P
Patrick Bouthemy
Researcher at French Institute for Research in Computer Science and Automation
Publications - 190
Citations - 7888
Patrick Bouthemy is an academic researcher from French Institute for Research in Computer Science and Automation. The author has contributed to research in topics: Motion estimation & Image segmentation. The author has an hindex of 41, co-authored 189 publications receiving 7619 citations. Previous affiliations of Patrick Bouthemy include Institut de Recherche en Informatique et Systèmes Aléatoires.
Papers
More filters
Journal ArticleDOI
Robust multiresolution estimation of parametric motion models
TL;DR: Numerical results support this approach, as validated by the use of these algorithms on complex sequences, and two robust estimators in a multi-resolution framework are developed.
Proceedings ArticleDOI
Better Exploiting Motion for Better Action Recognition
TL;DR: It is established that adequately decomposing visual motion into dominant and residual motions, both in the extraction of the space-time trajectories and for the computation of descriptors, significantly improves action recognition algorithms.
Journal ArticleDOI
Optical flow modeling and computation
TL;DR: A survey of optical flow estimation classifying the main principles elaborated during this evolution, with a particular concern given to recent developments is proposed.
Journal ArticleDOI
Multimodal estimation of discontinuous optical flow using Markov random fields
Fabrice Heitz,Patrick Bouthemy +1 more
TL;DR: It is shown that multiple constraints can provide more accurate flow estimation in a wide range of circumstances and is presented a multimodal approach to the problem of motion estimation in which the computation of visual motion is based on several complementary constraints.
Proceedings ArticleDOI
Action Localization with Tubelets from Motion
TL;DR: This paper introduces a sampling strategy to produce 2D+t sequences of bounding boxes, called tubelets, that significantly outperforms the state-of-the-art on both datasets, while restricting the search of actions to a fraction of possible bounding box sequences.