Automatic Casting from Videos Using Deep Convolutional Neural Networks
In automatic casting applications, the aim is to accurately recognise facial regions that correspond to a same actor appearing in a movie to produce described video. In particular, this project will focus on challenging tasks of capturing and modeling the facial trajectory for each person appearing in a movie in order to predict when/where the principal actors appear. This is a challenging task because recent movies are typically high quality and faces are often occluded and their appearance varies significantly according to pose, illumination, blur, etc. The first objective of this project is to analyse and evaluate the state-of-the-art algorithms that are suitable for accurate detection and tracking faces in high resolution movies for fast automatic casting. Given the facial trajectories captured in a movie, the second objective is to investigate methods for learning or adapting predictive models to detect the principal actors in a film.