Search For:

Displaying 1-31 out of 31 total
Social behavior recognition in continuous video
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By X. P. Burgos-Artizzu,P. Dollar, Dayu Lin,D. J. Anderson,P. Perona
Issue Date:June 2012
pp. 1322-1329
We present a novel method for analyzing social behavior. Continuous videos are segmented into action `bouts' by building a temporal context model that combines features from spatio-temporal energy and agent trajectories. The method is tested on an unpreced...
 
Learning Object Categories from Google?s Image Search
Found in: Computer Vision, IEEE International Conference on
By R. Fergus, L. Fei-Fei, P. Perona, A. Zisserman
Issue Date:October 2005
pp. 1816-1823
Current approaches to object category recognition require datasets of training images to be manually prepared, with varying degrees of supervision. We present an approach that can learn an object category from just its name, by utilizing the raw output of ...
 
A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By R. Fergus, P. Perona, A. Zisserman
Issue Date:June 2005
pp. 380-387
<p>We present a
 
Object Class Recognition by Unsupervised Scale-Invariant Learning
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By R. Fergus, P. Perona, A. Zisserman
Issue Date:June 2003
pp. 264
We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of t...
 
A computational model for motion detection and direction discrimination in humans
Found in: Human Motion, Workshop on
By Yang Song, P. Perona
Issue Date:December 2000
pp. 11
Seeing biological motion is very important for both humans and computers. Psychophysics experiments show that the ability of our visual system for biological motion detection and direction discrimination is different from that for simple translation. The e...
 
Scale-Space and Edge Detection Using Anisotropic Diffusion
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By P. Perona, J. Malik
Issue Date:July 1990
pp. 629-639
<p>A new definition of scale-space is suggested, and a class of algorithms used to realize a diffusion process is introduced. The diffusion coefficient is chosen to vary spatially in such a way as to encourage intraregion smoothing rather than interr...
 
Detecting Motion through Dynamic Refraction
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By M. Alterman,Y. Y. Schechner,P. Perona,J. Shamir
Issue Date:January 2013
pp. 245-251
Refraction causes random dynamic distortions in atmospheric turbulence and in views across a water interface. The latter scenario is experienced by submerged animals seeking to detect prey or avoid predators, which may be airborne or on land. Man encounter...
 
Carving from Ray-Tracing Constraints: IRT-Carving
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By M. Andreetto, S. Savarese, P. Perona
Issue Date:June 2006
pp. 49-56
We present a new algorithm for improving an available (conservative) estimate of the shape of an object using constraints from ray-tracing. In particular, we exploit incoherences between the lit portions of the object - detected on a set of acquired images...
 
Dynamic rigid motion estimation from weak perspective
Found in: Computer Vision, IEEE International Conference on
By S. Soatto, P. Perona
Issue Date:June 1995
pp. 321
No summary available.
 
Finding faces in cluttered scenes using random labeled graph matching
Found in: Computer Vision, IEEE International Conference on
By T.K. Leung, M.C. Burl, P. Perona
Issue Date:June 1995
pp. 637
An algorithm for locating quasi-frontal views of human faces in cluttered scenes is presented. The algorithm works by coupling a set of local feature detectors with a statistical model of the mutual distances between facial features it is invariant with re...
 
Pedestrian Detection: An Evaluation of the State of the Art
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By P. Dollar,C. Wojek,B. Schiele,P. Perona
Issue Date:April 2012
pp. 743-761
Pedestrian detection is a key problem in computer vision, with several applications that have the potential to positively impact quality of life. In recent years, the number of approaches to detecting pedestrians in monocular images has grown steadily. How...
 
Pedestrian detection: A benchmark
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By P. Dollar, C. Wojek, B. Schiele, P. Perona
Issue Date:June 2009
pp. 304-311
Pedestrian detection is a key problem in computer vision, with several applications including robotics, surveillance and automotive safety. Much of the progress of the past few years has been driven by the availability of challenging public datasets. To co...
 
Reach Out and Touch Space (Motion Learning)
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By L. Goncalves, E. di Bernardo, P. Perona
Issue Date:April 1998
pp. 234
No summary available.
 
Reducing
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By S. Soatto, P. Perona
Issue Date:June 1996
pp. 825
The literature on recursive estimation of structure and motion from monocular image sequences comprises a large number of different models and estimation techniques. We propose a framework that allows us to derive and compare all models by following the id...
 
Unsupervised Learning of Categorical Segments in Image Collections
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By M. Andreetto,L. Zelnik-Manor,P. Perona
Issue Date:September 2012
pp. 1842-1855
Which one comes first: segmentation or recognition? We propose a unified framework for carrying out the two simultaneously and without supervision. The framework combines a flexible probabilistic model, for representing the shape and appearance of each seg...
 
