Search For:

Displaying 1-47 out of 47 total
Region-Based Image Querying
Found in: Content-Based Access of Image and Video Libraries, IEEE Workshop on
By Chad Carson, Serge Belongie, Hayit Greenspan, Jitendra Malik
Issue Date:June 1997
pp. 42
Retrieving images from large and varied collections using image content as a key is a challenging and important problem. In this paper we present a new image representation which provides a transformation from the raw pixel data to a small set of localized...
 
Relative ranking of facial attractiveness
Found in: 2013 IEEE Workshop on Applications of Computer Vision (WACV)
By Hani Altwaijry,Serge Belongie
Issue Date:January 2013
pp. 117-124
Automatic evaluation of human facial attractiveness is a challenging problem that has received relatively little attention from the computer vision community. Previous work in this area have posed attractiveness as a classification problem. However, for ap...
 
Non-rigid surface detection for gestural interaction with applicable surfaces
Found in: Applications of Computer Vision, IEEE Workshop on
By Andrew Ziegler,Serge Belongie
Issue Date:January 2012
pp. 73-80
In this work we present a novel application of non-rigid surface detection to enable gestural interaction with applicable surfaces. This method can add interactivity to traditionally passive media such as books, newspapers, restaurant menus, or anything el...
 
Pose, illumination and expression invariant pairwise face-similarity measure via Doppelgänger list comparison
Found in: Computer Vision, IEEE International Conference on
By Florian Schroff,Tali Treibitz,David Kriegman,Serge Belongie
Issue Date:November 2011
pp. 2494-2501
Face recognition approaches have traditionally focused on direct comparisons between aligned images, e.g. using pixel values or local image features. Such comparisons become prohibitively difficult when comparing faces across extreme differences in pose, i...
 
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...
 
End-to-end scene text recognition
Found in: Computer Vision, IEEE International Conference on
By Kai Wang,Boris Babenko,Serge Belongie
Issue Date:November 2011
pp. 1457-1464
This paper focuses on the problem of word detection and recognition in natural images. The problem is significantly more challenging than reading text in scanned documents, and has only recently gained attention from the computer vision community. Sub-comp...
 
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...
 
Robust Object Tracking with Online Multiple Instance Learning
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Boris Babenko, Ming-Hsuan Yang, Serge Belongie
Issue Date:August 2011
pp. 1619-1632
In this paper, we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques called “tracking by detection” has been shown to give promising results at real-...
 
Multi-class object localization by combining local contextual interactions
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Carolina Galleguillos, Brian McFee, Serge Belongie, Gert Lanckriet
Issue Date:June 2010
pp. 113-120
Recent work in object localization has shown that the use of contextual cues can greatly improve accuracy over models that use appearance features alone. Although many of these models have successfully explored different types of contextual sources, they o...
 
Re-thinking non-rigid structure from motion
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Vincent Rabaud, Serge Belongie
Issue Date:June 2008
pp. 1-8
We present a novel approach to non-rigid structure from motion (NRSFM) from an orthographic video sequence, based on a new interpretation of the problem. Existing approaches assume the object shape space is well-modeled by a linear subspace. Our approach o...
 
Object categorization using co-occurrence, location and appearance
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Carolina Galleguillos, Andrew Rabinovich, Serge Belongie
Issue Date:June 2008
pp. 1-8
In this work we introduce a novel approach to object categorization that incorporates two types of context — co-occurrence and relative location — with local appearance-based features. Our approach, named CoLA (for Co-occurrence, Location and Appearance), ...
 
Soylent Grid: it's Made of People
Found in: Computer Vision, IEEE International Conference on
By Stephan Steinbach, Vincent Rabaud, Serge Belongie
Issue Date:October 2007
pp. 1-7
The ground truth labeling of an image dataset is a task that often requires a large amount of human time and labor. We present an infrastructure for distributed human labeling that can exploit the modularity of common vision problems involving segmentation...
 
Globally Optimal Affine and Metric Upgrades in Stratified Autocalibration
Found in: Computer Vision, IEEE International Conference on
By Manmohan Chandraker, Sameer Agarwal, David Kriegman, Serge Belongie
Issue Date:October 2007
pp. 1-8
We present a practical, stratified autocalibration algorithm with theoretical guarantees of global optimality. Given a projective reconstruction, the first stage of the algorithm upgrades it to affine by estimating the position of the plane at infinity. Th...
 
