Research Scientist offer on ‘Development of an end-to-end embedding of a CNN into a HMM for human action recognition’
The Centre for Robotics-MINES ParisTech is opening a short-term position for a research scientist on ‘Development of an end-to-end embedding of a CNN into a HMM‘, which is horizontal on various H2020 and industrial projects. The most recent advances of Convolutional Neural Networks (CNNs) in computer vision, have also shown promising results in human action recognition. Nevertheless, in most previous CNN-based approaches the stochasticity of the human movement, which can also be seen as a temporal evolution of video data, is not properly taken into account. The majority of the studies make use of a simple sliding window while evaluate the output as a per-frame overlap with the ground truth. Furthermore, very often CNNs are trained on a frame-level while only a very few datasets provide frame labels. In practice, this is very rarely the case, especially for real-time human action recognition in professional environments or other real-life data scenarios. Stochastic models, such as Hidden Markov Models (HMMs), manage well tasks where the inputs have a variable length. The objective of this short-term recent position is to model the emission probability of the HMM by an embedded CNN, which has more powerful image modelling capabilities than generative models such as Gaussian Mixture Models, in a bayesian framework.