We propose a novel learning algorithm to detect moving pedestrians from a stationary camera in real-time. The algorithm learns a discriminative model based on eigenflow, i.e. the ...
We present an algorithm for producing behavior descriptions of planar fixed axes mechanical motions from image sequences using a formal behavior language. The language, which cove...
An adaptive spatiotemporal saliency algorithm for video attention detection using motion vector decision is proposed, motivated by the importance of motion information in video se...
Yaping Zhu, Natan Jacobson, Hong Pan, Truong Q. Ng...
We present a novel geometrical constraint on the egomotion of a single, moving camera. Using a camera with a large field-of-view (FOV), the optical flow measured at a single pair ...
Abstract. In this pilot study, a neural architecture for temporal emotion recognition from image sequences is proposed. The investigation aims at the development of key principles ...