A spoken language generation system has been developed that learns to describe objects in computer-generated visual scenes. The system is trained by a `show-and-tell' procedu...
Recognition of complex activities from surveillance video requires detection and temporal ordering of its constituent "atomic" events. It also requires the capacity to ro...
—We present in this paper an integrated solution to rapidly recognizing dynamic objects in surveillance videos by exploring various contextual information. This solution consists...
Xiaobai Liu, Liang Lin, Shuicheng Yan, Hai Jin, We...
In this paper we address the problem of estimating who is speaking from automatically extracted low resolution visual cues in group meetings. Traditionally, the task of speech/non...
— The environmental science and engineering communities are actively engaged in planning and developing the next generation of large-scale sensor-based observing systems. These s...
Sameer Tilak, Paul Hubbard, Matt Miller, Tony Foun...