Generative models can be used for a wide range of tasks, and have the appealing ability to
learn from both labelled and unlabelled data. In contrast, discriminative models cannot learn …

Video (used as a form of examination or homework) as an efficient approach for examining
students' abilities is drawing increasing attention in the education field. How to assess video …

We propose a new approach to Human Action Evaluation (HAE) in long videos using graph-
based multi-task modeling. Previous works in activity assessment either directly compute a …

Human action recognition is a hot topic and it has been applied to various fields. Deep
learning is one of the techniques in human action recognition which has achieved good …

Gesture recognition is a much studied research area which has myriad real-world
applications including robotics and human-machine interaction. Current gesture recognition …

Neural Memory Networks (NMNs) have received increased attention in recent years
compared to deep architectures that use a constrained memory. Despite their new appeal …

With increasingly high interest in assistive robots and smart surveillance systems, we need a
powerful perception mechanism to be able to describe the events in a scene. However …