Zhipeng Sui — accepted AI-conference papers

2026

Adaptive Spatial-Temporal Window: Unlocking the Potential of Event Cameras in Heterogeneous Velocity Scenarios

Zhipeng Sui, Haiqing Hao, Weihua He, Seng-Hong Lee, Wenhui Wang

CVPR 2026

Most event-based algorithms typically split the event stream into fixed groups (e.g., fixed time or fixed count) for downstream processing, lacking adaptivity to scene dynamics. Several adaptive partitioning strategies have been proposed, but they are unable to cope well with heterogeneous velocity

Cited by 0 Source ↗Scholar ↗

2026

Maximizing Asynchronicity in Event-based Neural Networks

Haiqing Hao, Nikola Zubic, Weihua He, Zhipeng Sui, Davide Scaramuzza, Wenhui Wang

ICLR 2026poster

Event cameras deliver visual data with high temporal resolution, low latency, and minimal redundancy, yet their asynchronous, sparse sequential nature challenges standard tensor-based machine learning (ML). While the recent asynchronous-to-synchronous (A2S) paradigm aims to bridge this gap by async…

Cited by 0 Source ↗code ↗Scholar ↗