Sciweavers

CVPR
2012
IEEE
13 years 7 months ago
We are not contortionists: Coupled adaptive learning for head and body orientation estimation in surveillance video
In this paper, we deal with the estimation of body and head poses (i.e orientations) in surveillance videos, and we make three main contributions. First, we address this issue as ...
Cheng Chen, Jean-Marc Odobez
CVPR
2012
IEEE
13 years 7 months ago
Learning object class detectors from weakly annotated video
Object detectors are typically trained on a large set of still images annotated by bounding-boxes. This paper introduces an approach for learning object detectors from realworld w...
Alessandro Prest, Christian Leistner, Javier Civer...
CVPR
2012
IEEE
13 years 7 months ago
Incremental gradient on the Grassmannian for online foreground and background separation in subsampled video
It has recently been shown that only a small number of samples from a low-rank matrix are necessary to reconstruct the entire matrix. We bring this to bear on computer vision prob...
Jun He, Laura Balzano, Arthur Szlam
CVPR
2012
IEEE
13 years 7 months ago
Leveraging stereopsis for saliency analysis
Stereopsis provides an additional depth cue and plays an important role in the human vision system. This paper explores stereopsis for saliency analysis and presents two approache...
Yuzhen Niu, Yujie Geng, Xueqing Li, Feng Liu
CVPR
2012
IEEE
13 years 7 months ago
Pose pooling kernels for sub-category recognition
The ability to normalize pose based on super-category landmarks can significantly improve models of individual categories when training data are limited. Previous methods have co...
Ning Zhang, Ryan Farrell, Trevor Darrell
CVPR
2012
IEEE
13 years 7 months ago
2.5D building modeling by discovering global regularities
We introduce global regularities in the 2.5D building modeling problem, to reflect the orientation and placement similarities between planar elements in building structures. Give...
Qian-Yi Zhou, Ulrich Neumann
CVPR
2012
IEEE
13 years 7 months ago
Higher order motion models and spectral clustering
Motion segmentation based on point trajectories can integrate information of a whole video shot to detect and separate moving objects. Commonly, similarities are defined between ...
Peter Ochs, Thomas Brox
CVPR
2012
IEEE
13 years 7 months ago
Learning shared body plans
We cast the problem of recognizing related categories as a unified learning and structured prediction problem with shared body plans. When provided with detailed annotations of o...
Ian Endres, Vivek Srikumar, Ming-Wei Chang, Derek ...
CVPR
2012
IEEE
13 years 7 months ago
Classifying covert photographs
The advances in image acquisition techniques make recording images never easier and brings a great convenience to our daily life. It raises at the same time the issue of privacy p...
Haitao Lang, Haibin Ling
CVPR
2012
IEEE
13 years 7 months ago
Color constancy using faces
In this work, we investigate how illuminant estimation can be performed exploiting the color statistics extracted from the faces automatically detected in the image. The proposed ...
Simone Bianco, Raimondo Schettini