that are as accurate, and considerably faster, than th...
 
A Lazy Man's Approach to Benchmarking: Semisupervised Classifier Evaluation and Recalibration
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Peter Welinder,Max Welling,Pietro Perona
Issue Date:June 2013
pp. 3262-3269
How many labeled examples are needed to estimate a classifier's performance on a new dataset? We study the case where data is plentiful, but labels are expensive. We show that by making a few reasonable assumptions on the structure of the data, it is possi...
 
Human Action Recognition By Sequence of Movelet Codewords
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Xiaolin Feng, Pietro Perona
Issue Date:June 2002
pp. 717
An algorithm for the recognition of human actions in image sequences is presented. The algorithm consists of 3 stages: background subtraction, body pose classification, and action recognition. A pose is represented in space-time {we call it `movelet'. A mo...
 
Visual Signature Verification Using Affine Arc-Length
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Mario E. Munich, Pietro Perona
Issue Date:June 1999
pp. 2180
Signatures can be acquired with a camera-based system with enough resolution to perform verification. This paper presents the performance of a visual-acquisition signature verification system, emphasizing on the importance of the parameterization of the si...
 
3D Photography on Your Desk
Found in: Computer Vision, IEEE International Conference on
By Jean-Yves Bouguet, Pietro Perona
Issue Date:January 1998
pp. 43
A simple and inexpenssive approach for extracting the three-dimentional shape of objects is presented. It is based on 'weak structured lighting'; it differs from other conventional structured lighting approaches in that it requires very little hardware bes...
 
Progress in visual categorization: technical perspective
Found in: Communications of the ACM
By Pietro Perona
Issue Date:September 2013
pp. 96-96
Last month (Aug. 2013) you needed to win several chess games in a row, alternately playing white and black, and had to decide with which color you should start.
     
Seeing the trees, the forest, and much more
Found in: Communications of the ACM
By Pietro Perona
Issue Date:March 2010
pp. 106-106
Computer scientists have made great strides in how decision-making mechanisms are used.
     
 1  2 Next >>