The paper introduces a new framework for feature learning in classification motivated by information theory. We first systematically study the information structure and present a n...
Several spatiotemporal feature point detectors have been recently used in video analysis for action recognition. Feature points are detected using a number of measures, namely sali...
Konstantinos Rapantzikos, Stefanos D. Kollias, Yan...
This paper studies automatic segmentation of multiple
motions from tracked feature points through spectral embedding
and clustering of linear subspaces. We show that
the dimensi...
Mean shift is a popular method to segment images and videos. Pixels are represented by feature points, and the segmentation is driven by the point density in feature space. In thi...
In this paper, we propose a novel predictive model for
object boundary, which can integrate information from any
sources. The model is a dynamic “object” model whose
manifes...
Tian Shen (Lehigh University), Hongsheng Li (Lehig...