# Learning to Recognize Actions from Limited Training Examples Using a Recurrent Spiking Neural Model

arXiv: https://arxiv.org/abs/1710.07354 · HTML: https://mlsanity.com/paper/1710.07354/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2017.

## Built on by (most cited first, 7 of 7)

- [HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors](https://mlsanity.com/paper/2211.09648/) (2022)
- [SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognition](https://mlsanity.com/paper/2308.04369/) (2023)
- [SVFormer: A Direct Training Spiking Transformer for Efficient Video Action Recognition](https://mlsanity.com/paper/2406.15034/) (2024)
- [ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action Recognition](https://mlsanity.com/paper/2409.01564/) (2024)
- [Exploiting Heterogeneity in Timescales for Sparse Recurrent Spiking Neural Networks for Energy-Efficient Edge Computing](https://mlsanity.com/paper/2407.06452/) (2024)
- [Adaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networks](https://mlsanity.com/paper/2304.01015/) (2023)
- [SPACT18: Spiking Human Action Recognition Benchmark Dataset with Complementary RGB and Thermal Modalities](https://mlsanity.com/paper/2507.16151/) (2025)

## Abstract (arXiv)

A fundamental challenge in machine learning today is to build a model that can learn from few examples. Here, we describe a reservoir based spiking neural model for learning to recognize actions with a limited number of labeled videos. First, we propose a novel encoding, inspired by how microsaccades influence visual perception, to extract spike information from raw video data while preserving the temporal correlation across different frames. Using this encoding, we show that the reservoir generalizes its rich dynamical activity toward signature action/movements enabling it to learn from few training examples. We evaluate our approach on the UCF-101 dataset. Our experiments demonstrate that our proposed reservoir achieves 81.3%/87% Top-1/Top-5 accuracy, respectively, on the 101-class data while requiring just 8 video examples per class for training. Our results establish a new benchmark for action recognition from limited video examples for spiking neural models while yielding competetive accuracy with respect to state-of-the-art non-spiking neural models.