-
Seeing the Arrow of Time
AbstractWe explore whether we can observe Time's Arrow in a temporal sequence--is it possible to tell whether a video is running forwards or backwards? We investigate this somewhat philosophical question using computer vision and machine learning techniques. We explore three methods by which we might detect Time's Arrow in video sequences, based on distinct ways in which motion in video sequences might be asymmetric in time. We demonstrate good video forwards/backwards classification results on a selection of YouTube video clips, and on natively-captured sequences (with no temporally-dependent video compression), and examine what motions the models have learned that help discriminate forwards from backwards time.
Related Material
[pdf][bibtex]@InProceedings{Pickup_2014_CVPR,
author = {Pickup, Lyndsey C. and Pan, Zheng and Wei, Donglai and Shih, YiChang and Zhang, Changshui and Zisserman, Andrew and Scholkopf, Bernhard and Freeman, William T.},
title = {Seeing the Arrow of Time},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2014}
}
These CVPR 2014 papers are the Open Access versions, provided by the Computer Vision Foundation.
Except for the watermark, they are identical to the accepted versions; the final published version of the proceedings is available on IEEE Xplore.
Except for the watermark, they are identical to the accepted versions; the final published version of the proceedings is available on IEEE Xplore.
This material is presented to ensure timely dissemination of scholarly and technical work.
Copyright and all rights therein are retained by authors or by other copyright holders.
All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright.