Modeling the Temporal Extent of Actions

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. Frame 1 Frame 127 cropped training video full training video Frame 45 Frame 53

• Type: Journal
• Year: 2010
• Where: ECCV
• Authors: Scott Satkin, Martial Hebert
• Keywords: Action Recognition, Computer Vision, ECCV 2010, State-of-the-art Action Recognition, Training Video