Xiaowei Hu 胡晓伟 - 程明明

Skip to content

I am a Master student at CCCE&CS, Nankai University (Tianjin, China). My advisor is Professor is Ming-Ming Cheng. I received my bachelor degree from Tianjin University in 2016.

My research interest includes:

• computer vision
• image generation
• reinforcement learning

Feel free to contact xiaowei.hu[AT]outlook.com if you have any questions.

Publications

• Learning hybrid convolutional features for edge detection. Xiaowei Hu, Yun Liu, Kai Wang, and Bo Ren. Springer Neurocomputing, 2018.
• Deeply supervised salient object detection with short connections. Qibin Hou, Ming-Ming Cheng, Xiaowei Hu, Ali Borji, Zhuowen Tu, and Philip Torr. IEEE TPAMI, 2018.
• Richer convolutional features for edge detection. Yun Liu, Ming-Ming Cheng, Xiaowei Hu, Kai Wang, and Xiang Bai. IEEE CVPR, 2017.
• Deeply supervised salient object detection with short connections. Qibin Hou, Ming-Ming Cheng, Xiaowei Hu, Ali Borji, Zhuowen Tu, and Philip Torr. IEEE CVPR, 2017.
• Salient object detection: A discriminative regional feature integration approach. Jingdong Wang, Huaizu Jiang, Zejian Yuan, Ming-Ming Cheng, Xiaowei Hu, Nanning Zheng. Springer IJCV 2018.

Projects

• pysc2-agents

This is a simple implementation of DeepMind’s PySC2 RL agents. In this project, the agents are defined according to the original paper, which use all feature maps and structured information to predict both actions and arguments via an A3C algorithm.

• cyclegan-tensorflow

Tensorflow implementation for learning an image-to-image translation without input-output pairs.

Experience

• AI Lab at Bytedance (2018 April – Now, my leader is yuning jiang)
  • focus on AD creative generation
• Microsoft Research Asia (2017 May – 2017 november, my leader is bo xin)
  • image style transfer
  • reinforcement learning

Professional Service

Reviewer of CVPR 2018