AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Event2Vec: Processing neuromorphic events directly by representations in vector space

Wei Fang, Priyadarshini Panda

ICML 2026 · Architectures and efficiency › Spiking networks · approach: Event-camera spiking networks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 changedWhereMeasuredEffect
use parametric instead of standard spatial embedding (with conv temporal) (ablation)Event2Vec · DVS Gestureaccuracy (%): 91.18 -> 97.57Improved
use parametric instead of standard spatial embedding (with sin temporal) (ablation)Event2Vec · DVS Gestureaccuracy (%): 93.16 -> 96.56Improved
use convolutional temporal embedding on delta t instead of sinusoidal (parametric spatial) (ablation)Event2Vec · DVS Gestureaccuracy (%): 96.56 -> 97.57Improved
use conv temporal embedding with standard spatial embedding (ablation)Event2Vec · DVS Gestureaccuracy (%): 93.16 -> 91.18Hurt
use Batched K-Means++ clustered events instead of random eventsEvent2Vec · DVS-Lipaccuracy (%): 70.62 -> 75.88Improved
use batched K-Means++ instead of Faiss (iters=20) (ablation)Event2Vec clustering · DVS-Lipaccuracy (%): 74.40 -> 75.88Improved
use batched K-Means++ instead of Scikit-learn (iters=300) (ablation)Event2Vec clustering · DVS-Lipaccuracy (%): 75.08 -> 75.88Improved
use Forgetting Transformer instead of Gated Linear Attention (ablation)Event2Vec · DVS-Lipaccuracy (%): 72.35 -> 75.88Improved
use Forgetting Transformer instead of Gated Linear Attention (ablation)Event2Vec · DVS Gestureaccuracy (%): 96.67 -> 97.57Improved
share parameters in bidirectional self-attention (ablation)Event2Vec · DVS Gestureaccuracy (%): 96.63 -> 97.57Improved
add Event2Vec parametric+conv embedding before frozen 5 Transformer layers for linear probing (ablation)Linear probe · DVS Gesturelinear probing accuracy (%): 56.32 -> 86.94Improved
use Event2Vec parametric+conv embedding instead of raw events for linear probing (ablation)Linear probe · ASL-DVSlinear probing accuracy (%): 12.65 -> 38.90Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy