PhD Defence | Aspects of Time for Recognizing Human Activities

University of Amsterdam PhD candidate, Nour Hussein will be defending his PhD thesis Aspects of Time for Recognizing Human Activities on Friday 9th April.

Hussein completed his research under the supervision of Arnold Smeulders and Efstratios Gavves (both from UvA).

This thesis contributes to the literature of understanding and recognizing human activities in videos. More specifically, the thesis draw line between short-range atomic actions and long-range complex activities. For the classification of the latter, the mainstream approach in literature is to divide the activity into a handful of short segments, called atomic actions. Then, a neural model, such as 3D CNN, is trained to represent and classify each segment independently. Then, the activity-level classification probability scores are obtained by pooling over that of the segments. Differently, this work argues that long-range activities are better classified in full. That is to say, the neural model has to reason about the long-range activity, all at once, to better recognize it. Based on this argument, the thesis proposes different methods and neural network models for recognizing these complex activities.