SOURCE-LINKED INTELLIGENCE

Hyper-RED: Scalable Event Pre-training via Semantic Hypergraph Distillation

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Event cameras have shown great potential for robust visual perception, yet scaling event representation learning remains challenging due to the scarcity of large-scale annotated event data. Pretrained image models provide scalable semantic supervision, but existing image-to-event methods rely on rigid pixel-wise or token-wise alignment that overlooks modality discrepancies in texture, density, and appearance, potentially causing semantic collapse and limiting transferability. To address this issue, we propose Hyper-RED, a simple, painless, and scalable image-to-event pretraining framework that

Read original source ↗ Open in workspace

recordType

paper

region

Global