Modeling the Temporal Extent of Actions - Robotics Institute Carnegie Mellon University

Modeling the Temporal Extent of Actions

Conference Paper, Proceedings of (ECCV) European Conference on Computer Vision, pp. 536 - 548, September, 2010

Abstract

In this paper, we present a framework for estimating what portions of videos are most discriminative for the task of action recognition. We explore the impact of the temporal cropping of training videos on the overall accuracy of an action recognition system, and we formalize what makes a set of croppings optimal. In addition, we present an algorithm to determine the best set of croppings for a dataset, and experimentally show that our approach increases the accuracy of various state-of-the-art action recognition techniques.

BibTeX

@conference{Satkin-2010-10524,
author = {Scott Satkin and Martial Hebert},
title = {Modeling the Temporal Extent of Actions},
booktitle = {Proceedings of (ECCV) European Conference on Computer Vision},
year = {2010},
month = {September},
pages = {536 - 548},
}