arXiv Analytics

Sign in

arXiv:1802.08936 [cs.CV]AbstractReferencesReviewsResources

A Dataset To Evaluate The Representations Learned By Video Prediction Models

Ryan Szeto, Simon Stent, German Ros, Jason J. Corso

Published 2018-02-25Version 1

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.

Related articles: Most relevant | Search more
arXiv:2008.12378 [cs.CV] (Published 2020-08-27)
Metrics for Exposing the Biases of Content-Style Disentanglement
arXiv:2301.04454 [cs.CV] (Published 2023-01-11)
Allo-centric Occupancy Grid Prediction for Urban Traffic Scene Using Video Prediction Networks
arXiv:2011.12527 [cs.CV] (Published 2020-11-25)
Match Them Up: Visually Explainable Few-shot Image Classification