Motion information scalability is an important requirement for a fully scalable video codec, especially in low bit rate or small resolution decoding scenarios, for which the fully...
In this paper we explore the interlink between temporally dense view-based object recognition and sparse image representations with local keypoints. The temporal component is an a...
—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...
Video-based recognition and prediction of a temporally extended activity can benefit from a detailed description of high-level expectations about the activity. Stochastic grammars...
Many industrial real-time systems have evolved over a long period of time and were initially so simple that it was possible to predict consequences of adding new functionality by c...
Anders Wall, Johan Andersson, Jonas Neander, Chris...