| Summary: | <p>We propose a novel <em>human-centric</em> approach to <em>detect and localize</em> human actions in <em>challenging</em> video data, such as Hollywood movies. Our goal is to localize actions in time through the video and spatially in each frame. We achieve this by first obtaining generic spatio-temporal human tracks and then detecting specific actions within these using a sliding window classifier.</p>
<br>
<p>We make the following contributions: (i) We show that splitting the action localization task into spatial and temporal search leads to an efficient localization algorithm where generic human tracks can be reused to recognize multiple human actions; (ii) We develop a human detector and tracker which is able to cope with a wide range of postures, articulations, motions and camera viewpoints. The tracker includes detection interpolation and a principled classification stage to suppress false positive tracks; (iii) We propose a track-aligned 3D-HOG action representation, investigate its parameters, and show that action localization benefits from using tracks; and (iv) We introduce a new action localization dataset based on Hollywood movies.</p>
<br>
<p>Results are presented on a number of <em>real-world</em> movies with crowded, dynamic environment, partial occlusion and cluttered background. On the Coffee&Cigarettes dataset we significantly improve over the state of the art. Furthermore, we obtain excellent results on the new <em>Hollywood–Localization</em> dataset.</p>
|
|---|