We present a distributed representation of pose and appearance of people called the “poselet activation vector”. First we show that this representation can be used to estimate...
This paper presents a novel method for facial expression classification that employs the combination of two different feature sets in an ensemble approach. A pool of base classi...
Thiago H. H. Zavaschi, Alessandro L. Koerich, Luiz...
It has always been very difficult to recognize realistic actions from unconstrained videos because there are tremendous variations from camera motion, background clutter, object a...
In this paper, we consider the problem of speaker verification as a two-class object detection problem in computer vision, where the object instances are 1-D short-time spectral v...
We propose a dense local region detector to extract features suitable for image matching and object recognition tasks. Whereas traditional local interest operators rely on repeata...