Tone Reproduction: A Perspective from Luminance-Driven Perceptual Grouping (2008)
Hwann-tzong Chen, Tyng-luh Liu, Tien-lung Chang
We address the tone reproduction problem by integrating local adaptation with global-contrast consistency. Many previous works have tried to compress high-dynamic-range (HDR) luminances into a...
Tyng-luh Liu, Mike Donahue, Davi Geiger, Robert Hummel
Abstract. We study the problem of how to detect "interesting objects" appeared in a given image, I. Our approach is to treat it as a function approximation problem based on an...
Hwann-tzong Chen, Tyng-luh Liu
Optimization methods based on iterative schemes can be divided into two classes: linesearch methods and trustregion methods. While linesearch techniques are commonly found in various vision...
Tyng-luh Liu, Mike Donahue, Davi Geiger, Robert Hummel
Abstract. We study the problem of how to detect "interesting objects" appeared in a given image, I. Our approach is to treat it as a function approximation problem based on an...
Detecting Deformable Objects with Flexible Shape Priors (2007)
We address the problem of detecting objects/shapes with large deformation and articulation in cluttered images. The approach requires a shape prior that describes the approximated outline and...
Probabilistic Tracking with Optimal Scale and Orientation Selection (2007)
Hwann-tzong Chen, Tyng-luh Liu
We describe a probabilistic framework based on trustregion method to track rigid or non-rigid objects with automatic optimal scale and orientation selection. The approach uses a flexible probability...
Probabilistic Tracking with Adaptive Feature Selection (2004)
Hwann-tzong Chen, Tyng-luh Liu, Chiou-shann Fuh
We propose a color-based tracking framework that infers alternately an object's configuration and good color features via particle filtering. The tracker adaptively selects discriminative color...
Multi-object tracking using dynamical graph matching (2001)
Hwann-tzong Chen, Horng-horng Lin, Tyng-luh Liu
We describe a tracking algorithm to address the interactions among objects, and to track them individually and confidently via a static camera. It is achieved by constructing an invariant bipartite...
Multi-object tracking using dynamical graph matching (2001)
Hwann-tzong Chen, Horng-horng Lin, Tyng-luh Liu
We describe a tracking algorithm to address the interactions among objects, and to track them individually and confidently via a static camera. It is achieved by constructing an invariant bipartite...
Sparse Representations for Image Decompositions (1999)
Davi Geiger, Tyng-luh Liu, Michael J. Donahue
We are given an image I and a library of templates such that is an overcomplete basis for I . The templates can represent objects, faces, features, analytical functions, or be single pixel templates...
Approximate tree matching and shape similarity (1999)
We present a framework for 2D shape contour (silhouette) comparison that can account for stretchings, occlusions and region information. Topological changes due to the original 3D scenarios and...
Sparse representations for image decompositions (1999)
Davi Geiger, Tyng-luh Liu, Michael J. Donahue
We are given an image I and a library of templates L, such that L is an overcomplete basis for I. The templates can represent objects, faces, features, analytical functions, or be single pixel...
Segmenting by seeking the symmetry axis (1998)
Tyng-luh Liu, Davi Geiger, Alan L. Yuille
We introduce a method for segmenting a shape from an image and simultaneously determining its symmetry axis. The symmetry is used to help the segmentation and in turn the segmentation determines the...
Segmenting by Seeking the Symmetry Axis (1998)
Tyng-luh Liu, Davi Geiger, Alan L. Yuille
We introduce a method for segmenting a shape from an image and simultaneously determining its symmetry axis. The symmetry is used to help the segmentation and in turn the segmentation determines the...
Representation and Self-Similarity of Shapes (1998)
Tyng-luh Liu, Davi Geiger, Robert V. Kohn
Representing shapes is a significant problem for vision systems that must recognize or classify objects. We derive a representation for a given shape by investigating its self-similarities, and...
Segmenting by seeking the symmetry axis (1998)
We introduce a method for segmenting a shape from an image and simultaneously determining its symmetry axis. The symmetry is used to help the segmentation and in turn the segmentation determines the...
Representation and self-similarity of shapes (1998)
Tyng-luh Liu, Davi Geiger, Robert V. Kohn
Representing shapes is a signi cant problem for vision systems that must recognize or classify objects. We derive a representation for a given shape by investigating its self-similarities, and...
Representation and self-similarity of shapes (1998)
Tyng-luh Liu, Davi Geiger, Robert V. Kohn
Representing shapes is a signi cant problem for vision systems that must recognize or classify objects. We derive a representation for a given shape by investigating its self-similarities, and...
Visual Deconstruction: Recognizing Articulated Objects (1997)
. We propose a deconstruction framework to recognize and find articulated objects. In particular we are interested in human arm and leg articulations. The deconstruction view of recognition naturally...
Sparse Representations for Image Decomposition with Occlusions (1996)
Mike Donahue Davi, Mike Donahue, Davi Geiger, Robert Hummel, Tyng-luh Liu
We study the problem of how to detect "interesting objects" appeared in a given image, I. Our approach is to treat it as a function approximation problem based on an over-redundant basis,...
Image Recognition with Occlusions (1996)
Tyng-luh Liu, Mike Donahue, Davi Geiger, Robert Hummel
Abstract. We study the problem of how to detect \interesting objects" appeared in a given image, I. Our approach is to treat it as a function approximation problem based on an over-redundant...
Sparse Representations for Image Decomposition with Occlusions (1996)
Mike Donahue, Davi Geiger, Robert Hummel, Tyng-luh Liu
We study the problem of how to detect "interesting objects" appeared in a given image, I. Our approach is to treat it as a function approximation problem based on an over-redundant basis,...
Image Recognition with Occlusions (1996)
Tyng-luh Liu, Mike Donahue, Davi Geiger, Robert Hummel
. We study the problem of how to detect "interesting objects" appeared in a given image, I. Our approach is to treat it as a function approximation problem based on an over-redundant basis....