228
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
Depth ordering is instrumental for understanding the 3D geometry of an image. We as humans are surprisingly good ordering even with abstract 2D line drawings. In this paper we pro...
177
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
Objects in scenes interact with each other in complex ways. A key observation is that these interactions manifest themselves as predictable visual patterns in the image. Discoveri...
152
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
This paper presents a method for the detection and recognition of social interactions in a day-long first-person video of a social event, like a trip to an amusement park. The lo...
171
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
A large number of vision applications rely on matching keypoints across images. The last decade featured an arms-race towards faster and more robust keypoints and association algo...
167
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
Camera spectral sensitivity plays an important role for various color-based computer vision tasks. Although several methods have been proposed to estimate it, their applicability ...
154
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
We focus on the detection of orthogonal vanishing points using line segments extracted from a single view, and using these for camera self-calibration. Recent methods view this pr...
130
Voted
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
This paper proposes a content-aware image resizing method which simultaneously preserves both salient image features and important line structure properties: parallelism, collinea...
181
Voted
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
We couple occlusion modeling and multi-frame motion estimation to compute dense, temporally extended point trajectories in video with significant occlusions. Our approach combine...
205
click to vote
CVPR
2012
IEEE
13 years 7 months ago
2012
IEEE
In this paper, we present a novel approach for human action recognition with histograms of 3D joint locations (HOJ3D) as a compact representation of postures. We extract the 3D sk...