Papers › SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos
SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos
Salar Hosseini Khorasgani, Yuxuan Chen, Florian Shkurti
Self-supervised methods have significantly closed the gap with end-to-end supervised learning for image classification. In the case of human action videos, however, where both appearance and motion are significant factors of variation, this gap remains significant. One of the key reasons for this is that sampling pairs of similar video clips, a required step for many self-supervised contrastive learning methods, is currently done conservatively to avoid false positives. A typical assumption is that similar clips only occur temporally close within a single video, leading to insufficient examples of motion similarity. To mitigate this, we propose SLIC, a clustering-based self-supervised contrastive learning method for human action videos. Our key contribution is that we improve upon the traditional intra-video positive sampling by using iterative clustering to group similar video instances. This enables our method to leverage pseudo-labels from the cluster assignments to sample harder positives and negatives. SLIC outperforms state-of-the-art video retrieval baselines by +15.4% on top-1 recall on UCF101 and by +5.7% when directly transferred to HMDB51. With end-to-end finetuning for action classification, SLIC achieves 83.2% top-1 accuracy (+0.8%) on UCF101 and 54.5% on HMDB51 (+1.6%). SLIC is also competitive with the state-of-the-art in action classification after self-supervised pretraining on Kinetics400.
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 | SLIC (R3D-18) | Frozen | false | #30 of 48 | Archive leaderboard | report |
| Self-Supervised Action Recognition | HMDB51 | SLIC (R3D-18) | Pre-Training Dataset | UCF101 | #30 of 48 | Archive leaderboard | report |
| Self-Supervised Action Recognition | HMDB51 | SLIC (R3D-18) | Top-1 Accuracy | 54.5 | #30 of 48 | Archive leaderboard | report |
| Self-Supervised Action Recognition | UCF101 | SLIC (R3D-18) | Frozen | false | #53 of 53 | Archive leaderboard | report |
| Self-Supervised Action Recognition | UCF101 | SLIC (R3D-18) | Pre-Training Dataset | UCF101 | #53 of 53 | Archive leaderboard | report |
| Self-Supervised Action Recognition | UCF101 | SLIC (R3D-18) | split-1 Top-1 Accuracy | 83.2 | #53 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.
Methods
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