Preprint
Sep 2026
Hyper-RED: Scalable Event Pre-training via Semantic Hypergraph Distillation
A hypergraph relational distillation loss is introduced that imposes complementary intra- and cross-modal constraints, enabling the event encoder to inherit image-derived semantic organization while preserving local relational consistency and event-specific characteristics.
Mei Wang, Zhi-Qiang Tian, Wei Bao et al.
· 0 citations