Sciweavers

CVPR
2012
IEEE
12 years 2 months ago
Background modeling using adaptive pixelwise kernel variances in a hybrid feature space
Recent work on background subtraction has shown developments on two major fronts. In one, there has been increasing sophistication of probabilistic models, from mixtures of Gaussi...
Manjunath Narayana, Allen R. Hanson, Erik G. Learn...
CVPR
2012
IEEE
12 years 2 months ago
Geodesic flow kernel for unsupervised domain adaptation
In real-world applications of visual recognition, many factors—such as pose, illumination, or image quality—can cause a significant mismatch between the source domain on whic...
Boqing Gong, Yuan Shi, Fei Sha, Kristen Grauman
ICDAR
2011
IEEE
13 years 4 days ago
Text Detection and Character Recognition in Scene Images with Unsupervised Feature Learning
—Reading text from photographs is a challenging problem that has received a signicant amount of attention. Two key components of most systems are (i) text detection from images a...
Adam Coates, Blake Carpenter, Carl Case, Sanjeev S...
DAGM
2011
Springer
13 years 9 days ago
Agnostic Domain Adaptation
The supervised learning paradigm assumes in general that both training and test data are sampled from the same distribution. When this assumption is violated, we are in the setting...
Alexander Vezhnevets, Joachim M. Buhmann
SIGIR
2011
ACM
13 years 3 months ago
Bag-of-visual-words vs global image descriptors on two-stage multimodal retrieval
The Bag-Of-Visual-Words (BOVW) paradigm is fast becoming a popular image representation for Content-Based Image Retrieval (CBIR), mainly because of its better retrieval effectiven...
Savvas A. Chatzichristofis, Konstantinos Zagoris, ...
RECOMB
2011
Springer
13 years 3 months ago
Rich Parameterization Improves RNA Structure Prediction
Motivation. Current approaches to RNA structure prediction range from physics-based methods, which rely on thousands of experimentally-measured thermodynamic parameters, to machin...
Shay Zakov, Yoav Goldberg, Michael Elhadad, Michal...
ICASSP
2011
IEEE
13 years 4 months ago
A novel approach using modulation features for multiphone-based speech recognition
Recent advances in coherent and convex demodulation have proven useful for analyzing and modifying the low-frequency envelope structure of speech. This paper reports the applicati...
Pascal Clark, Gregory Sell, Les E. Atlas
FGR
2011
IEEE
255views Biometrics» more  FGR 2011»
13 years 4 months ago
Beyond simple features: A large-scale feature search approach to unconstrained face recognition
— Many modern computer vision algorithms are built atop of a set of low-level feature operators (such as SIFT [1], [2]; HOG [3], [4]; or LBP [5], [6]) that transform raw pixel va...
David D. Cox, Nicolas Pinto
NIPS
2008
14 years 1 months ago
Dimensionality Reduction for Data in Multiple Feature Representations
In solving complex visual learning tasks, adopting multiple descriptors to more precisely characterize the data has been a feasible way for improving performance. These representa...
Yen-Yu Lin, Tyng-Luh Liu, Chiou-Shann Fuh
MMM
2008
Springer
117views Multimedia» more  MMM 2008»
14 years 7 months ago
Distribution-Based Similarity for Multi-represented Multimedia Objects
In modern multimedia databases, objects can be represented by a large variety of feature representations. In order to employ all available information in a best possible way, a joi...
Hans-Peter Kriegel, Peter Kunath, Alexey Pryakhin,...