Weidong Hao — accepted AI-conference papers

2026

SMV-EAR: Bring Spatiotemporal Multi-View Representation Learning into Efficient Event-Based Action Recognition

Rui Fan, Weidong Hao, Juntao Guan, Lai Rui, Tong Wu, Fanhong Zeng +1

CVPR 2026

Event cameras action recognition (EAR) offers compelling privacy-protecting and efficiency advantages, where temporal motion dynamics is of great importance. Existing spatiotemporal multi-view representation learning (SMVRL) methods for event-based object recognition (EOR) offer promising solutions

Cited by 0 Source ↗code ↗Scholar ↗

2025

EventPillars: Pillar-based Efficient Representations for Event Data

Rui Fan, Weidong Hao, Juntao Guan, Lai Rui, Lin Gu, Tong Wu +2

AAAI 2025technical

Event Cameras offer appealing advantages, including power efficiency and ultra-low latency, driving forward advancements in edge applications. In order to leverage mature frame-based algorithms, most approaches typically compute dense, image-like representations from sparse, asynchronous events. How…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