# Slow and steady feature analysis: higher order temporal coherence in video

arXiv: https://arxiv.org/abs/1506.04714 · HTML: https://mlsanity.com/paper/1506.04714/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2015.

## Built on by (most cited first, 28 of 28)

- [Anticipative Video Transformer](https://mlsanity.com/paper/2106.02036/) (2021)
- [Video Transformers: A Survey](https://mlsanity.com/paper/2201.05991/) (2022)
- [Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment](https://mlsanity.com/paper/2306.05526/) (2023)
- [Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers](https://mlsanity.com/paper/2108.11996/) (2021)
- [Shot Contrastive Self-Supervised Learning for Scene Boundary Detection](https://mlsanity.com/paper/2104.13537/) (2021)
- [ReSkin: versatile, replaceable, lasting tactile skins](https://mlsanity.com/paper/2111.00071/) (2021)
- [Video Autoencoder: self-supervised disentanglement of static 3D structure and motion](https://mlsanity.com/paper/2110.02951/) (2021)
- [Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation](https://mlsanity.com/paper/2203.02925/) (2022)
- [Noether Networks: Meta-Learning Useful Conserved Quantities](https://mlsanity.com/paper/2112.03321/) (2021)
- [Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference](https://mlsanity.com/paper/2403.04082/) (2024)
- [Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labels](https://mlsanity.com/paper/2304.07978/) (2023)
- [CoCon: Cooperative-Contrastive Learning](https://mlsanity.com/paper/2104.14764/) (2021)
- [Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening](https://mlsanity.com/paper/2509.08502/) (2025)
- [A Review of Predictive and Contrastive Self-supervised Learning for Medical Images](https://mlsanity.com/paper/2302.05043/) (2023)
- [Self-supervised visual learning from interactions with objects](https://mlsanity.com/paper/2407.06704/) (2024)
- [Adaptive Graph Convolutional Networks for Weakly Supervised Anomaly Detection in Videos](https://mlsanity.com/paper/2202.06503/) (2022)
- [MRI Contrast Enhancement Kinetics World Model](https://mlsanity.com/paper/2602.19285/) (2026)
- [3DTINC: Time-Equivariant Non-Contrastive Learning for Predicting Disease Progression from Longitudinal OCTs](https://mlsanity.com/paper/2312.16980/) (2023)
- [Self-Supervised Learning for Image Segmentation: A Comprehensive Survey](https://mlsanity.com/paper/2505.13584/) (2025)
- [Learning Temporally Equivariance for Degenerative Disease Progression in OCT by Predicting Future Representations](https://mlsanity.com/paper/2405.09404/) (2024)
- [Human Gaze Boosts Object-Centered Representation Learning](https://mlsanity.com/paper/2501.02966/) (2025)
- [Beyond Instance Consistency: Investigating View Diversity in Self-supervised Learning](https://mlsanity.com/paper/2509.11344/) (2025)
- [TeCoNeRV: Leveraging Temporal Coherence for Compressible Neural Representations for Videos](https://mlsanity.com/paper/2602.16711/) (2026)
- [Contrastive Learning Boosts Deterministic and Generative Models for Weather Data](https://mlsanity.com/paper/2603.24744/) (2026)
- [The Impact of Spatiotemporal Augmentations on Self-Supervised Audiovisual Representation Learning](https://mlsanity.com/paper/2110.07082/) (2021)
- [Multi-Modal Video Topic Segmentation with Dual-Contrastive Domain Adaptation](https://mlsanity.com/paper/2312.00220/) (2023)
- [Collecting Consistently High Quality Object Tracks with Minimal Human Involvement by Using Self-Supervised Learning to Detect Tracker Errors](https://mlsanity.com/paper/2405.03643/) (2024)
- [Temporal Slowness in Central Vision Drives Semantic Object Learning](https://mlsanity.com/paper/2602.04462/) (2026)

## Abstract (arXiv)

How can unlabeled video augment visual learning? Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures the fact that high-level visual signals change slowly over time, it fails to capture *how* the visual content changes. We propose to generalize slow feature analysis to "steady" feature analysis. The key idea is to impose a prior that higher order derivatives in the learned feature space must be small. To this end, we train a convolutional neural network with a regularizer on tuples of sequential frames from unlabeled video. It encourages feature changes over time to be smooth, i.e., similar to the most recent changes. Using five diverse datasets, including unlabeled YouTube and KITTI videos, we demonstrate our method's impact on object, scene, and action recognition tasks. We further show that our features learned from unlabeled video can even surpass a standard heavily supervised pretraining approach.