3 papers
cs.ET2021
High speed and reconfigurable optronic neural network with digital nonlinear activation
Qiuhao Wu, Jia Liu, Xiubao Sui +2
With its unique parallel processing capability, optical neural network has shown low-power consumption in image recognition and speech processing. At present, the manufacturing tec…
cs.CV2020
Object Tracking Using Spatio-Temporal Future Prediction
Yuan Liu, Ruoteng Li, Robby T. Tan +2
Occlusion is a long-standing problem that causes many modern tracking methods to be erroneous. In this paper, we address the occlusion problem by exploiting the current and future…
cs.CV2018
Thermal Infrared Colorization via Conditional Generative Adversarial Network
Xiaodong Kuang, Xiubao Sui, Chengwei Liu +3
Transforming a thermal infrared image into a realistic RGB image is a challenging task. In this paper we propose a deep learning method to bridge this gap. We propose learning the…