AI Paper Atlas

Research map / Benchmarks / DVS-Gesture

DVS-Gesture leaderboard

25 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on DVS-Gesture. Best accuracy: 99.31 (CLIF, 16 timesteps, ICML 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

DVS-Gesture · accuracy

25 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
199.31CLIF, 16 timesteps
Spike-Driven-Transformer
CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networks
ICML 2024 · Table 2
Spiking networks
299.3S3NetS3Net: Spatiotemporally Separated Sparse Network for Neuromorphic Vision Processing
AAAI 2026 · Table 2
Spiking networks
399.08Strong2Weak
QKFormer
Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers
NeurIPS 2025 · Comparative results on neuromo
Knowledge distillation
498.61FPT, K=3Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity
ICML 2025 · Appendix, Ablation Study of K
Spiking networks
598.48Quantized SNNAre Conventional SNNs Really Efficient? A Perspective from Network Quantization
CVPR 2024 · Table 3
Spiking networks
698.26PIT
VGG11 (T x D 20x2)
Advancing Spatiotemporal Representations in Spiking Neural Networks via Parametric Invertible Transformation
ICLR 2026 · Table 12
Spiking networks
797.92AGMM
VGGSNN
Towards Accurate Binary Spiking Neural Networks: Learning with Adaptive Gradient Modulation Mechanism
AAAI 2025 · Table 1
Spiking networks
897.92SASTC, ResNet-18, T=16
ResNet-18
Self-Attentive Spatio-Temporal Calibration for Precise Intermediate Layer Matching in ANN-to-SNN Distillation
AAAI 2025 · Table: Neuromorphic Datasets
Spiking networks
997.927B-Net (SEW ADD)
7B-Net
Deep Residual Learning in Spiking Neural Networks
NeurIPS 2021 · Table 3
Spiking networks
1097.8CNN+EGRU+DA
CNN+GRU
Efficient recurrent architectures through activity sparsity and sparse back-propagation through time
ICLR 2023 · Table 1
RNNs and normalization
15 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.