Results 1  10
of
97
Oneshot learning of object categories
 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 2006
"... 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 learning from scratch, one can take advant ..."
Abstract

Cited by 360 (22 self)
 Add to MetaCart
(Show Context)
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 learning from scratch, one can take advantage of knowledge coming from previously learned categories, no matter how different these categories might be. We explore a Bayesian implementation of this idea. Object categories are represented by probabilistic models. Prior knowledge is represented as a probability density function on the parameters of these models. The posterior model for an object category is obtained by updating the prior in the light of one or more observations. We test a simple implementation of our algorithm on a database of 101 diverse object categories. We compare category models learned by an implementation of our Bayesian approach to models learned from by Maximum Likelihood (ML) and Maximum A Posteriori (MAP) methods. We find that on a database of more than 100 categories, the Bayesian approach produces informative models when the number of training examples is too small for other methods to operate successfully.
Hierarchical matching of deformable shapes
 In CVPR
, 2007
"... We describe a new hierarchical representation for twodimensional objects that captures shape information at multiple levels of resolution. The representation is based on a hierarchical description of an object’s boundary, and can be used in an elastic matching framework, both for comparing pairs of ..."
Abstract

Cited by 108 (1 self)
 Add to MetaCart
(Show Context)
We describe a new hierarchical representation for twodimensional objects that captures shape information at multiple levels of resolution. The representation is based on a hierarchical description of an object’s boundary, and can be used in an elastic matching framework, both for comparing pairs of objects and for detecting objects in cluttered images. In contrast to classical elastic models, our representation explicitly captures global shape information. This leads to richer geometric models and more accurate recognition results. Our experiments demonstrate classification results that are significantly better than the current stateoftheart in several shape datasets. We also show initial experiments in matching shapes to cluttered images. 1 1.
Proximity Distribution Kernels for Geometric Context in Category Recognition
"... haibin.ling @ siemens.com We propose using the proximity distribution of vectorquantized ..."
Abstract

Cited by 55 (3 self)
 Add to MetaCart
(Show Context)
haibin.ling @ siemens.com We propose using the proximity distribution of vectorquantized
Nearoptimal detection of geometric objects by fast multiscale methods
 IEEE Trans. Inform. Theory
, 2005
"... Abstract—We construct detectors for “geometric ” objects in noisy data. Examples include a detector for presence of a line segment of unknown length, position, and orientation in twodimensional image data with additive white Gaussian noise. We focus on the following two issues. i) The optimal detec ..."
Abstract

Cited by 43 (10 self)
 Add to MetaCart
(Show Context)
Abstract—We construct detectors for “geometric ” objects in noisy data. Examples include a detector for presence of a line segment of unknown length, position, and orientation in twodimensional image data with additive white Gaussian noise. We focus on the following two issues. i) The optimal detection threshold—i.e., the signal strength below which no method of detection can be successful for large dataset size. ii) The optimal computational complexity of a nearoptimal detector, i.e., the complexity required to detect signals slightly exceeding the detection threshold. We describe a general approach to such problems which covers several classes of geometrically defined signals; for example, with onedimensional data, signals having elevated mean on an interval, and, indimensional data, signals with elevated mean on a rectangle, a ball, or an ellipsoid. In all these problems, we show that a naive or straightforward approach leads to detector thresholds and algorithms which are asymptotically far away from optimal. At the same time, a multiscale geometric analysis of these classes of objects allows us to derive asymptotically optimal detection thresholds and fast algorithms for nearoptimal detectors. Index Terms—Beamlets, detecting hot spots, detecting line segments, Hough transform, image processing, maxima of Gaussian processes, multiscale geometric analysis, Radon transform. I.
Image Segmentation by BranchandMincut
"... Abstract. Efficient global optimization techniques such as graph cut exist for energies corresponding to binary image segmentation from lowlevel cues. However, introducing a highlevel prior such as a shape prior or a colordistribution prior into the segmentation process typically results in an ene ..."
Abstract

