Sciweavers

86
Voted
ICCV
2009
IEEE
2205views Computer Vision» more  ICCV 2009»
16 years 4 months ago
Video stabilization using robust feature trajectories
This paper proposes a new approach for video stabilization. Most existing video stabilization methods adopt a framework of three steps, motion estimation, motion compensation an...
Ken-Yi Lee, Yung-Yu, Chuang Bing-Yu, Chen Ming Ouh...
87
Voted
ICCV
2009
IEEE
16 years 4 months ago
Tracking in Unstructured Crowded Scenes
This paper presents a target tracking framework for unstructured crowded scenes. Unstructured crowded scenes are defined as those scenes where the motion of a crowd appears to b...
Mikel Rodriguez, Saad Ali, Takeo Kanade
ICCV
2009
IEEE
16 years 4 months ago
Learning Pedestrian Dynamics from the Real World
In this paper we describe a method to learn parameters which govern pedestrian motion by observing video data. Our learning framework is based on variational mode learning and a...
Paul Scovanner, Marshall Tappen
76
Voted
ICCV
2009
IEEE
16 years 4 months ago
A linear formulation of shape from specular flow
When a curved mirror-like surface moves relative to its environment, it induces a motion field—or specular flow— on the image plane that observes it. This specular flow is r...
Guillermo D. Canas, Yuriy Vasilyev, Yair Adato, To...
ICCV
2009
IEEE
1038views Computer Vision» more  ICCV 2009»
16 years 4 months ago
Combining efficient object localization and image classification
In this paper we present a combined approach for ob- ject localization and classification. Our contribution is two- fold. (a) A contextual combination of localization and clas- ...
Hedi Harzallah, Frederic Jurie, Cordelia Schmid
ICCV
2009
IEEE
1176views Computer Vision» more  ICCV 2009»
16 years 4 months ago
Building Rome in a Day
We present a system that can match and reconstruct 3D scenes from extremely large collections of photographs such as those found by searching for a given city (e.g., Rome) on In...
Sameer Agarwal, Noah Snavely, Ian Simon, Steven M....
80
Voted
ICCV
2009
IEEE
16 years 4 months ago
Boundary Ownership by Lifting to 2.5D
This paper addresses the “boundary ownership” problem, also known as the figure/ground assignment problem. Estimating boundary ownerships is a key step in perceptual organiz...
Ido Leichter and Michael Lindenbaum
76
Voted
ICCV
2009
IEEE
1042views Computer Vision» more  ICCV 2009»
16 years 4 months ago
Activity Recognition using the velocity histories of tracked keypoints
We present an activity recognition feature inspired by human psychophysical performance. This feature is based on the velocity history of tracked keypoints. We present a generat...
Ross Messing, Chris Pal, Henry Kautz
75
Voted
ICCV
2009
IEEE
16 years 4 months ago
Super-Resolution from a Single Image
Methods for super-resolution can be broadly classified into two families of methods: (i) The classical multi-image super-resolution (combining images obtained at subpixel misali...
Daniel Glasner, Shai Bagon, Michal Irani
ICCV
2009
IEEE
1419views Computer Vision» more  ICCV 2009»
16 years 4 months ago
On Feature Combination for Multiclass Object Classification
A key ingredient in the design of visual object classification systems is the identification of relevant class specific aspects while being robust to intra-class variations. Whil...
Peter Gehler, Sebastian Nowozin