Search Results for author:
Found 7 papers, 1 papers with code
EM-driven unsupervised learning for efficient motion segmentation
The core idea of our work is to leverage the Expectation-Maximization (EM) framework in order to design in a well-founded manner a loss function and a training procedure of our motion segmentation neural network that does not require either ground-truth or manual annotation.
Learning how to be robust: Deep polynomial regression
We bypass the need for a tailored loss function on the regression parameters by attaching to our model a differentiable hard-wired decoder corresponding to the polynomial operation at hand.
Tubelets: Unsupervised action proposals from spatiotemporal super-voxels
First, inspired by selective search for object proposals, we introduce an approach to generate action proposals from spatiotemporal super-voxels in an unsupervised manner, we call them Tubelets.
Determining Occlusions From Space and Time Image Reconstructions
With this in mind, we propose a novel approach to occlusion detection where visibility or not of a point in next frame is formulated in terms of visual reconstruction.
Aggregation of local parametric candidates with exemplar-based occlusion handling for optical flow
The idea is to supply local motion candidates at every pixel in a first step, and then to combine them to determine the global optical flow field in a second step.
Action Localization with Tubelets from Motion
Our approach significantly outperforms the state-of-the-art on both datasets, while restricting the search of actions to a fraction of possible bounding box sequences.
Better Exploiting Motion for Better Action Recognition
Several recent works on action recognition have attested the importance of explicitly integrating motion characteristics in the video description.
