Video scene parsing is challenging due to the following two reasons: firstly, it is non-trivial to
learn meaningful video representations for producing the temporally consistent labeling …

Predicting the future is an important aspect for decision-making in robotics or autonomous
driving systems, which heavily rely upon visual scene understanding. While prior work …

In this work, we study a poorly understood trade-off between accuracy and runtime costs for
deep semantic video segmentation. While recent work has demonstrated advantages of …

In order to protect a server to become overloading due to concentration of accesses, a mirror
server system is widely used for distributing the load to multiservers. For such a system, it is …

Advances in wireless and sensing technology and the proliferation of context-aware systems
have highlighted the requirement to reduce the complexity of system development by …