Cited by 28 (4 self)
 Add to MetaCart
(Show Context)
Abstract. Efficient global optimization techniques such as graph cut exist for energies corresponding to binary image segmentation from lowlevel cues. However, introducing a highlevel prior such as a shape prior or a colordistribution prior into the segmentation process typically results in an energy that is much harder to optimize. The main contribution of the paper is a new global optimization framework for a wide class of such energies. The framework is built upon two powerful techniques: graph cut and branchandbound. These techniques are unified through the derivation of lower bounds on the energies. Being computable via graph cut, these bounds are used to prune branches within a branchandbound search. We demonstrate that the new framework can compute globally optimal segmentations for a variety of segmentation scenarios in a reasonable time on a modern CPU. These scenarios include unsupervised segmentation of an object undergoing 3D pose change, categoryspecific shape segmentation, and the segmentation under intensity/color priors defined by ChanVese and GrabCut functionals. 2 Extended technical report of ECCV2008 publication 1
Matching by Linear Programming and Successive Convexification
"... Abstract—We present a novel convex programming scheme to solve matching problems, focusing on the challenging problem of matching in a large search range and with cluttered background. Matching is formulated as metric labeling with L1 regularization terms, for which we propose a novel linear program ..."
Abstract

Cited by 26 (4 self)
 Add to MetaCart
(Show Context)
Abstract—We present a novel convex programming scheme to solve matching problems, focusing on the challenging problem of matching in a large search range and with cluttered background. Matching is formulated as metric labeling with L1 regularization terms, for which we propose a novel linear programming relaxation method and an efficient successive convexification implementation. The unique feature of the proposed relaxation scheme is that a much smaller set of basis labels is used to represent the original label space. This greatly reduces the size of the searching space. A successive convexification scheme solves the labeling problem in a coarse to fine manner. Importantly, the original cost function is reconvexified at each stage, in the new focus region only, and the focus region is updated so as to refine the searching result. This makes the method wellsuited for large label set matching. Experiments demonstrate successful applications of the proposed matching scheme in object detection, motion estimation, and tracking. Index Terms—Matching, correspondence, linear programming, successive relaxation. Ç 1
OBJCUT: Efficient Segmentation Using TopDown and BottomUp Cues
 IEEE Transactions on Pattern Analysis and Machine Intelligence
, 2010
"... ..."
(Show Context)
Probabilistic models of object geometry for grasp planning
 Proceedings of Robotics: Science and Systems (RSS 2008
, 2008
"... Application to Grasping Robot manipulators typically rely on complete knowledge of object geometry in order to plan motions and compute grasps. However, when an object is not fully in view it can be difficult to form an accurate estimate of the object’s shape and pose, particularly when the object ..."
Abstract

Cited by 20 (0 self)
 Add to MetaCart
(Show Context)
Application to Grasping Robot manipulators typically rely on complete knowledge of object geometry in order to plan motions and compute grasps. However, when an object is not fully in view it can be difficult to form an accurate estimate of the object’s shape and pose, particularly when the object deforms. In this paper we describe a generative model of object geometry based on Mardia and Dryden’s “Probabilistic Procrustean Shape”, which captures both nonrigid deformations and object variability in a class. We extend their shape model to the setting where point correspondences are unknown using Scott and Nowak’s COPAP framework. We use this model to recognize objects in a cluttered image and to infer their complete twodimensional boundaries with a novel algorithm called OSIRIS. We show examples of learned models from image data and demonstrate how the models can be used by a manipulation planner to grasp objects in cluttered visual scenes. KEY WORDS—procrustean shape, robotic grasping, shape completion, occlusions, correspondences, MPEG7 1.
A 2D Human Body Model Dressed in Eigen Clothing
"... Abstract. Detection, tracking, segmentation and pose estimation of people in monocular images are widely studied. Twodimensional models of the human body are extensively used, however, they are typically fairly crude, representing the body either as a rough outline or in terms of articulated geomet ..."
Abstract

Cited by 17 (4 self)
 Add to MetaCart
(Show Context)
Abstract. Detection, tracking, segmentation and pose estimation of people in monocular images are widely studied. Twodimensional models of the human body are extensively used, however, they are typically fairly crude, representing the body either as a rough outline or in terms of articulated geometric primitives. We describe a new 2D model of the human body contour that combines an underlying naked body with a lowdimensional clothing model. The naked body is represented as a Contour Person that can take on a wide variety of poses and body shapes. Clothing is represented as a deformation from the underlying body contour. This deformation is learned from training examples using principal component analysis to produce eigen clothing. We find that the statistics of clothing deformations are skewed and we model the a priori probability of these deformations using a Beta distribution. The resulting generative model captures realistic human forms in monocular images and is used to infer 2D body shape and pose under clothing. We also use the coefficients of the eigen clothing to recognize different categories of clothing on dressed people. The method is evaluated quantitatively on synthetic and real images and achieves better accuracy than previous methods for estimating body shape under clothing. 1