Sciweavers

ECCV
2010
Springer
14 years 23 days ago
Towards Computational Models of Visual Aesthetic Appeal of Consumer Videos
In this paper, we tackle the problem of characterizing the aesthetic appeal of consumer videos and automatically classifying them into high or low aesthetic appeal. First, we condu...
ACCV
2009
Springer
14 years 23 days ago
Person De-identification in Videos
Advances in cameras and web technology have made it easy to capture and share large amounts of video data over to a large number of people. A large number of cameras oversee public...
Prachi Agrawal, P. J. Narayanan
ACCV
2009
Springer
14 years 23 days ago
Adaptive-Scale Robust Estimator Using Distribution Model Fitting
We propose a new robust estimator for parameter estimation in highly noisy data with multiple structures and without prior information on the noise scale of inliers. This is a diag...
Trung Ngo Thanh, Hajime Nagahara, Ryusuke Sagawa, ...
ECCV
2010
Springer
14 years 23 days ago
Object of Interest Detection by Saliency Learning
In this paper, we present a method for object of interest detection. This method is statistical in nature and hinges in a model which combines salient features using a mixture of l...
ECCV
2010
Springer
14 years 23 days ago
Self-Adapting Feature Layers
Abstract. This paper presents a new approach for fitting a 3D morphable model to images of faces, using self-adapting feature layers (SAFL). The algorithm integrates feature detect...
ECCV
2010
Springer
14 years 23 days ago
Image Invariants for Smooth Reflective Surfaces
Image invariants are those properties of the images of an object that remain unchanged with change in camera parameters, illumination etc. In this paper, we derive an image invari...
ECCV
2010
Springer
14 years 23 days ago
Conjugate Gradient Bundle Adjustment
Abstract. Bundle adjustment for multi-view reconstruction is traditionally done using the Levenberg-Marquardt algorithm with a direct linear solver, which is computationally very e...
CVPR
2010
IEEE
14 years 23 days ago
The Phase Only Transform for unsupervised surface defect detection
We present a simple, fast, and effective method to detect defects on textured surfaces. Our method is unsupervised and contains no learning stage or information on the texture bei...
Dror Aiger, Hugues Talbot
CVPR
2010
IEEE
14 years 23 days ago
Player Localization Using Multiple Static Cameras for Sports Visualization
We present a novel approach for robust localization of multiple people observed using multiple cameras. We use this location information to generate sports visualizations, which i...
Raffay Hamid, Ramkrishan Kumar, Matthias Grundmann...
VISAPP
2007
14 years 24 days ago
Simultaneous robust fitting of multiple curves
In this paper, we address the problem of robustly recovering several instances of a curve model from a single noisy data set with outliers. Using M-estimators revisited in a Lagran...
Jean-Philippe Tarel, Pierre Charbonnier, Sio-Song ...