Abstract. This paper presents a novel approach to sign language recognition that provides extremely high classification rates on minimal training data. Key to this approach is a 2 ...
Richard Bowden, David Windridge, Timor Kadir, Andr...
Representation and measurement are two important issues for saliency models. Different with previous works that learnt sparse features from large scale natural statistics, we prop...
Xiaoshuai Sun, Hongxun Yao, Rongrong Ji, Pengfei X...
We propose and investigate a paradigm for activity recognition, distinguishing the ‘on-going activity’ recognition task (OGA) from that addressing ‘complete activities’ (C...
Bruno Lepri, Nadia Mana, Alessandro Cappelletti, F...
In this paper, computer vision and fuzzy set theory are merged for the robust construction of three-dimensional objects using a small number of cameras and minimal a priori knowled...
Derek Anderson, Robert H. Luke III, Erik E. Stone,...
In knowledge discovery applications, where new features are to be added, an acquisition policy can help select the features to be acquired based on their relevance and the cost of...