Sciweavers

ICCV
2009
IEEE
15 years 5 months ago
Heterogeneous Feature Machines for Visual Recognition
With the recent efforts made by computer vision researchers, more and more types of features have been designed to describe various aspects of visual characteristics. Modeling s...
Liangliang Cao, Jiebo Luo, Feng Liang, Thomas S. H...
ICCV
2009
IEEE
15 years 5 months ago
Efficient subset selection based on the Renyi entropy
Many machine learning algorithms require the summation of Gaussian kernel functions, an expensive operation if implemented straightforwardly. Several methods have been proposed t...
Vlad I. Morariu1, Balaji V. Srinivasan, Vikas C. R...
ICCV
2009
IEEE
15 years 5 months ago
Adaptive Fragments-Based Tracking of Non-Rigid Objects Using Level Sets
We present an approach to visual tracking based on dividing a target into multiple regions, or fragments. The target is represented by a Gaussian mixture model in a joint feature...
Prakash Chockalingam, Nalin Pradeep
ICCV
2009
IEEE
15 years 5 months ago
Which Faces to Tag: Adding Prior Constraints into Active Learning
We introduce an algorithm that guides the user to tag faces in the best possible order during a face recognition assisted tagging scenario. In particular, we extend the active l...
Ashish Kapoor, Gang Hua, Amir Akbarzadeh and Simon...
ICCV
2009
IEEE
1318views Computer Vision» more  ICCV 2009»
15 years 5 months ago
Non-Local Sparse Models for Image Restoration
We propose in this paper to unify two different ap- proaches to image restoration: On the one hand, learning a basis set (dictionary) adapted to sparse signal descriptions has p...
Julien Mairal, Francis Bach, Jean Ponce, Guillermo...
ICCV
2009
IEEE
15 years 5 months ago
Is a detector only good for detection?
A common design of an object recognition system has two steps, a detection step followed by a foreground withinclass classification step. For example, consider face detection by...
Quan Yuan and Stan Sclaroff
ICCV
2009
IEEE
15 years 5 months ago
Deformable Model Fitting with a Mixture of Local Experts
Local experts have been used to great effect for fitting deformable models to images. Typically, the best location in an image for the deformable model’s landmarks are found t...
Jason M. Saragih, Simon Lucey, Jeffrey F. Cohn
ICCV
2009
IEEE
15 years 5 months ago
Scene Shape Priors for Superpixel Segmentation
Unsupervised over-segmentation of an image into superpixels is a common preprocessing step for image parsing algorithms. Superpixels are used as both regions of support for feat...
Alastair P. Moore, Simon J. D. Prince, Jonathan Wa...
ICCV
2009
IEEE
15 years 5 months ago
Detecting Interpretable and Accurate Scale-Invariant keypoints
This paper presents a novel method for detecting scale invariant keypoints. It fills a gap in the set of available methods, as it proposes a scale-selection mechanism for juncti...
Wolfgang F¨orstner, Timo Dickscheid, Falko Schind...
ICCV
2009
IEEE
1048views Computer Vision» more  ICCV 2009»
15 years 5 months ago
Face Recognition With Contiguous Occlusion Using Markov Random Fields
Partially occluded faces are common in many applications of face recognition. While algorithms based on sparse representation have demonstrated promising results, they achieve t...
Zihan Zhou, Andrew Wagner, Hossein Mobahi, John Wr...