Search For:

Displaying 1-16 out of 16 total
Feature Matching with Affine-Function Transformation Models
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Hongsheng Li,Xiaolei Huang,Junzhou Huang,Shaoting Zhang
Issue Date:December 2014
pp. 1-1
Feature matching is an important problem and has extensive uses in computer vision. However, existing feature matching methods support either a specific or a small set of transformation models. In this paper, we propose a unified feature matchingframework ...
 
Optimal object matching via convexification and composition
Found in: Computer Vision, IEEE International Conference on
By Hongsheng Li, Junzhou Huang, Shaoting Zhang,Xiaolei Huang
Issue Date:November 2011
pp. 33-40
In this paper, we propose a novel object matching method to match an object to its instance in an input scene image, where both the object template and the input scene image are represented by groups of feature points. We relax each template point's discre...
 
Automatic image annotation using group sparsity
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Shaoting Zhang, Junzhou Huang, Yuchi Huang, Yang Yu, Hongsheng Li, Dimitris N. Metaxas
Issue Date:June 2010
pp. 3312-3319
Automatically assigning relevant text keywords to images is an important problem. Many algorithms have been proposed in the past decade and achieved good performance. Efforts have focused upon model representations of keywords, but properties of features h...
 
Simultaneous image transformation and sparse representation recovery
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Junzhou Huang, Xiaolei Huang, Dimitris Metaxas
Issue Date:June 2008
pp. 1-8
Sparse representation in compressive sensing is gaining increasing attention due to its success in various applications. As we demonstrate in this paper, however, image sparse representation is sensitive to image plane transformations such that existing ap...
 
Optimization and Learning for Registration of Moving Dynamic Textures
Found in: Computer Vision, IEEE International Conference on
By Junzhou Huang, Xiaolei Huang, Dimitris Metaxas
Issue Date:October 2007
pp. 1-8
We address the problem of registering a sequence of images in a moving dynamic texture video. This involves optimization with respect to camera motion, the average image, and the dynamic texture model. This problem is highly illposed and almost impossible ...
 
Pose-Free Facial Landmark Fitting via Optimized Part Mixtures and Cascaded Deformable Shape Model
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Xiang Yu,Junzhou Huang,Shaoting Zhang,Wang Yan,Dimitris N. Metaxas
Issue Date:December 2013
pp. 1944-1951
This paper addresses the problem of facial landmark localization and tracking from a single camera. We present a two-stage cascaded deformable shape model to effectively and efficiently localize facial landmarks with large head pose variations. For face de...
 
Robust Visual Tracking Using Local Sparse Appearance Model and K-Selection
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Baiyang Liu, Junzhou Huang,Casimir Kulikowski, Lin Yang
Issue Date:December 2013
pp. 2968-2981
Online learned tracking is widely used for its adaptive ability to handle appearance changes. However, it introduces potential drifting problems due to the accumulation of errors during the self-updating, especially for occluded scenarios. The recent liter...
 
Learning active facial patches for expression analysis
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Lin Zhong, Qingshan Liu, Peng Yang, Bo Liu, Junzhou Huang,D. N. Metaxas
Issue Date:June 2012
pp. 2562-2569
In this paper, we present a new idea to analyze facial expression by exploring some common and specific information among different expressions. Inspired by the observation that only a few facial parts are active in expression disclosure (e.g., around mout...
 
Robust tracking using local sparse appearance model and K-selection
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Baiyang Liu, Junzhou Huang, Lin Yang,C. Kulikowsk
Issue Date:June 2011
pp. 1313-1320
Online learned tracking is widely used for it's adaptive ability to handle appearance changes. However, it introduces potential drifting problems due to the accumulation of errors during the self-updating, especially for occluded scenarios. The recent lite...
 
Sparse shape composition: A new framework for shape prior modeling
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Shaoting Zhang, Yiqiang Zhan,M. Dewan, Junzhou Huang,D. N. Metaxas,X. S. Zhou
Issue Date:June 2011
pp. 1025-1032
Image appearance cues are often used to derive object shapes, which is usually one of the key steps of image understanding tasks. However, when image appearance cues are weak or misleading, shape priors become critical to infer and refine the shape derived...
 
A New Iris Segmentation Method for Recognition
Found in: Pattern Recognition, International Conference on
By Junzhou Huang, Yunhong Wang, Tieniu Tan, Jiali Cui
Issue Date:August 2004
pp. 554-557
As the first stage, iris segmentation is very important for an iris recognition system. If the iris regions were not correctly segmented, there would possibly exist four kinds of noises in segmented iris regions: eyelashes, eyelids, reflections and pupil, ...
 
An Iris Image Synthesis Method Based on PCA and Super-Resolution
Found in: Pattern Recognition, International Conference on
By Jiali Cui, Yunhong Wang, JunZhou Huang, Tieniu Tan, Zhenan Sun
Issue Date:August 2004
pp. 471-474
It is very important for the performance evaluation of iris recognition algorithms to construct very large iris databases. However, limited by the real conditions, there are no very large common iris databases now. In this paper, an iris image synthesis me...
 
A 3D Laplacian-driven parametric deformable model
Found in: Computer Vision, IEEE International Conference on
By Tian Shen,Xiaolei Huang,Hongsheng Li,Edward Kim,Shaoting Zhang,Junzhou Huang
Issue Date:November 2011
pp. 279-286
3D parametric deformable models have been used to extract volumetric object boundaries and they generate smooth boundary surfaces as results. However, in some segmentation cases, such as cerebral cortex with complex folds and creases, and human lung with h...
 
Explicit occlusion detection based deformable fitting for facial landmark localization
Found in: 2013 10th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2013)
By Xiang Yu, Fei Yang, Junzhou Huang,Dimitris N. Metaxas
Issue Date:April 2013
pp. 1-6
This paper addresses the problem of facial landmark localization on partially occluded faces. We proposes an explicit occlusion detection based deformable fitting model for occluded landmark localization. Most recent shape registration methods apply landma...
   
The role of dictionary learning on sparse representation-based classification
Found in: Proceedings of the 6th International Conference on PErvasive Technologies Related to Assistive Environments (PETRA '13)
By Farhad Kamangar, Junzhou Huang, Soheil Shafiee, Vassilis Athitsos
Issue Date:May 2013
pp. 1-8
This paper analyzes the role of dictionary selection in Sparse Representation-based Classification (SRC). While SRC introduces interesting results in the field of classification, its performance is highly limited by the number of training samples to form t...
     
Learning with structured sparsity
Found in: Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09)
By Dimitris Metaxas, Junzhou Huang, Tong Zhang
Issue Date:June 2009
pp. 1-8
This paper investigates a new learning formulation called structured sparsity, which is a natural extension of the standard sparsity concept in statistical learning and compressive sensing. By allowing arbitrary structures on the feature set, this concept ...
     
 1