Made to Order: Discovering monotonic temporal changes via self-supervised video ordering

arXiv:2404.16828v1 Announce Type: cross
Abstract: Our objective is to discover and localize monotonic temporal changes in a sequence of images. To achieve this, we exploit a simple proxy task of ordering a shuffled image sequence, with `time' serving as a supervisory signal since only changes that are monotonic with time can give rise to the correct ordering. We also introduce a flexible transformer-based model for general-purpose ordering of image sequences of arbitrary length with built-in attribution maps. After training, the …

abstract arxiv cs.cv cs.lg exploit image images signal simple temporal type via video