Automated Driving

A Dataset To Evaluate The Representations Learned By Video Prediction Models

TRI Default Image

TRI Authors: Simon Stent, Ryan Szeto, German Ros

All Authors: Ryan Szeto and Simon Stent and German Ros and Jason J. Corso

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. Read More

Citation: Szeto, Ryan, Simon Stent, German Ros, and Jason J. Corso. "A dataset to evaluate the representations learned by video prediction models." 2018 ICLR, 2018.

SHARE: