Sciweavers

CVPR
2011
IEEE
13 years 7 months ago
Cross-View Action Recognition via View Knowledge Transfer
In this paper, we present a novel approach to recognizing human actions from different views by view knowledge transfer. An action is originally modelled as a bag of visual-words ...
Jingen Liu
CVPR
2011
IEEE
13 years 7 months ago
Truncated Message Passing
Training of conditional random fields often takes the form of a double-loop procedure with message-passing inference in the inner loop. This can be very expensive, as the need to...
Justin Domke
CVPR
2011
IEEE
13 years 7 months ago
Optimal Similarity Registration of Volumetric Images
Effrosyni Kokiopoulou, Michail Zervos, Daniel Kres...
CVPR
2011
IEEE
13 years 7 months ago
Adapting an Object Detector by Considering the Worst Case: a Conservative Approach
The performance of an offline-trained classifier can be improved on-site by adapting the classifier towards newly acquired data. However, the adaptation rate is a tuning parame...
Guang Chen, TonyX. Han
CVPR
2011
IEEE
13 years 7 months ago
Combining Randomization and Discrimination for Fine-Grained Image Categorization
In this paper, we study the problem of fine-grained image categorization. The goal of our method is to explore fine image statistics and identify the discriminative image patche...
Bangpeng Yao, Aditya Khosla, Li Fei-Fei
CVPR
2011
IEEE
13 years 7 months ago
Fast Cost-Volume Filtering for Visual Correspondence and Beyond
Many computer vision tasks can be formulated as labeling problems. The desired solution is often a spatially smooth labeling where label transitions are aligned with color edges o...
Christoph Rhemann, Asmaa Hosni, Michael Bleyer, Ca...
CVPR
2011
IEEE
13 years 7 months ago
High-quality shape from multi-view stereo and shading under general illumination
Multi-view stereo methods reconstruct 3D geometry from images well for sufficiently textured scenes, but often fail to recover high-frequency surface detail, particularly for smo...
Chenglei Wu, Bennett Wilburn, Yasuyuki Matsushita,...
CVPR
2011
IEEE
13 years 7 months ago
Robust Sparse Coding for Face Recognition
Recently the sparse representation (or coding) based classification (SRC) has been successfully used in face recognition. In SRC, the testing image is represented as a sparse lin...
Meng Yang, Lei Zhang
CVPR
2011
IEEE
13 years 7 months ago
Clues from the Beaten Path: Location Estimation with Bursty Sequences of Tourist Photos
Image-based location estimation methods typically recognize every photo independently, and their resulting reliance on strong visual feature matches makes them most suited for dis...
Chao-Yeh Chen, Kristen Grauman
CVPR
2011
IEEE
13 years 7 months ago
A Polar Representation of Motion and Implications for Optical Flow
We explore a polar representation of optical flow in which each element of the brightness motion field is represented by its magnitude and orientation instead of its Cartesian p...
Yair Adato, Todd Zickler, Ohad Ben-Shahar