A Dataset To Evaluate The Representations Learned By Video Prediction Models
This work provides a tool for the video prediction community to better understand model representations, though it is incremental as it focuses on evaluation rather than new prediction methods.
The authors introduced a synthetic dataset called Moving Symbols to objectively evaluate video prediction models, revealing issues in a state-of-the-art method and proposing a more interpretable performance metric.
We present a parameterized synthetic dataset called Moving Symbols to support the objective study of video prediction networks. Using several instantiations of the dataset in which variation is explicitly controlled, we highlight issues in an existing state-of-the-art approach and propose the use of a performance metric with greater semantic meaning to improve experimental interpretability. Our dataset provides canonical test cases that will help the community better understand, and eventually improve, the representations learned by such networks in the future. Code is available at https://github.com/rszeto/moving-symbols .