Neuromorphic event-based recognition boosted by motion-aware learning

Yuhan Liu, Yongjian Deng, Bochen Xie, Hai Liu, Zhen Yang, Youfu Li

Abstract: Highlights•We introduce the MAB for enhancing motion encoding ability of frame-based models.•We enhance feature fusion by aligning heterogeneous features via cross-attention.•Experiments show efficacy of our method qualitatively and quantitatively.