Sciweavers

CVPR
2012
IEEE
11 years 7 months ago
The scale of edges
Although the scale of isotropic visual elements such as blobs and interest points, e.g. SIFT[12], has been well studied and adopted in various applications, how to determine the s...
Xianming Liu, Changhu Wang, Hongxun Yao, Lei Zhang
CVPR
2012
IEEE
11 years 7 months ago
Example-based 3D object reconstruction from line drawings
Recovering 3D geometry from a single 2D line drawing is an important and challenging problem in computer vision. It has wide applications in interactive 3D modeling from images, c...
Tianfan Xue, Jianzhuang Liu, Xiaoou Tang
CVPR
2012
IEEE
11 years 7 months ago
Discrete texture traces: Topological representation of geometric context
Modeling representations of image patches that are quasi-invariant to spatial deformations is an important problem in computer vision. In this paper, we propose a novel concept, t...
Jan Ernst, Maneesh Kumar Singh, Visvanathan Ramesh
CVPR
2012
IEEE
11 years 7 months ago
Manifold-based fingerprinting for target identification
In this paper, we propose a fingerprint analysis algorithm based on using product manifolds to create robust signatures for individual targets in motion imagery. The purpose of ta...
Kang-Yu Ni, Terrell N. Mundhenk, Kyungnam Kim, Yur...
CVPR
2012
IEEE
11 years 7 months ago
Depth from optical turbulence
Turbulence near hot surfaces such as desert terrains and roads during the summer, causes shimmering, distortion and blurring in images. While recent works have focused on image re...
Yuandong Tian, Srinivasa G. Narasimhan, Alan J. Va...
CVPR
2012
IEEE
11 years 7 months ago
A learning-based framework for depth ordering
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...
Zhaoyin Jia, Andrew C. Gallagher, Yao-Jen Chang, T...
CVPR
2012
IEEE
11 years 7 months ago
Automatic discovery of groups of objects for scene understanding
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...
Congcong Li, Devi Parikh, Tsuhan Chen
CVPR
2012
IEEE
11 years 7 months ago
Social interactions: A first-person perspective
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...
Alireza Fathi, Jessica K. Hodgins, James M. Rehg
CVPR
2012
IEEE
11 years 7 months ago
FREAK: Fast Retina Keypoint
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...
Alexandre Alahi, Raphael Ortiz, Pierre Vandergheyn...