Max-Margin Early Event Detectors - Robotics Institute Carnegie Mellon University

Max-Margin Early Event Detectors

M. H. Nguyen and F. De la Torre
Journal Article, International Journal of Computer Vision, Vol. 107, No. 2, pp. 191 - 202, April, 2014

Abstract

The need for early detection of temporal events from sequential data arises in a wide spectrum of applications ranging from human-robot interaction to video security. While temporal event detection has been extensively studied, early detection is a relatively unexplored problem. This paper proposes a maximum-margin framework for training temporal event detectors to recognize partial events, enabling early detection. Our method is based on Structured Output SVM, but extends it to accommodate sequential data. Experiments on datasets of varying complexity, for detecting facial expressions, hand gestures, and human activities, demonstrate the benefits of our approach.

BibTeX

@article{Nguyen-2014-120724,
author = {M. H. Nguyen and F. De la Torre},
title = {Max-Margin Early Event Detectors},
journal = {International Journal of Computer Vision},
year = {2014},
month = {April},
volume = {107},
number = {2},
pages = {191 - 202},
}