In an attempt to improve models of human perception, the recognition of phonemes in nonsense utterances was predicted with automatic speech recognition (ASR) in order to analyze i...
In this paper we argue that gestures based on nonaccidental motion features can be reliably detected amongst unconstrained background motion. Specifically, we demonstrate that hu...
In this work we propose a model for video scenes that contain temporal variability in shape and appearance. We propose a conditionally linear model akin to a dynamic extension of ...
Human activity analysis is an important problem in computer
vision with applications in surveillance and summarization
and indexing of consumer content. Complex human
activities...
We consider the fully automated recognition of actions in uncontrolled environment. Most existing work relies on domain knowledge to construct complex handcrafted features from in...