University of Bristol
Examples of time-reversing

Abstract

We investigate video transforms that result in class-homogeneous label-transforms. These are video transforms that consistently maintain or modify the labels of all videos in each class. We propose a general approach to discover invariant classes, whose transformed examples maintain their label; pairs of equivariant classes, whose transformed examples exchange their labels; and novel-generating classes, whose transformed examples belong to a new class outside the dataset. Label transforms offer additional supervision previously unexplored in video recognition benefiting data augmentation and enabling zero-shot learning opportunities by learning a class from transformed videos of its counterpart.

Amongst such video transforms, we study horizontal-flipping, time-reversal, and their composition. We highlight errors in naively using horizontal-flipping as a form of data augmentation in video. Next, we validate the realism of time-reversed videos through a human perception study where people exhibit equal preference for forward and time-reversed videos. Finally, we test our approach on two datasets, Jester and Something-Something, evaluating the three video transforms for zero-shot learning and data augmentation. Our results show that gestures such as zooming in can be learnt from zooming out in a zero-shot setting, as well as more complex actions with state transitions such as digging something out of something from burying something in something.

Video

Poster

Poster

BibTeX

@article{price2019_RetroActionsLearning,
    author    = {Price, Will and Damen, Dima},
    title     = {{Retro-Actions}: Learning 'Close' by Time-Reversing 'Open' Videos},
    booktitle = {The IEEE International Conference on Computer Vision Workshops (ICCVW)},
    year      = {2019}
}

Downloads

Acknowledgements

Funded by EPSRC National Productivity Investment Fund (NPIF) Doctoral Training Programme.