# Slow Feature Analysis for Human Action Recognition

arXiv: https://arxiv.org/abs/1907.06670 · HTML: https://mlsanity.com/paper/1907.06670/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2019.

## Built on by (most cited first, 16 of 16)

- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Relaxed Transformer Decoders for Direct Action Proposal Generation](https://mlsanity.com/paper/2102.01894/) (2021)
- [Video Transformers: A Survey](https://mlsanity.com/paper/2201.05991/) (2022)
- [Tensor Methods in Computer Vision and Deep Learning](https://mlsanity.com/paper/2107.03436/) (2021)
- [A Recipe for Scaling up Text-to-Video Generation with Text-free Videos](https://mlsanity.com/paper/2312.15770/) (2023)
- [MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition](https://mlsanity.com/paper/2304.00946/) (2023)
- [A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames](https://mlsanity.com/paper/2312.07395/) (2023)
- [Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection](https://mlsanity.com/paper/2112.04771/) (2021)
- [Efficient Video Action Detection with Token Dropout and Context Refinement](https://mlsanity.com/paper/2304.08451/) (2023)
- [RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter](https://mlsanity.com/paper/2405.19465/) (2024)
- [Deep Motion Prior for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2108.05607/) (2021)
- [MRI Contrast Enhancement Kinetics World Model](https://mlsanity.com/paper/2602.19285/) (2026)
- [Spatio-Temporal Crop Aggregation for Video Representation Learning](https://mlsanity.com/paper/2211.17042/) (2022)
- [Concatenated Masked Autoencoders as Spatial-Temporal Learner](https://mlsanity.com/paper/2311.00961/) (2023)
- [Submission to Generic Event Boundary Detection Challenge@CVPR 2022: Local Context Modeling and Global Boundary Decoding Approach](https://mlsanity.com/paper/2206.15268/) (2022)
- [Temporal Cluster Assignment for Efficient Real-Time Video Segmentation](https://mlsanity.com/paper/2508.05851/) (2025)

## Abstract (arXiv)

Slow Feature Analysis (SFA) extracts slowly varying features from a quickly varying input signal. It has been successfully applied to modeling the visual receptive fields of the cortical neurons. Sufficient experimental results in neuroscience suggest that the temporal slowness principle is a general learning principle in visual perception. In this paper, we introduce the SFA framework to the problem of human action recognition by incorporating the discriminative information with SFA learning and considering the spatial relationship of body parts. In particular, we consider four kinds of SFA learning strategies, including the original unsupervised SFA (U-SFA), the supervised SFA (S-SFA), the discriminative SFA (D-SFA), and the spatial discriminative SFA (SD-SFA), to extract slow feature functions from a large amount of training cuboids which are obtained by random sampling in motion boundaries. Afterward, to represent action sequences, the squared first order temporal derivatives are accumulated over all transformed cuboids into one feature vector, which is termed the Accumulated Squared Derivative (ASD) feature. The ASD feature encodes the statistical distribution of slow features in an action sequence. Finally, a linear support vector machine (SVM) is trained to classify actions represented by ASD features. We conduct extensive experiments, including two sets of control experiments, two sets of large scale experiments on the KTH and Weizmann databases, and two sets of experiments on the CASIA and UT-interaction databases, to demonstrate the effectiveness of SFA for human action recognition.