Research map / Architectures and efficiency / Spiking networks
A Low Power, Fully Event-Based Gesture Recognition System
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add the 80 ms sliding window filter after the winner-take-all decoder (ablation) | TrueNorth gesture recognition system · DvsGesture out-of-sample, 11 categories | accuracy: 91.77% -> 94.59% | Helped |
| Add spatial translation augmentation (ablation) | TrueNorth gesture recognition CNN · DvsGesture out-of-sample, 10 categories | accuracy: 93.53 -> 96.49 | Helped |
| Use 32×32 rather than 64×64 input images (ablation) | TrueNorth gesture recognition CNN · DvsGesture out-of-sample, 10 categories | accuracy: 96.49 -> 92.59 | Hurt |
| Reduce delayed temporal channels from 6 to 4 (ablation) | TrueNorth gesture recognition CNN · DvsGesture out-of-sample, 10 categories | accuracy: 96.49 -> 95.25 | Hurt |
| Use 42×42 input images (ablation) | TrueNorth gesture recognition CNN · DvsGesture out-of-sample, 10 categories | accuracy: 96.49 -> 91.46 | Hurt |
| Increase temporal filter duration from 32 to 64 ticks (ablation) | TrueNorth gesture recognition CNN · DvsGesture out-of-sample, 10 categories | accuracy: 96.49 -> 92.17 | Hurt |
| Use a reduced network with stride 1 in layers 1 and 9 (ablation) | TrueNorth gesture recognition CNN · DvsGesture out-of-sample, 10 categories | accuracy: 96.49 -> 87.62 | Hurt |
| Increase temporal filter duration from 32 to 85 ticks (ablation) | TrueNorth gesture recognition CNN · DvsGesture out-of-sample, 10 categories | accuracy: 96.49 -> 92.24 | Hurt |
| Increase temporal filter duration from 32 to 128 ticks (ablation) | TrueNorth gesture recognition CNN · DvsGesture out-of-sample, 10 categories | accuracy: 96.49 -> 94.81 | Hurt |
Closest papers by meaning
- SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition (ICLR 2024 · similarity 0.87)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.87)
- PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors (CVPR 2024 · similarity 0.85)
- A Chaotic Dynamics Framework Inspired by Dorsal Stream for Event Signal Processing (ICML 2025 · similarity 0.84)
- SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network (NeurIPS 2024 · similarity 0.84)
- Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention (CVPR 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.