The popular bag-of-words paradigm for action recognition tasks is based on building histograms of quantized features, typically at the cost of discarding all information about rela...
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...
The Air Force has enthusiastically endorsed, at its most senior levels, advanced thinking with regard to the application of information technology. Recently, the notion of a Joint...
Abstract. Most cognitive studies of language acquisition in both natural systems and artificial systems have focused on the role of purely linguistic information as the central co...
Action recognition is a popular and important research topic in computer vision. However, it is challenging when facing viewpoint variance. So far, most researches in action recogn...