Objects in Context
Found in: Computer Vision, IEEE International Conference on
By Andrew Rabinovich, Andrea Vedaldi, Carolina Galleguillos, Eric Wiewiora, Serge Belongie
Issue Date:October 2007
pp. 1-8
In the task of visual object categorization, semantic context can play the very important role of reducing ambiguity in objects' visual appearance. In this work we propose to incorporate semantic object context as a post-processing step into any off-the-sh...
 
Task Specific Local Region Matching
Found in: Computer Vision, IEEE International Conference on
By Boris Babenko, Piotr Dollar, Serge Belongie
Issue Date:October 2007
pp. 1-8
Many problems in computer vision require the knowledge of potential point correspondences between two images. The usual approach for automatically determining correspondences begins by comparing small neighborhoods of high saliency in both images. Since sp...
 
Recognizing Groceries in situ Using in vitro Training Data
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Michele Merler, Carolina Galleguillos, Serge Belongie
Issue Date:June 2007
pp. 1-8
The problem of using pictures of objects captured under ideal imaging conditions (here referred to as in vitro) to recognize objects in natural environments (in situ) is an emerging area of interest in computer vision and pattern recognition. Examples of t...
 
Feature Mining for Image Classification
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Piotr Dollar, Zhuowen Tu, Hai Tao, Serge Belongie
Issue Date:June 2007
pp. 1-8
The efficiency and robustness of a vision system is often largely determined by the quality of the image features available to it. In data mining, one typically works with immense volumes of raw data, which demands effective algorithms to explore the data ...
 
Model Order Selection and Cue Combination for Image Segmentation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Andrew Rabinovich, Serge Belongie, Tilman Lange, Joachim M. Buhmann
Issue Date:June 2006
pp. 1130-1137
Model order selection and cue combination are both difficult open problems in the area of clustering. In this work we build upon stability-based approaches to develop a new method for automatic model order selection and cue combination with applications to...
 
Active Learning in Face Recognition: Using Tracking to Build a Face Model
Found in: Computer Vision and Pattern Recognition Workshop
By Robin Hewitt, Serge Belongie
Issue Date:June 2006
pp. 157
This paper describes a method by which a computer can autonomously acquire training data for learning to recognize a user?s face. The computer, in this method, actively seeks out opportunities to acquire informative face examples. Using the principles of c...
 
Counting Crowded Moving Objects
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Vincent Rabaud, Serge Belongie
Issue Date:June 2006
pp. 705-711
In its full generality, motion analysis of crowded objects necessitates recognition and segmentation of each moving entity. The difficulty of these tasks increases considerably with occlusions and therefore with crowding. When the objects are constrained t...
 
Supervised Learning of Edges and Object Boundaries
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Piotr Dollar, Zhuowen Tu, Serge Belongie
Issue Date:June 2006
pp. 1964-1971
Edge detection is one of the most studied problems in computer vision, yet it remains a very challenging task. It is difficult since often the decision for an edge cannot be made purely based on low level cues such as gradient, instead we need to engage al...
 
ImprovingWeb-based Image Search via Content Based Clustering
Found in: Computer Vision and Pattern Recognition Workshop
By Nadav Ben-Haim, Boris Babenko, Serge Belongie
Issue Date:June 2006
pp. 106
Current image search engines on the web rely purely on the keywords around the images and the filenames, which produces a lot of garbage in the search results. Alternatively, there exist methods for content based image retrieval that require a user to subm...
 
Efficient Shape Matching Using Shape Contexts
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Greg Mori, Serge Belongie, Jitendra Malik
Issue Date:November 2005
pp. 1832-1837
We demonstrate that shape contexts can be used to quickly prune a search for similar shapes. We present two algorithms for rapid shape retrieval: representative shape contexts, performing comparisons based on a small number of shape contexts, and shapemes,...
 
Big Little Icons
Found in: Computer Vision and Pattern Recognition Workshop
By Vincent Rabaud, Serge Belongie
Issue Date:June 2005
pp. 24
<p>Computer icons are small artificial images designed to be perceived with minimal ambiguity by the human visual system. In order to make them easier to perceive by visually impaired people, we propose a solution to the superresolution problem for c...
 
