Location Dependency in Video Prediction

원문 초록

Deep convolutional neural networks are used to address many computer vision problems, including video prediction. The task of video prediction requires analyzing the video frames, temporally and spatially, and constructing a model of how the environment evolves. Convolutional neural networks are spatially invariant, though, which prevents them from modeling location-dependent patterns. In this work, the authors propose location-biased convolutional layers to overcome this limitation. The effectiveness of location bias is evaluated on two architectures: Video Ladder Network (VLN) and Convolutional redictive Gating Pyramid (Conv-PGP). The results indicate that encoding location-dependent features is crucial for the task of video prediction. Our proposed methods significantly outperform spatially invariant models.