# Skip-Clip: Self-Supervised Spatiotemporal Representation Learning by Future Clip Order Ranking Source: [Skip-Clip: Self-Supervised Spatiotemporal Representation Learning by Future Clip Order Ranking]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:14:01.077Z Authors: Alaaeldin El-Nouby, Shuangfei Zhai, Graham W. Taylor, Joshua M. Susskind Published: 2019-10-28T15:54:45.000Z ## Abstract Deep neural networks require collecting and annotating large amounts of data to train successfully. In order to alleviate the annotation bottleneck, we propose a novel self-supervised representation learning approach for spatiotemporal features extracted from videos. We introduce Skip-Clip, a method that utilizes temporal coherence in videos, by training a deep model for future clip order ranking conditioned on a context clip as a surrogate objective for video future prediction. We show that features learned using our method are generalizable and transfer strongly to downstream tasks. For action recognition on the UCF101 dataset, we obtain 51.8% improvement over random initialization and outperform models initialized using inflated ImageNet parameters. Skip-Clip also achieves results competitive with state-of-the-art self-supervision methods. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Action Recognition on UCF101 (1)](): Action Recognition; UCF101 (1); Accuracy: 64.4. - [Action Recognition on UCF101 (Split 1)](): Action Recognition; UCF101 (Split 1); Top-1 Acc: 64.4. ## Original sources and implementation [Original paper]() [PDF]()