Papers › A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
Christoph Feichtenhofer, Haoqi Fan, Bo Xiong, Ross Girshick, Kaiming He
We present a large-scale study on unsupervised spatiotemporal representation learning from videos. With a unified perspective on four recent image-based frameworks, we study a simple objective that can easily generalize all these methods to space-time. Our objective encourages temporally-persistent features in the same video, and in spite of its simplicity, it works surprisingly well across: (i) different unsupervised frameworks, (ii) pre-training datasets, (iii) downstream datasets, and (iv) backbone architectures. We draw a series of intriguing observations from this study, e.g., we discover that encouraging long-spanned persistency can be effective even if the timespan is 60 seconds. In addition to state-of-the-art results in multiple benchmarks, we report a few promising cases in which unsupervised pre-training can outperform its supervised counterpart. Code is made available at https://github.com/facebookresearch/SlowFast
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Self-Supervised Action Recognition | HMDB51 | pBYOL | Frozen | false | #3 of 48 | Archive leaderboard | report |
| Self-Supervised Action Recognition | HMDB51 | pBYOL | Pre-Training Dataset | Kinetics400 | #3 of 48 | Archive leaderboard | report |
| Self-Supervised Action Recognition | HMDB51 | pBYOL | Top-1 Accuracy | 75.0 | #3 of 48 | Archive leaderboard | report |
| Self-Supervised Action Recognition | UCF101 | pBYOL | 3-fold Accuracy | 96.3 | #5 of 53 | Archive leaderboard | report |
| Self-Supervised Action Recognition | UCF101 | pBYOL | Frozen | false | #5 of 53 | Archive leaderboard | report |
| Self-Supervised Action Recognition | UCF101 | pBYOL | Pre-Training Dataset | Kinetics400 | #5 of 53 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections