Sciweavers

CVPR
2007
IEEE
14 years 11 months ago
From Videos to Verbs: Mining Videos for Activities using a Cascade of Dynamical Systems
Clustering video sequences in order to infer and extract activities from a single video stream is an extremely important problem and has significant potential in video indexing, s...
Pavan K. Turaga, Ashok Veeraraghavan, Rama Chellap...
CVPR
2007
IEEE
14 years 11 months ago
Large scale vision-based navigation without an accurate global reconstruction
Autonomous cars will likely play an important role in the future. A vision system designed to support outdoor navigation for such vehicles has to deal with large dynamic environme...
Albert Diosi, Anthony Remazeilles, François...
CVPR
2007
IEEE
14 years 11 months ago
A Fast 3D Correspondence Method for Statistical Shape Modeling
Accurately identifying corresponded landmarks from a population of shape instances is the major challenge in constructing statistical shape models. In this paper, we address this ...
Pahal Dalal, Brent C. Munsell, Song Wang, Jijun Ta...
CVPR
2007
IEEE
14 years 11 months ago
Linear Laplacian Discrimination for Feature Extraction
Discriminant feature extraction plays a fundamental role in pattern recognition. In this paper, we propose the Linear Laplacian Discrimination (LLD) algorithm for discriminant fea...
Deli Zhao, Zhouchen Lin, Rong Xiao, Xiaoou Tang
CVPR
2007
IEEE
14 years 11 months ago
Learning Visual Representations using Images with Captions
Current methods for learning visual categories work well when a large amount of labeled data is available, but can run into severe difficulties when the number of labeled examples...
Ariadna Quattoni, Michael Collins, Trevor Darrell
CVPR
2007
IEEE
14 years 11 months ago
Quality-Driven Face Occlusion Detection and Recovery
This paper presents a framework to automatically detect and recover the occluded facial region. We first derive a Bayesian formulation unifying the occlusion detection and recover...
Dahua Lin, Xiaoou Tang
CVPR
2007
IEEE
14 years 11 months ago
Automatic Removal of Chromatic Aberration from a Single Image
Many high resolution images exhibit chromatic aberration (CA), where the color channels appear shifted. Unfortunately, merely compensating for these shifts is sometimes inadequate...
Sing Bing Kang
CVPR
2007
IEEE
14 years 11 months ago
A Topic-Motion Model for Unsupervised Video Object Discovery
The bag-of-words representation has attracted a lot of attention recently in the field of object recognition. Based on the bag-of-words representation, topic models such as Probab...
David Liu, Tsuhan Chen
CVPR
2007
IEEE
14 years 11 months ago
Harmony in Motion
Cross-modal analysis offers information beyond that extracted from individual modalities. Consider a camcorder having a single microphone in a cocktail-party: it captures several ...
Zohar Barzelay, Yoav Y. Schechner
CVPR
2007
IEEE
14 years 11 months ago
Part-based Face Recognition Using Near Infrared Images
Recently, we developed NIR based face recognition for highly accurate face recognition under illumination variations [10]. In this paper, we present a part-based method for improv...
Ke Pan, ShengCai Liao, Zhijian Zhang, Stan Z. Li, ...