Sciweavers

CVPR
2011
IEEE
12 years 8 months ago
Who are you with and where are you Going?
We propose an agent-based behavioral model of pedestrians to improve tracking performance in realistic scenarios. In this model, we view pedestrians as decision-making agents who ...
Kota Yamaguchi, Alexander Berg, Luis Ortiz, Tamara...
CVPR
2011
IEEE
12 years 8 months ago
Blur kernel estimation using the Radon Transform
Camera shake is a common source of degradation in photographs. Restoring blurred pictures is challenging because both the blur kernel and the sharp image are unknown, which makes ...
Taeg Sang Cho, Sylvain Paris, Bill Freeman, Bertho...
CVPR
2011
IEEE
12 years 8 months ago
Max-margin Clustering: Detecting Margins from Projections of Points on Lines
Given a unlabelled set of points X ∈ RN belonging to k groups, we propose a method to identify cluster assignments that provides maximum separating margin among the clusters. We...
Raghuraman Gopalan, Jagan Sankaranarayanan
CVPR
2011
IEEE
12 years 8 months ago
An Associate-Predict Model for Face Recognition
Handling intra-personal variation is a major challenge in face recognition. It is difficult how to appropriately measure the similarity between human faces under significantly di...
Qi Yin, Jian Sun, Xiaoou Tang
CVPR
2011
IEEE
12 years 8 months ago
Connecting Non-Quadratic Variational Models and MRFs
Spatially-discrete Markov random fields (MRFs) and spatially-continuous variational approaches are ubiquitous in low-level vision, including image restoration, segmentation, opti...
Kevin Schelten, Stefan Roth
CVPR
2011
IEEE
12 years 8 months ago
Tag Localization with Spatial Correlations and Joint Group Sparsity
Nowadays numerous social images have been emerging on the Web. How to precisely label these images is critical to image retrieval. However, traditional image-level tagging methods...
Yang Yang, Yi Yang, Zi Huang, Heng Tao Shen, Feipi...
CVPR
2011
IEEE
12 years 8 months ago
Line-Based Relative Pose Estimation
We present an algorithm for calibrated camera relative pose estimation from lines. Given three lines with two of the lines parallel and orthogonal to the third we can compute the ...
Ali Elqursh, Ahmed Elgammal
CVPR
2011
IEEE
12 years 8 months ago
Supervised Hypergraph Labeling
We address the problem of labeling individual datapoints given some knowledge about (small) subsets or groups of them. The knowledge we have for a group is the likelihood value fo...
Toufiq Parag, Ahmed Elgammal
CVPR
2011
IEEE
12 years 8 months ago
Projective Alignment of Range and Parallax Data
An approximately Euclidean representation of the visible scene can be obtained directly from a range, or ‘time-offlight’, camera. An uncalibrated binocular system, in contras...
Miles Hansard, Radu Horaud, Michel Amat, Seungkyu ...
CVPR
2011
IEEE
12 years 8 months ago
Learning-based Hypothesis Fusion for Robust Catheter Tracking in 2D X-ray Fluoroscopy
Catheter tracking has become more and more important in recent interventional applications. It provides real time guidance for the physicians and can be used as motion compensated...
Wen Wu, Terrence Chen, Adrian Barbu, Peng Wang, No...