We introduce ViDaS, a two-stream, fully convolutional Video, Depth-Aware...
In this paper we present an integrated robotic system capable of
partici...
We present a novel multi-attentional convolutional architecture to tackl...
We introduce STAViS, a spatio-temporal audiovisual saliency network that...
Detecting visual relationships, i.e. <Subject, Predicate, Object> triple...
In this paper we address the problem of multi-cue affect recognition in
...
In this work we propose a multi-task spatio-temporal network, called SUS...
In this work we tackle the problem of child engagement estimation while
...
In this work we present a novel Long Short Term Memory (LSTM) based on-l...
Despite the availability of a huge amount of video data accompanied by
d...