Sciweavers

CVPR
2006
IEEE
15 years 4 days ago
Space-Time Video Montage
Conventional video summarization methods focus predominantly on summarizing videos along the time axis, such as building a movie trailer. The resulting video trailer tends to reta...
Hong-Wen Kang, Yasuyuki Matsushita, Xiaoou Tang, X...
CVPR
2006
IEEE
15 years 4 days ago
Contour-Based Structure from Reflection
Po-Hao Huang, Shang-Hong Lai
CVPR
2006
IEEE
15 years 4 days ago
Escaping local minima through hierarchical model selection: Automatic object discovery, segmentation, and tracking in video
Recently, the generative modeling approach to video segmentation has been gaining popularity in the computer vision community. For example, the flexible sprites framework has been...
Nebojsa Jojic, John M. Winn, Larry Zitnick
CVPR
2006
IEEE
15 years 4 days ago
Context and Hierarchy in a Probabilistic Image Model
It is widely conjectured that the excellent ROC performance of biological vision systems is due in large part to the exploitation of context at each of many levels in a part/whole...
Ya Jin, Stuart Geman
CVPR
2006
IEEE
15 years 4 days ago
Measurement integration under inconsistency for robust tracking
The solutions to many vision problems involve integrating measurements from multiple sources. Most existing methods rely on a hidden assumption, i.e., these measurements are consi...
Gang Hua, Ying Wu
CVPR
2006
IEEE
15 years 4 days ago
Successive Convex Matching for Action Detection
We propose human action detection based on a successive convex matching scheme. Human actions are represented as sequences of postures and specific actions are detected in video b...
Hao Jiang, Mark S. Drew, Ze-Nian Li
CVPR
2006
IEEE
15 years 4 days ago
Accelerated Kernel Feature Analysis
A fast algorithm, Accelerated Kernel Feature Analysis (AKFA), that discovers salient features evidenced in a sample of n unclassified patterns, is presented. Like earlier kernel-b...
Xianhua Jiang, Yuichi Motai, Robert R. Snapp, Xing...
CVPR
2006
IEEE
15 years 4 days ago
Learning Boosted Asymmetric Classifiers for Object Detection
Object detection can be posted as those classification tasks where the rare positive patterns are to be distinguished from the enormous negative patterns. To avoid the danger of m...
Xinwen Hou, Cheng-Lin Liu, Tieniu Tan
CVPR
2006
IEEE
15 years 4 days ago
Multi-Resolution Patch Tensor for Facial Expression Hallucination
In this paper, we propose a sequential approach to hallucinate/synthesize high-resolution images of multiple facial expressions. We propose an idea of multi-resolution tensor for ...
Kui Jia, Shaogang Gong
CVPR
2006
IEEE
15 years 4 days ago
Hierarchical Volumetric Multi-view Stereo Reconstruction of Manifold Surfaces based on Dual Graph Embedding
This paper presents a new volumetric stereo algorithm to reconstruct the 3D shape of an arbitrary object. Our method is based on finding the minimum cut in an octahedral graph str...
Alexander Hornung, Leif Kobbelt