Action localization with tubelets from motion - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Action localization with tubelets from motion

Abstract

This paper considers the problem of action localization, where the objective is to determine when and where certain actions appear. We introduce a sampling strategy to produce 2D+t sequences of bounding boxes, called tubelets. Compared to state-of-the-art alternatives, this drastically reduces the number of hypotheses that are likely to include the action of interest. Our method is inspired by a recent technique introduced in the context of image localization. Beyond considering this technique for the first time for videos, we revisit this strategy for 2D+t sequences obtained from super-voxels. Our sampling strategy advantageously exploits a criterion that reflects how action related motion deviates from background motion. We demonstrate the interest of our approach by extensive experiments on two public datasets: UCF Sports and MSR-II. 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.
Fichier principal
Vignette du fichier
jain_cvpr2014_tubelets.pdf (1.09 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00996844 , version 1 (27-05-2014)

Identifiers

  • HAL Id : hal-00996844 , version 1

Cite

Mihir Jain, Jan van Gemert, Hervé Jégou, Patrick Bouthemy, Cees Snoek. Action localization with tubelets from motion. CVPR - International Conference on Computer Vision and Pattern Recognition, Jun 2014, Columbus, United States. ⟨hal-00996844⟩
2172 View
606 Download

Share

Gmail Facebook X LinkedIn More