Dec 14, 2022 · To this end, we propose a bio-inspired unsupervised learning framework, which takes advantage of the spatiotemporal information of events/spikes ...

To this end, we propose a bio-inspired unsupervised learning framework, which takes advantage of the spatiotemporal information of events/spikes generated by ...

Dec 14, 2022 · 神经形态视觉传感器的像素根据场景辐射变化以高时间分辨率异步输出事件/尖峰，自然适合捕获场景中的高速运动。然而，如何利用事件/尖峰平滑地跟踪高速移动 ...

My research interests include areas of neuromorphic computing, computer vision, machine learning and spiking neural networks.

Spike-Based Motion Estimation for Object Tracking Through Bio-Inspired Unsupervised Learning Yajing Zheng, Zhaofei Yu*, Song Wang, Tiejun Huang IEEE ...

Spike-based motion estimation for object tracking through bio-inspired unsupervised learning. Y Zheng, Z Yu, S Wang, T Huang. IEEE Transactions on Image ...

Spike-based motion estimation for object tracking through bio-inspired unsupervised learning. Y Zheng, Z Yu, S Wang, T Huang. IEEE Transactions on Image ...

Jun 1, 2024 · To underscore the effectiveness of spike cameras in magnifying high-speed micro-motions, the SpikeMM module will utilize a learning-based motion ...

This paper presents the first hierarchical spiking architecture in which motion (direction and speed) selectivity emerges in an unsupervised fashion from ...

SCFlow [17] is a deep pyramidal network with a motion-adaptive representation for spike-based optical flow, trained by graphics-based simulated data. ... ...