We present a new scheme to robustly detect a type of human attentive behavior, which we call frequent change in focus of attention (FCFA), from video sequences. FCFA behavior can b...
Web lectures are a form of educational content that differs from classic hypertext in a number of ways. Web lectures are easier to produce and therefore large amounts of material ...
Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task a...
In this paper we propose a novel appearance descriptor for 3D human pose estimation from monocular images using a learning-based technique. Our image-descriptor is based on the int...
—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...