Towards Automatic Discovery of Object Categories
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By M. Weber, M. Welling, P. Perona
Issue Date:June 2000
pp. 2101
We propose a method to learn heterogeneous models of object classes for visual recognition. The training images contain a preponderance of clutter and learning is unsupervised. Our models represent objects as probabilistic constellations of rigid parts (fe...
 
Recognition of Planar Object Classes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By M.C. Burl, P. Perona
Issue Date:June 1996
pp. 223
We present a new framework for recognizing planar object classes, which is based on local feature detectors and a probabilistic model of the spatial arrangement of the features. The allowed object deformations are represented through shape statistics, whic...
 
Using Hierarchical Shape Models to Spot Keywords in Cursive Handwriting Data
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By M.C. Burl, P. Perona
Issue Date:June 1998
pp. 535
No summary available.
 
Motion from fixation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By S. Soatto, P. Perona
Issue Date:June 1996
pp. 817
We study the problem of estimating rigid motion from a sequence of monocular perspective images obtained by navigating around an object while fixating a particular feature point. We cast the problem in the framework of
 
Pyramidal implementation of deformable kernels
Found in: Image Processing, International Conference on
By R. Manduchi, P. Perona
Issue Date:October 1995
pp. 378
In computer vision and increasingly, in rendering and image processing, it is useful to filter images with continuous rotated and scaled families of filters. For practical implementations, one can think of using a discrete family of filters, and then to in...
 
Viewpoint-Invariant Learning and Detection of Human Heads
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By M. Weber, W. Einhäuser, M. Welling, P. Perona
Issue Date:March 2000
pp. 20
We present a method to learn models of human heads for the purpose of detection from different viewing angles. We focus on a model where objects are represented as constellations of rigid features (parts). Variability is represented by a joint probability ...
 
Real-Time 2-D Feature Detection on a Reconfigurable Computer
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By A. Benedetti, P. Perona
Issue Date:June 1998
pp. 586
No summary available.
 
Orientation diffusions
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By P. Perona
Issue Date:June 1997
pp. 710
Diffusions provide a convenient way of smoothing noisy brightness images, of analyzing images at multiple scales, and of enhancing discontinuities. Some quantities of interest in computer vision are defined on curved manifolds; typical examples are orienta...
 
Monocular Tracking of the Human Arm in 3D: Real-Time Implementation and Experiments
Found in: Pattern Recognition, International Conference on
By E. Di Bernardo, L. Goncalves, P. Perona
Issue Date:August 1996
pp. 622
No summary available.
 
Visual motion estimation from point features: unified view
Found in: Image Processing, International Conference on
By S. Soatto, P. Perona
Issue Date:October 1995
pp. 3021
All methods for recursive estimation of 3-D motion from sequences of perspective images of point-features may be cast within a common framework. The unifying concept is the decoupling of the states of the dynamic observer that estimates motion and structur...
 
Visual navigation using a single camera
Found in: Computer Vision, IEEE International Conference on
By J.-Y. Bouguet, P. Perona
Issue Date:June 1995
pp. 645
We assess the usefulness of monocular recursive motion estimation techniques for vehicle navigation in the absence of a model for the environment. For this purpose we extend a recently proposed recursive motion estimator, the Essential filter, to handle sc...
 
Towards automated large scale discovery of image families
Found in: Computer Vision and Pattern Recognition Workshop
By M. Aly, P. Welinder, M. Munich, P. Perona
Issue Date:June 2009
pp. 9-16
Gathering large collections of images is quite easy nowadays with the advent of image sharing Web sites, such as flickr.com. However, such collections inevitably contain duplicates and highly similar images, what we refer to as image families. Automatic di...
 
Probablistic Affine Invariants for Recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By T.K. Leung, M.C. Burl, P. Perona
Issue Date:June 1998
pp. 678
No summary available.
 
Scene Segmentation from 3D Motion
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By X. Feng, P. Perona
Issue Date:June 1998
pp. 225
No summary available.
 
Monocular tracking of the human arm in 3D
Found in: Computer Vision, IEEE International Conference on
By L. Goncalves, E. Di Bernardo, E. Ursella, P. Perona
Issue Date:June 1995
pp. 764
We address the problem of estimating the position and motion of a human arm in 3D without any constraints on its behavior and without the use of special markers. We model the arm as two truncated right-circular cones connected with spherical joints. We pro...
 
Visual Input for Pen-Based Computers
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By M.E. Munich, P. Perona
Issue Date:March 2002
pp. 313-328
<p>The design and implementation of a camera-based, human-computer interface for acquisition of handwriting is presented. The camera focuses on a standard sheet of paper and images a common pen; the trajectory of the tip of the pen is tracked and the...
 
 1