Sciweavers

7596 search results - page 339 / 1520
» Challenges in forensic computing
Sort
View
CVPR
2005
IEEE
16 years 7 months ago
Modelling Dynamic Scenes by Registering Multi-View Image Sequences
In this paper, we present a new variational method for multi-view stereovision and non-rigid three-dimensional motion estimation from multiple video sequences. Our method minimize...
Jean-Philippe Pons, Renaud Keriven, Olivier D. Fau...
ICCV
2007
IEEE
16 years 7 months ago
Rotational Motion Deblurring of a Rigid Object from a Single Image
Most previous motion deblurring methods restore the degraded image assuming a shift-invariant linear blur filter. These methods are not applicable if the blur is caused by spatial...
Qi Shan, Wei Xiong, Jiaya Jia
ICCV
2005
IEEE
16 years 7 months ago
Discontinuity Preserving Stereo with Small Baseline Multi-Flash Illumination
Currently, sharp discontinuities in depth and partial occlusions in multiview imaging systems pose serious challenges for many dense correspondence algorithms. However, it is impo...
Rogerio Feris, Ramesh Raskar, Longbin Chen, Kar-Ha...
155
Voted
ECCV
2008
Springer
16 years 7 months ago
Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks
Abstract. Building visual recognition models that adapt across different domains is a challenging task for computer vision. While feature-learning machines in the form of hierarchi...
Amr Ahmed, Kai Yu, Wei Xu, Yihong Gong, Eric P. Xi...
CHI
2009
ACM
16 years 5 months ago
Critical methods and user generated content: the iPhone on YouTube
Sites like YouTube offer vast sources of data for studies of Human Computer Interaction (HCI). However, they also present a number of methodological challenges. This paper offers ...
Mark Blythe, Paul A. Cairns