Reviews: Predicting Scene Parsing and Motion Dynamics in the Future

The paper proposes a deep-learning-based approach to joint prediction of future optical flow and semantic segmentation in videos. The authors evaluate the approach in a driving scenario and show that the two components - flow prediction and semantic segmentation prediction - benefit from each other. The paper is related to works of Jin et al. and Neverova et al. However, as far as I understand, both of these have not been officially published at the time of submission (and the work of Neverova et al. Detailed comment: Pros: 1) The idea seems sound: predicting segmentation and optical flow are both important tasks, and they should be mutually beneficial.