Advanced School for Computing and Imaging (ASCI)

ASCI office
Delft University of Technology
Building 28, room 04.E120
Van Mourik Broekmanweg 6
2628 XE – DELFT, The Netherlands

P: +31 15 27 88032

Visiting hours office
Monday, Tuesday, Thursday: 10:00 – 15:00


The ASCI office is located at the Delft University of Technology campus.  It is easily accessible by bicycle, public transport and car. The numbers of buildings can help you find your way around the campus. Make sure you remember the name and building number of your destination.

Contact us at +31 15 278 8032 or send us an email at

Aspects of Time for Recognizing Human Activities

Aspects of Time for Recognizing Human Activities

Author : Noureldien Hussein
Promotor(s) : Prof. dr. ir. A.W.M. Smeulders / Dr. E. Gavves
University : Universiteit van Amsterdam
Year of publication : 2019
Link to repository : link to thesis


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 the 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 .