Sciweavers

CVPR
2009
IEEE
14 years 3 months ago
Shape-based object recognition in videos using 3D synthetic object models
In this paper we address the problem of recognizing moving objects in videos by utilizing synthetic 3D models. We use only the silhouette space of the synthetic models making thus...
Alexander Toshev, Ameesh Makadia, Kostas Daniilidi...
CVPR
2009
IEEE
14 years 3 months ago
Imbalanced RankBoost for efficiently ranking large-scale image/video collections
Ranking large scale image and video collections usually expects higher accuracy on top ranked data, while tolerates lower accuracy on bottom ranked ones. In view of this, we propo...
Michele Merler, Rong Yan, John R. Smith
CVPR
2009
IEEE
14 years 3 months ago
Towards high-resolution large-scale multi-view stereo
Boosted by the Middlebury challenge, the precision of dense multi-view stereovision methods has increased drastically in the past few years. Yet, most methods, although they perfo...
Vu Hoang Hiep, Renaud Keriven, Patrick Labatut, Je...
CVPR
2009
IEEE
14 years 3 months ago
Learning to associate: HybridBoosted multi-target tracker for crowded scene
We propose a learning-based hierarchical approach of multi-target tracking from a single camera by progressively associating detection responses into longer and longer track fragm...
Yuan Li, Chang Huang, Ram Nevatia
CVPR
2009
IEEE
14 years 3 months ago
Label diagnosis through self tuning forweb image search
Jun Wang, Yu-Gang Jiang, Shih-Fu Chang
CVPR
2009
IEEE
14 years 3 months ago
High-quality curvelet-based motion deblurring from an image pair
One promising approach to remove motion deblurring is to recover one clear image using an image pair. Existing dual-image methods require an accurate image alignment between the i...
Jian-Feng Cai, Hui Ji, Chaoqiang Liu, Zuowei Shen
CVPR
2009
IEEE
14 years 3 months ago
Keypoint induced distance profiles for visual recognition
We show that histograms of keypoint descriptor distances can make useful features for visual recognition. Descriptor distances are often exhaustively computed between sets of keyp...
Tat-Jun Chin, David Suter
CVPR
2009
IEEE
14 years 3 months ago
ImageNet: A large-scale hierarchical image database
The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images a...
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai...
CVPR
2009
IEEE
14 years 3 months ago
Efficiently training a better visual detector with sparse eigenvectors
Face detection plays an important role in many vision applications. Since Viola and Jones [1] proposed the first real-time AdaBoost based object detection system, much effort has ...
Sakrapee Paisitkriangkrai, Chunhua Shen, Jian Zhan...
CVPR
2009
IEEE
14 years 3 months ago
Efficient image alignment using linear appearance models
Visual tracking is a key component in many computer vision applications. Linear subspace techniques (e.g. eigentracking) are one of the most popular approaches to align templates ...
Jose Gonzalez-Mora, Nicolas Guil, Emilio L. Zapata...