Search For:

Displaying 1-50 out of 72 total
Active Learning with Gaussian Processes for Object Categorization
Found in: Computer Vision, IEEE International Conference on
By Ashish Kapoor, Kristen Grauman, Raquel Urtasun, Trevor Darrell
Issue Date:October 2007
pp. 1-8
Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gaussian Processes (GPs) are powerful regression techniques with explicit uncertai...
 
Pyramid Match Hashing: Sub-Linear Time Indexing Over Partial Correspondences
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Kristen Grauman, Trevor Darrell
Issue Date:June 2007
pp. 1-8
Matching local features across images is often useful when comparing or recognizing objects or scenes, and efficient techniques for obtaining image-to-image correspondences have been developed [4, 11, 16]. However, given a query image, searching a very lar...
 
Learning Visual Representations using Images with Captions
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ariadna Quattoni, Michael Collins, Trevor Darrell
Issue Date:June 2007
pp. 1-8
Current methods for learning visual categories work well when a large amount of labeled data is available, but can run into severe difficulties when the number of labeled examples is small. When labeled data is scarce it may be beneficial to use unlabeled ...
 
Latent-Dynamic Discriminative Models for Continuous Gesture Recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Louis-Philippe Morency, Ariadna Quattoni, Trevor Darrell
Issue Date:June 2007
pp. 1-8
Many problems in vision involve the prediction of a class label for each frame in an unsegmented sequence. In this paper, we develop a discriminative framework for simultaneous sequence segmentation and labeling which can capture both intrinsic and extrins...
 
Perceptive Presence
Found in: IEEE Computer Graphics and Applications
By Frank Bentley, Konrad Tollmar, David Demirdjian, Kimberle Koile, Trevor Darrell
Issue Date:September 2003
pp. 26-36
<p>Perceptive presence systems automatically convey awareness of user states to a remote location or application without the user having to perform explicit commands or mode selection. The article describes a component-based architecture for creating...
 
Modeling Radiometric Uncertainty for Vision with Tone-Mapped Color Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ayan Chakrabarti,Ying Xiong,Baochen Sun,Trevor Darrell,Daniel Scharstein,Todd Zickler,Kate Saenko
Issue Date:November 2014
pp. 1-1
To produce images that are suitable for display, tone-mapping is widely used in digital cameras to map linear color measurements into narrow gamuts with limited dynamic range. This introduces non-linear distortion that must be undone, through a radiometric...
 
Latent Task Adaptation with Large-Scale Hierarchies
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Yangqing Jia,Trevor Darrell
Issue Date:December 2013
pp. 2080-2087
Recent years have witnessed the success of large-scale image classification systems that are able to identify objects among thousands of possible labels. However, it is yet unclear how general classifiers such as ones trained on Image Net can be optimally ...
 
Learning cross-modality similarity for multinomial data
Found in: Computer Vision, IEEE International Conference on
By Yangqing Jia,Mathieu Salzmann,Trevor Darrell
Issue Date:November 2011
pp. 2407-2414
Many applications involve multiple-modalities such as text and images that describe the problem of interest. In order to leverage the information present in all the modalities, one must model the relationships between them. While some techniques have been ...
 
Scalable classifiers for Internet vision tasks
Found in: Computer Vision and Pattern Recognition Workshop
By Tom Yeh, John J. Lee, Trevor Darrell
Issue Date:June 2008
pp. 1-8
Object recognition systems designed for Internet applications typically need to adapt to users’ needs in a flexible fashion and scale up to very large data sets. In this paper, we analyze the complexity of several multiclass SVM-based algorithms and highli...
 
Transfer learning for image classification with sparse prototype representations
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ariadna Quattoni, Michael Collins, Trevor Darrell
Issue Date:June 2008
pp. 1-8
To learn a new visual category from few examples, prior knowledge from unlabeled data as well as previous related categories may be useful. We develop a new method for transfer learning which exploits available unlabeled data and an arbitrary kernel functi...
 
Autotagging Facebook: Social network context improves photo annotation
Found in: Computer Vision and Pattern Recognition Workshop
By Zak Stone, Todd Zickler, Trevor Darrell
Issue Date:June 2008
pp. 1-8
Most personal photos that are shared online are embedded in some form of social network, and these social networks are a potent source of contextual information that can be leveraged for automatic image understanding. In this paper, we investigate the util...
 
Dynamic visual category learning
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tom Yeh, Trevor Darrell
Issue Date:June 2008
pp. 1-8
Dynamic visual category learning calls for efficient adaptation as new training images become available or new categories are defined, existing training images or categories become modified or obsolete, or when categories are divided into subcategories or ...
 
Adaptive Vocabulary Forests br Dynamic Indexing and Category Learning
Found in: Computer Vision, IEEE International Conference on
By Tom Yeh, John Lee, Trevor Darrell
Issue Date:October 2007
pp. 1-8
Histogram pyramid representations computed from a vacabulary tree of visual words have proven valuable for a range of image indexing and recognition tasks; however, they have only used a single, fixed partition of feature space. We present a new efficient ...
 
Conditional Random People: Tracking Humans with CRFs and Grid Filters
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Leonid Taycher, David Demirdjian, Trevor Darrell, Gregory Shakhnarovich
Issue Date:June 2006
pp. 222-229
We describe a state-space tracking approach based on a Conditional Random Field (CRF) model, where the observation potentials are learned from data. We find functions that embed both state and observation into a space where similarity corresponds to L1 dis...
 
Hidden Conditional Random Fields for Gesture Recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Sy Bor Wang, Ariadna Quattoni, Louis-Philippe Morency, David Demirdjian, Trevor Darrell
Issue Date:June 2006
pp. 1521-1527
We introduce a discriminative hidden-state approach for the recognition of human gestures. Gesture sequences often have a complex underlying structure, and models that can incorporate hidden structures have proven to be advantageous for recognition tasks. ...
 
Visual Speech Recognition with Loosely Synchronized Feature Streams
Found in: Computer Vision, IEEE International Conference on
By Kate Saenko, Karen Livescu, Michael Siracusa, Kevin Wilson,, James Glass, Trevor Darrell
Issue Date:October 2005
pp. 1424-1431
We present an approach to detecting and recognizing spoken isolated phrases based solely on visual input. We adopt an architecture that first employs discriminative detection of visual speech and articulatory features, and then performs recognition using a...
 
Incorporating Semantic Constraints into a Discriminative Categorization and Labelling Model.
Found in: Computer Vision Workshops, International Conference on
By Ariadna Quattoni, Michael Collins, Trevor Darrell
Issue Date:October 2005
pp. 1877
<p>This paper describes an approach to incorporate semantic knowledge sources within a discriminative learning framework. We consider a joint scene categorization and region labelling task and assume that some semantic knowledge is available. For exa...
 
Efficient Image Matching with Distributions of Local Invariant Features
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Kristen Grauman, Trevor Darrell
Issue Date:June 2005
pp. 627-634
Sets of local features that are invariant to common image transformations are an effective representation to use when comparing images; current methods typically judge feature sets? similarity via a voting scheme (which ignores co-occurrence statistics) or...
 
On Modelling Nonlinear Shape-and-Texture Appearance Manifolds
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By C. Mario Christoudias, Trevor Darrell
Issue Date:June 2005
pp. 1067-1074
Statistical shape-and-texture appearance models employ image metamorphosis to form a rich, compact representation of object appearance. They achieve their efficiency by decomposing appearance into simpler shape-and-texture representations. In general, the ...
 
Face Recognition with Image Sets Using Manifold Density Divergence
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ognjen Arandjelović, Gregory Shakhnarovich, John Fisher, Roberto Cipolla, Trevor Darrell
Issue Date:June 2005
pp. 581-588
In many automatic face recognition applications, a set of a person?s face images is available rather than a single image. In this paper, we describe a novel method for face recognition using image sets. We propose a flexible, semi-parametric model for lear...
 
Learning Appearance Manifolds from Video
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ali Rahimi, Ben Recht, Trevor Darrell
Issue Date:June 2005
pp. 868-875
The appearance of dynamic scenes is often largely governed by a latent low-dimensional dynamic process. We show how to learn a mapping from video frames to this low-dimensional representation by exploiting the temporal coherence between frames and supervis...
 
Combining Object and Feature Dynamics in Probabilistic Tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Leonid Taycher, John W. Fisher III, Trevor Darrell
Issue Date:June 2005
pp. 106-113
Objects can exhibit different dynamics at different scales, and this is often exploited by visual tracking algorithms. A local dynamic model is typically used to extract image features that are then used as input to a system for tracking the entire object ...
 
Incorporating Object Tracking Feedback into Background Maintenance Framework
Found in: Applications of Computer Vision and the IEEE Workshop on Motion and Video Computing, IEEE Workshop on
By Leonid Taycher, John W. Fisher III, Trevor Darrell
Issue Date:January 2005
pp. 120-125
Adaptive background modeling/subtraction techniques are popular, in particular, because they are able to cope with background variations that are due to lighting variations. Unfortunately these models also tend to adapt to foreground objects that become st...
 
Simultaneous Calibration and Tracking with a Network of Non-Overlapping Sensors
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ali Rahimi, Brian Dunagan, Trevor Darrell
Issue Date:July 2004
pp. 187-194
We describe a method for simultaneously recovering the trajectory of a target and the external calibration parameters of non-overlapping cameras in a multi-camera system. Each camera is assumed to measure the location of a moving target within its field of...
 
Inferring 3D Structure with a Statistical Image-Based Shape Model
Found in: Computer Vision, IEEE International Conference on
By Kristen Grauman, Gregory Shakhnarovich, Trevor Darrell
Issue Date:October 2003
pp. 641
We present an image-based approach to infer 3D structure parameters using a probabilistic
 
Fast Pose Estimation with Parameter-Sensitive Hashing
Found in: Computer Vision, IEEE International Conference on
By Gregory Shakhnarovich, Paul Viola, Trevor Darrell
Issue Date:October 2003
pp. 750
Example-based methods are effective for parameter estimation problems when the underlying system is simple or the dimensionality of the input is low. For complex and high-dimensional problems such as pose estimation, the number of required examples and the...
 
A Bayesian Approach to Image-Based Visual Hull Reconstruction
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Kristen Grauman, Gregory Shakhnarovich, Trevor Darrell
Issue Date:June 2003
pp. 187
We present a Bayesian approach to image-based visual hull reconstruction. The 3-D shape of an object of a known class is represented by sets of silhouette views simultaneously observed from multiple cameras. We show how the use of a class-specific prior in...
 
Audiovisual Arrays for Untethered Spoken Interfaces
Found in: Multimodal Interfaces, IEEE International Conference on
By Kevin Wilson, Vibhav Rangarajan, Neal Checka, Trevor Darrell
Issue Date:October 2002
pp. 389
When faced with a distant speaker at a known location in a noisy environment, a microphone array can provide a significantly improved audio signal for speech recognition. Estimating the location of a speaker in a reverberant environment from audio informat...
 
Stereo Tracking Using ICP and Normal Flow Constraint
Found in: Pattern Recognition, International Conference on
By Louis-Philippe Morency, Trevor Darrell
Issue Date:August 2002
pp. 40367
This paper presents a new approach for 3D view registration of stereo images. We introduce a hybrid error function which combines constraints from the ICP (Iterative Closest Point) algorithm and normal flow constraint. This new technique is more precise fo...
 
Fast 3D Model Acquisition from Stereo Images
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Louis-Philippe Morency, Ali Rahimi, Trevor Darrell
Issue Date:June 2002
pp. 172
We propose a fast 3D model acquisition system that aligns intensity and depth images, and reconstructs a texture 3D mesh. 3D views are registered with shape alignment based on intensity gradient constraints and a global registration algorithm. We reconstru...
 
On Probabilistic Combination of Face and Gait Cues for Identification
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Gregory Shakhnarovich, Trevor Darrell
Issue Date:May 2002
pp. 0176
We approach the task of person identification based on face and gait cues. The cues are derived from multiple simultaneous camera views, combined through the visual hull algorithm to create imagery in canonical pose prior to recognition. These view-normali...
 
Fast Stereo-Based Head Tracking for Interactive Environments
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Louis-Philippe Morency, Ali Rahimi, Neal Checka, Trevor Darrell
Issue Date:May 2002
pp. 0390
We present a robust implementation of stereo-based head tracking designed for interactive environments with uncontrolled lighting. We integrate fast face detection and drift reduction algorithms with a gradient-based stereo rigid motion tracking technique....
 
Articulated-Pose Estimation Using Brightness and Depth-Constancy Constraints
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Michele Covell, Ali Rahimi, Michael Harville, Trevor Darrell
Issue Date:June 2000
pp. 2438
This paper explores several approaches for articulated-pose estimation, assuming that video-rate depth information is available, from either stereo cameras or other sensors. We use these depth measurements in the traditional linear brightness constraint eq...
 
Rendering Articulated Figures from Examples
Found in: Multi-View Modeling and Analysis of Visual Scenes, IEEE Workshop on
By Trevor Darrell
Issue Date:June 1999
pp. 65
This paper presents new methods to robustly track and interpolate images of complex articulated figures. Traditional interpolation approaches fail on these cases since appearance is not necessarily a smooth function nor a linear manifold. We show how to mo...
 
Active Face Tracking and Pose Estimation in an Interactive Room
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Trevor Darrell, Baback Moghaddam, Alex P. Pentland
Issue Date:June 1996
pp. 67
We demonstrate real-time face tracking and pose estimation in an unconstrained office environment with an active foveated camera. Using vision routines previously implemented for an interactive environment, we determine the spatial location of a user's hea...
 
Cooperative Robust Estimation Using Layers of Support
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Trevor Darrell, Alex P. Pentland
Issue Date:May 1995
pp. 474-487
<p><it>Abstract</it>—We present an approach to the problem of representing images that contain multiple objects or surfaces. Rather than use an edge-based approach to represent the segmentation of a scene, we propose a multilayer estimati...
 
YouTube2Text: Recognizing and Describing Arbitrary Activities Using Semantic Hierarchies and Zero-Shot Recognition
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Sergio Guadarrama,Niveda Krishnamoorthy,Girish Malkarnenkar,Subhashini Venugopalan,Raymond Mooney,Trevor Darrell,Kate Saenko
Issue Date:December 2013
pp. 2712-2719
Despite a recent push towards large-scale object recognition, activity recognition remains limited to narrow domains and small vocabularies of actions. In this paper, we tackle the challenge of recognizing and describing activities ``in-the-wild''. We pres...
 
Deformable Part Descriptors for Fine-Grained Recognition and Attribute Prediction
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Ning Zhang,Ryan Farrell,Forrest Iandola,Trevor Darrell
Issue Date:December 2013
pp. 729-736
Recognizing objects in fine-grained domains can be extremely challenging due to the subtle differences between subcategories. Discriminative markings are often highly localized, leading traditional object recognition approaches to struggle with the large p...
 
Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance
Found in: Computer Vision, IEEE International Conference on
By Ryan Farrell,Om Oza, Ning Zhang,Vlad I. Morariu,Trevor Darrell,Larry S. Davis
Issue Date:November 2011
pp. 161-168
Subordinate-level categorization typically rests on establishing salient distinctions between part-level characteristics of objects, in contrast to basic-level categorization, where the presence or absence of parts is determinative. We develop an approach ...
 
Multistream Articulatory Feature-Based Models for Visual Speech Recognition
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kate Saenko, Karen Livescu, James Glass, Trevor Darrell
Issue Date:September 2009
pp. 1700-1707
We study the problem of automatic visual speech recognition (VSR) using dynamic Bayesian network (DBN)-based models consisting of multiple sequences of hidden states, each corresponding to an articulatory feature (AF) such as lip opening (LO) or lip roundi...
 
