Browsing CSAIL Digital Archive by Author "Darrell, Trevor"
Now showing items 1-17 of 17
-
Approximate Correspondences in High Dimensions
Grauman, Kristen; Darrell, Trevor (2006-06-15)Pyramid intersection is an efficient method for computing an approximate partial matching between two sets of feature vectors. We introduce a novel pyramid embedding based on a hierarchy of non-uniformly shaped bins that ... -
Combining Object and Feature Dynamics in Probabilistic Tracking
Taycher, Leonid; Fisher III, John W.; Darrell, Trevor (2005-03-02)Objects can exhibit different dynamics at different scales, a property that isoftenexploited by visual tracking algorithms. A local dynamicmodel is typically used to extract image features that are then used as inputsto a ... -
Conditional Random People: Tracking Humans with CRFs and Grid Filters
Taycher, Leonid; Shakhnarovich, Gregory; Demirdjian, David; Darrell, Trevor (2005-12-01)We describe a state-space tracking approach based on a Conditional Random Field(CRF) model, where the observation potentials are \emph{learned} from data. Wefind functions that embed both state and observation into a space ... -
Discriminative Gaussian Process Latent Variable Model for Classification
Urtasun, Raquel; Darrell, Trevor (2007-03-28)Supervised learning is difficult with high dimensional input spacesand very small training sets, but accurate classification may bepossible if the data lie on a low-dimensional manifold. GaussianProcess Latent Variable ... -
Efficient Image Matching with Distributions of Local Invariant Features
Grauman, Kristen; Darrell, Trevor (2004-11-22)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 ... -
Fast concurrent object classification and localization
Yeh, Tom; Lee, John J.; Darrell, Trevor (2008-06-10)Object localization and classification are important problems incomputer vision. However, in many applications, exhaustive searchover all class labels and image locations is computationallyprohibitive. While several methods ... -
Fast Contour Matching Using Approximate Earth Mover's Distance
Grauman, Kristen; Darrell, Trevor (2003-12-05)Weighted graph matching is a good way to align a pair of shapesrepresented by a set of descriptive local features; the set ofcorrespondences produced by the minimum cost of matching features fromone shape to the features ... -
Latent-Dynamic Discriminative Models for Continuous Gesture Recognition
Morency, Louis-Philippe; Quattoni, Ariadna; Darrell, Trevor (2007-01-07)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 ... -
A Projected Subgradient Method for Scalable Multi-Task Learning
Quattoni, Ariadna; Carreras, Xavier; Collins, Michael; Darrell, Trevor (2008-07-23)Recent approaches to multi-task learning have investigated the use of a variety of matrix norm regularization schemes for promoting feature sharing across tasks.In essence, these approaches aim at extending the l1 framework ... -
Pyramid Match Kernels: Discriminative Classification with Sets of Image Features
Grauman, Kristen; Darrell, Trevor (2005-03-17)Discriminative learning is challenging when examples are setsof local image features, and the sets vary in cardinality and lackany sort of meaningful ordering. Kernel-based classificationmethods can learn complex decision ... -
Pyramid Match Kernels: Discriminative Classification with Sets of Image Features (version 2)
Grauman, Kristen; Darrell, Trevor (2006-03-18)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, ... -
Rank Priors for Continuous Non-Linear Dimensionality Reduction
Stiefelhagen, Rainer; Darrell, Trevor; Urtasun, Raquel; Geiger, Andreas (2008-09-26)Non-linear dimensionality reduction methods are powerful techniques to deal with high-dimensional datasets. However, they often are susceptible to local minima and perform poorly when initialized far from the global optimum, ... -
Transfer learning for image classification with sparse prototype representations
Quattoni, Ariadna; Collins, Michael; Darrell, Trevor (2008-03-03)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 ... -
Transfering Nonlinear Representations using Gaussian Processes with a Shared Latent Space
Urtasun, Raquel; Quattoni, Ariadna; Darrell, Trevor (2007-11-06)When a series of problems are related, representations derived fromlearning earlier tasks may be useful in solving later problems. Inthis paper we propose a novel approach to transfer learning withlow-dimensional, non-linear ... -
Transferring Nonlinear Representations using Gaussian Processes with a Shared Latent Space
Urtasun, Raquel; Quattoni, Ariadna; Lawrence, Neil; Darrell, Trevor (2008-04-11)When a series of problems are related, representations derived from learning earlier tasks may be useful in solving later problems. In this paper we propose a novel approach to transfer learning with low-dimensional, ... -
Unsupervised Distributed Feature Selection for Multi-view Object Recognition
Christoudias, C. Mario; Urtasun, Raquel; Darrell, Trevor (2008-02-17)Object recognition accuracy can be improved when information frommultiple views is integrated, but information in each view can oftenbe highly redundant. We consider the problem of distributed objectrecognition or indexing ... -
Virtual Visual Hulls: Example-Based 3D Shape Estimation from a Single Silhouette
Grauman, Kristen; Shakhnarovich, Gregory; Darrell, Trevor (2004-01-28)Recovering a volumetric model of a person, car, or other objectof interest from a single snapshot would be useful for many computergraphics applications. 3D model estimation in general is hard, andcurrently requires active ...