Tracking Multiple Mouse Contours (without Too Many Samples)
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Kristin Branson, Serge Belongie
Issue Date:June 2005
pp. 1039-1046
We present a particle filtering algorithm for robustly tracking the contours of multiple deformable objects through severe occlusions. Our algorithm combines a multiple blob tracker with a contour tracker in a manner that keeps the required number of sampl...
 
Spectral Grouping Using the Nyström Method
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Charless Fowlkes, Serge Belongie, Fan Chung, Jitendra Malik
Issue Date:January 2004
pp. 214-225
<p><b>Abstract</b>—Spectral graph theoretic methods have recently shown great promise for the problem of image segmentation. However, due to the computational demands of these approaches, applications to large problems such as spatiotempo...
 
What Went Where
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Josh Wills, Sameer Agarwal, Serge Belongie
Issue Date:June 2003
pp. 37
We present a novel framework for motion segmentation that combines the concepts of layer-based methods and feature-based motion estimation. We estimate the initial correspondences by comparing vectors of filter outputs at interest points, from which we com...
 
Blobworld: Image Segmentation Using Expectation-Maximization and Its Application to Image Querying
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Chad Carson, Serge Belongie, Hayit Greenspan, Jitendra Malik
Issue Date:August 2002
pp. 1026-1038
<p>Retrieving images from large and varied collections using image content as a key is a challenging and important problem. We present a new image representation that provides a transformation from the raw pixel data to a small set of image regions t...
 
Shape contexts enable efficient retrieval of similar shapes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Greg Mori, Serge Belongie, Jitendra Malik
Issue Date:December 2001
pp. 723
In this work we demonstrate that a recently introduced shape descriptor, the
 
Efficient Spatiotemporal Grouping Using the Nystr?m Method
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Charless Fowlkes, Serge Belongie, Jitendra Malik
Issue Date:December 2001
pp. 231
Spectral graph theoretic methods have recently shown great promise for the problem of image segmentation, but due to the computational demands, applications of such methods to spatiotemporal data have been slow to appear. For even a short video sequence, t...
 
Matching Shapes
Found in: Computer Vision, IEEE International Conference on
By Serge Belongie, Jitendra Malik, Jan Puzicha
Issue Date:July 2001
pp. 454
We present a novel approach to measuring similarity between shapes and exploit it for object recognition. In our framework, the measurement of similarity is preceded by (1) solving for correspondences between points on the two shapes, (2) using the corresp...
 
Model-Based Halftoning for Color Image Segmentation
Found in: Pattern Recognition, International Conference on
By Jan Puzicha, Serge Belongie
Issue Date:September 2000
pp. 3633
Grouping algorithms based on histograms over measured image features have very successfully been applied to textured image segmentation [2, 11, 6]. However, the competing goals of statistical estimation significance demanding few quantization levels versus...
 
Matching with Shape Contexts
Found in: Content-Based Access of Image and Video Libraries, IEEE Workshop on
By Serge Belongie, Jitendra Malik
Issue Date:June 2000
pp. 20
We introduce a new shape descriptor, the shape context, for measuring shape similarity and recovering point correspondences. The shape context describes the coarse arrangement of the shape with respect to a point inside or on the boundary of the shape. We ...
 
Textons, Contours and Regions: Cue Integration in Image Segmentation
Found in: Computer Vision, IEEE International Conference on
By Jitendra Malik, Serge Belongie, Jianbo Shi, Thomas Leung
Issue Date:September 1999
pp. 918
This paper makes two contributions. It provides (1) an operational definition of textons, the putative elementary units of texture perception, and (2) an algorithm for partitioning the image into disjoint regions of coherent bright-ness and texture, where ...
 
Color- and Texture-Based Image Segmentation Using EM and Its Application to Content-Based Image Retrieval
Found in: Computer Vision, IEEE International Conference on
By Serge Belongie, Chad Carson, Hayit Greenspan, Jitendra Malik
Issue Date:January 1998
pp. 675
<p>Retrieving images fromlarge and varied collections using image content as a key is a challenging and important problem. In this paper we present a new image representation which provides a transformation from the raw pixel data to a small set of i...
 
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...
 