Unsupervised feature selection via distributed coding for multi-view object recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By C. Mario Christoudias, Raquel Urtasun, Trevor Darrell
Issue Date:June 2008
pp. 1-8
Object recognition accuracy can be improved when information from multiple views is integrated, but information in each view can often be highly redundant. We consider the problem of distributed object recognition or indexing from multiple cameras, where t...
 
Sparse probabilistic regression for activity-independent human pose inference
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Raquel Urtasun, Trevor Darrell
Issue Date:June 2008
pp. 1-8
Discriminative approaches to human pose inference in volve mapping visual observations to articulated body configurations. Current probabilistic approaches to learn this mapping have been limited in their ability to handle domains with a large number of ac...
 
Hidden Conditional Random Fields
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ariadna Quattoni, Sybor Wang, Louis-Philippe Morency, Michael Collins, Trevor Darrell
Issue Date:October 2007
pp. 1848-1852
We present a discriminative latent variable model for classification problems in structured domains where inputs can be represented by a graph of local observations. A hidden-state Conditional Random Field framework learns a set of latent variables conditi...
 
Learning to Transform Time Series with a Few Examples
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ali Rahimi, Ben Recht, Trevor Darrell
Issue Date:October 2007
pp. 1759-1775
We describe a semi-supervised regression algorithm that learns to transform one time series into another time series given examples of the transformation. This algorithm is applied to tracking, where a time series of observations from sensors is transforme...
 
The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features
Found in: Computer Vision, IEEE International Conference on
By Kristen Grauman, Trevor Darrell
Issue Date:October 2005
pp. 1458-1465
Discriminative learning is challenging when examples are sets of features, and the sets vary in cardinality and lack any sort of meaningful ordering. Kernel-based classification methods can learn complex decision boundaries, but a kernel over unordered set...
 
Fast Contour Matching Using Approximate Earth Mover's Distance
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Kristen Grauman, Trevor Darrell
Issue Date:July 2004
pp. 220-227
Weighted graph matching is a good way to align a pair of shapes represented by a set of descriptive local features; the set of correspondences produced by the minimum cost matching between two shapes? features often reveals how similar the shapes are. Howe...
 
Searching the Web with Mobile Images for Location Recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Tom Yeh, Konrad Tollmar, Trevor Darrell
Issue Date:July 2004
pp. 76-81
In this paper, we describe an approach to recognizing location from mobile devices using image-based web search. We demonstrate the usefulness of common image search metrics applied on images captured with a camera-equipped mobile device to find matching i...
 
Pose Estimation using 3D View-Based Eigenspaces
Found in: Analysis and Modeling of Faces and Gestures, IEEE International Workshop on
By Louis-Philippe Morency, Patrik Sundberg, Trevor Darrell
Issue Date:October 2003
pp. 45
In this paper we present a method for estimating the absolute pose of a rigid object based on intensity and depth view-based eigenspaces, built across multiple views of example objects of the same class. Given an initial frame of an object with unknown pos...
 
Adaptive View-Based Appearance Models
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Louis-Philippe Morency, Ali Rahimi, Trevor Darrell
Issue Date:June 2003
pp. 803
We present a method for online rigid object tracking using an adaptive view-based appearance model. When the object?s pose trajectory crosses itself, our tracker has bounded drift and can track objects undergoing large motion for long periods of time. Our ...
 
A Probabilistic Framework for Multi-modal Multi-Person Tracking
Found in: Computer Vision and Pattern Recognition Workshop
By Neal Checka, Kevin Wilson, Vibhav Rangarajan, Trevor Darrell
Issue Date:June 2003
pp. 100
In this paper, we present a probabilistic tracking framework that combines sound and vision to achieve more robust and accurate tracking of multiple objects. In a cluttered or noisy scene, our measurements have a non-Gaussian, multi-modal distribution. We ...
 
 1  2 Next >>