AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

OmniEvent: Unified Event Representation Learning

Weiqi Yan, Chenlu Lin, Youbiao Wang, Zhipeng Cai, Xiuhong Lin, Yangyang Shi, Weiquan Liu, Yu Zang

AAAI 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
remove one or more components (SFCA branches, STA, statistical features) (ablation)OmniEvent · CIFAR10-DVStop-1 accuracy (%): 74.7 to 82.0 when ablated -> 85.2 fullImproved
use decoupled spatial, temporal and spatio-temporal branches instead of EP2T weighted fusionEP2T · CIFAR10-DVStop-1 accuracy (%): 79.6 -> 85.2Improved
use space-filling-curve aggregation instead of KNNEP2T · CIFAR10-DVSGPU memory (MB): 4650 -> 3146Improved
use space-filling-curve aggregation instead of KNNEP2T · CIFAR10-DVSinference time (ms): 42.8 -> 36.6Improved
use OmniEvent instead of ESTEST · CIFAR10-DVSinference time (ms): 6.3 -> 36.6Hurt
use OmniEvent representation for event-to-point-cloud registrationEP2T · MVSEC E2PRE (deg): 3.606 -> 1.146Improved
use OmniEvent on VECtor registration translation errorTORE · VECtor E2PTE (m): 7.254 -> 7.201No clear effect
use OmniEvent in optical flow on flying3M-LSTM+EVFlowNet · MVSEC indoor flying3AEE: 1.08 -> 1.15Hurt

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