This paper presents GeoS, a new algorithm for the efficient segmentation of n-dimensional image and video data. The segmentation problem is cast as approximate energy minimization ...
In this paper we are interested in the joint reconstruction of geometry and photometry of scenes with multiple moving objects from a collection of motion-blurred images. We make s...
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...
Abstract. Computer vision algorithms for individual tasks such as object recognition, detection and segmentation have shown impressive results in the recent past. The next challeng...
We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden conditi...