Junru (Charles) Wu

Ph.D. Student

Dept. of Computer Science & Enigneering, Texas A&M University
sandboxmaster@tamu.edu [CV]

Brief Biography

I’m a second year Ph.D Student in Computer Science at Texas A&M University, my advisor is Dr. Zhangyang Wang. I also worked closely with Dr. Xiang Yu and Dr. Manmohan Chandraker at NEC Labs America.

From 2016 to 2017, I was a research assistant at Visual Computing Lab, ShanghaiTech University, under the supervision of Dr. Shenghua Gao. I received my B.Eng degree in Electrical Engineering from Tongji University, Shanghai in 2016.

Research Interests

My research interests lie in deep learning and computer vision, specifically in compression of CNN to enable deployment on resource-constrained mobile devices.

I also work on high-level vision task such as saliency detection, low-level vision task such as image denoising, dehazing, deblurring, super-resolution, low quality image restoration in general.


Junru Wu, Yue Wang, Zhenyu Wu, Zhangyang Wang, Ashok Veeraraghavan and Yingyan Lin. “Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions” International Conference on Machine Learning (ICML), 2018. [PDF] [Github]

Yanyu Xu, Yanbing Dong, Junru Wu, Zhengzhong Sun, Zhiru Shi, Jingyi Yu, and Shenghua Gao. “Gaze Prediction in Dynamic 360◦ Immersive Videos” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [PDF] [Github]

Yanyu Xu, Nianyi Li, Junru Wu, Jingyi Yu, and Shenghua Gao. “Beyond Universal Saliency: Personalized Saliency Prediction with Multi-task CNN” IEEE International Joint Conference on Artificial Intelligence (IJCAI), 2017. (Best Student Paper Finalist) [PDF] [Github]

Yanyu Xu*, Shenghua Gao*, Junru Wu*, Nianyi Li and Jingyi Yu, “Beyond Universal Saliency: Personalized Saliency and its Prediction”, to be appear on IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). [PDF] *Equal contributions