Video text detection and recognition: Dataset and benchmark
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Phuc Xuan Nguyen,Kai Wang,Serge Belongie
Issue Date:March 2014
pp. 776-783
This paper focuses on the problem of text detection and recognition in videos. Even though text detection and recognition in images has seen much progress in recent years, relatively little work has been done to extend these solutions to the video domain. ...
   
Recognizing locations with Google Glass: A case study
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Hani Altwaijry,Mohammad Moghimi,Serge Belongie
Issue Date:March 2014
pp. 167-174
Wearable computers are rapidly gaining popularity as more people incorporate them into their everyday lives. The introduction of these devices allows for wider deployment of Computer Vision based applications. In this paper, we describe a system developed ...
   
Improving streaming video segmentation with early and mid-level visual processing
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Subarna Tripathi, Youngbae Hwang,Serge Belongie, Truong Nguyen
Issue Date:March 2014
pp. 477-484
Despite recent advances in video segmentation, many opportunities remain to improve it using a variety of low and mid-level visual cues. We propose improvements to the leading streaming graph-based hierarchical video segmentation (streamGBH) method based o...
   
Cross-View Image Geolocalization
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Tsung-Yi Lin,Serge Belongie,James Hays
Issue Date:June 2013
pp. 891-898
The recent availability of large amounts of geotagged imagery has inspired a number of data driven solutions to the image geolocalization problem. Existing approaches predict the location of a query image by matching it to a database of georeferenced photo...
 
Attribute-Based Detection of Unfamiliar Classes with Humans in the Loop
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Catherine Wah,Serge Belongie
Issue Date:June 2013
pp. 779-786
Recent work in computer vision has addressed zero-shot learning or unseen class detection, which involves categorizing objects without observing any training examples. However, these problems assume that attributes or defining characteristics of these unob...
 
Efficient Large-Scale Structured Learning
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Steve Branson,Oscar Beijbom,Serge Belongie
Issue Date:June 2013
pp. 1806-1813
We introduce an algorithm, SVM-IS, for structured SVM learning that is computationally scalable to very large datasets and complex structural representations. We show that structured learning is at least as fast-and often much faster-than methods based on ...
 
Wet fingerprint recognition: Challenges and opportunities
Found in: Biometrics, International Joint Conference on
By Prasanna Krishnasamy,Serge Belongie,David Kriegman
Issue Date:October 2011
pp. 1-7
Many fingers wrinkle or shrivel when immersed in water. When used for biometric identification, the recognition rate for wrinkled fingers degrades. The impact of wrinkling has so far not been well-understood. In this study, we present an investigation of h...
 
Toward a perceptual space for gloss
Found in: ACM Transactions on Graphics (TOG)
By David Kriegman, Josh Wills, Sameer Agarwal, Serge Belongie
Issue Date:August 2009
pp. 1-15
We design and implement a comprehensive study of the perception of gloss. This is the largest study of its kind to date, and the first to use real material measurements. In addition, we develop a novel multi-dimensional scaling (MDS) algorithm for analyzin...
     
CAPTCHA-based image labeling on the Soylent Grid
Found in: Proceedings of the ACM SIGKDD Workshop on Human Computation (HCOMP '09)
By John Miller, Kai Wang, Peter Faymonville, Serge Belongie
Issue Date:June 2009
pp. 46-49
We introduce an open labeling platform for Computer Vision researchers based on Captchas, creating as a byproduct labeled image data sets while supporting web security. For the two different tasks of annotation and detection, we explore usability issues. W...
     
Higher order learning with graphs
Found in: Proceedings of the 23rd international conference on Machine learning (ICML '06)
By Kristin Branson, Sameer Agarwal, Serge Belongie
Issue Date:June 2006
pp. 17-24
Recently there has been considerable interest in learning with higher order relations (i.e., three-way or higher) in the unsupervised and semi-supervised settings. Hypergraphs and tensors have been proposed as the natural way of representing these relation...
     
Structured importance sampling of environment maps
Found in: ACM SIGGRAPH 2003 Papers (SIGGRAPH '03)
By Henrik Wann Jensen, Ravi Ramamoorthi, Sameer Agarwal, Serge Belongie
Issue Date:July 2003
pp. 56-ff
We introduce structured importance sampling, a new technique for efficiently rendering scenes illuminated by distant natural illumination given in an environment map. Our method handles occlusion, high-frequency lighting, and is significantly faster than a...
     
 1