Action Localization with Tubelets from Motion

Mihir Jain, Jan van Gemert, Herve Jegou, Patrick Bouthemy, Cees G.M. Snoek; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 740-747


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.

Related Material

author = {Jain, Mihir and van Gemert, Jan and Jegou, Herve and Bouthemy, Patrick and Snoek, Cees G.M.},
title = {Action Localization with Tubelets from Motion},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2014}