Abstract. In this paper, we propose a novel approach for action classification in soccer videos using a recurrent neural network scheme. Thereby, we extract from each video action ...
Moez Baccouche, Franck Mamalet, Christian Wolf, Ch...
This paper presents an approach to reconstruct nonstationary, articulated objects from silhouettes obtained with a monocular video sequence. We introduce the concept of motion blu...
A novel video object segmentation method is proposed which aims at combining color and motion information. The model has a multilayer structure: Each feature has its own layer, cal...
We propose an efficient orthonormal wavelet-domain video denoising algorithm based on an appropriate integration of motion compensation into an adapted version of our recently devi...
The complexity of dynamical laws governing 3D atmospheric flows associated to incomplete and noisy observations makes very difficult the recovery of atmospheric dynamics from sate...