# Skip-Clip: Self-Supervised Spatiotemporal Representation Learning by Future Clip Order Ranking

arXiv: https://arxiv.org/abs/1910.12770 · HTML: https://mlsanity.com/paper/1910.12770/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2019.

## Built on by (most cited first, 8 of 8)

- [The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing](https://mlsanity.com/paper/2207.09812/) (2022)
- [Position Prediction as an Effective Pretraining Strategy](https://mlsanity.com/paper/2207.07611/) (2022)
- [There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning](https://mlsanity.com/paper/2106.04480/) (2021)
- [Motion-Augmented Self-Training for Video Recognition at Smaller Scale](https://mlsanity.com/paper/2105.01646/) (2021)
- [Generating coherent comic with rich story using ChatGPT and Stable Diffusion](https://mlsanity.com/paper/2305.11067/) (2023)
- [Self-Supervised Learning via multi-Transformation Classification for Action Recognition](https://mlsanity.com/paper/2102.10378/) (2021)
- [Order-Based Pre-training Strategies for Procedural Text Understanding](https://mlsanity.com/paper/2404.04676/) (2024)
- [MIO : Mutual Information Optimization using Self-Supervised Binary Contrastive Learning](https://mlsanity.com/paper/2111.12664/) (2021)

## Abstract (arXiv)

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.