2019/09/20 by Will Price, Dima Damen, Price, Will +1 · 3 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.CV
paper · pdf · doi:10.48550/arxiv.1909.09422
ICCVW 2019, 8 pages, 7 figures, 6 tables. https://video-reversal.willprice.dev/
arxiv created 2019/09/20 · arxiv updated 2019/09/23
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.