Datasets are an integral part of contemporary object recognition research. They have been the chief reason for the considerable progress in the field, not just as source of large...
Abstract. The shape recognition of an object is important for dexterous manipulation by humans. Therefore, we have developed a haptic display that integrates both electrotactile an...
Katsunari Sato, Hideaki Nii, Naoki Kawakami, Susum...
In this paper we propose a system that annotates a user generated video based on the associated location metadata, by exploiting user-tagged image databases. An example of such a ...
We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden conditi...
Abstract. We propose an extension of the Restricted Boltzmann Machine (RBM) that allows the joint shape and appearance of foreground objects in cluttered images to be modeled indep...