Exploring Deep Learning Architectures for Automatic Casting from Movies
Automatic casting applications aim is to accurately recognise facial regions that correspond to a same actor appearing in a movie to produce described video. This project will focus on the tasks of re-identify the face of each principal actors when they appear in different scenes of a movie. This is a challenging task because although recent movies are typically high resolution, the faces are often occluded and their appearance varies significantly according to pose, scale, illumination, blur, etc. This project will focus on developing and evaluating convolutional neural network (CNN) architectures that are suitable for accurate face re-identification in automatic casting applications. Deep learning architectures have recently been shown to provide a significantly higher level of accuracy compared to conventional methods on many challenging visual recognition problems. However, these architectures are complex, and the unlabelled facial trajectories captured in a movie provide a limited reference data to adapt or fine-tune CNNs. TO BE CONT’D
Voir la description complète du projetÉric Granger
Centre de recherche informatique de Montréal (CRIM)
Computer science
Information and Communications Technology; Technology; Entertainment and Media
École de technologie supérieure
Accelerate