Nilanjan Ray

Professor
Department of Computing Science
University of Alberta, Canada


Recurrent Fully Convolutional Networks for Video Semantic Segmentation

Fig. 1: Overview of the Method
Fig. 2: Architecture

We are one of the first groups to combine convolutional and recurrent neural nets for semantic segmentation of videos. For detained results and comparisons with other models see our publications below.

Related Publications
  • S Valipour, M Siam, M Jagersand, N Ray, "Recurrent fully convolutional networks for video segmentation," WACV 2017.
  • M. Siam, S. Valipour, M. Jagersand, N. Ray, “Convolutional Gated Recurrent Networks for Video Segmentation,” IEEE ICIP 2017.
  • M Siam, S Valipour, M Jagersand, N Ray, S Yogamani, “Convolutional gated recurrent networks for video semantic segmentation in automated driving,” 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).