Multi-stream hidden Markov models (HMMs) have recently been very successful in audio-visual speech recognition, where the audio and visual streams are fused at the final decision...
Abstract-- Automatic recognition of activities using time series data collected from exercise can facilitate development of applications that motivate people to exercise more frequ...
Pekka Siirtola, Perttu Laurinen, Eija Haapalainen,...
In the real visual world, the number of categories a classifier needs to discriminate is on the order of hundreds or thousands. For example, the SUN dataset [24] contains 899 sce...
Advances in computer processing power and emerging algorithms are allowing new ways of envisioning Human Computer Interaction. This paper focuses on the development of a computing...
Zhihong Zeng, Jilin Tu, Brian Pianfetti, Ming Liu,...
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...