Chapter Seven: Action recognition in egocentric video
Abstract
In this chapter, we address recognition and localization of single as well as multiple actions from egocentric video. We propose two solutions to this problem. As the first solution, we apply random walks to recognize single action. In a more comprehensive second solution, we propose a superpixel level weakly supervised graph-theoretic framework for joint localization, recognition, and summarization of actions. Here, we recognize and localize single as well as multiple action(s) in each frame of an egocentric video, and construct a summary of these detected actions. The superpixel level solution helps in precise localization of actions in addition to improving the recognition accuracy. ...
Get Graph Based Multimedia Analysis now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
