Hello, adventurers! My name is Xiaowei Hu (胡晓伟 in Chinese). I am a second-year master student in Media Computing Lab at Nankai University. My adviser is Prof. Cheng and my research interests are machine learning and computer vision. Before that, I got the B.S. degree of Mathematics at Tianjin University in 2016.
Nankai University, Tianjin China, Sept.2016 - Present
M.S. in Computer Science, advised by Prof. Ming-Ming Cheng
TianJin University, Tianjin China, Sept.2012 - Jun.2016
B.S. in Mathematics, GPA: 89/100 Rank: 2/27
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.
Tensorflow implementation for learning an image-to-image translation without input-output pairs. The method is proposed by Jun-Yan Zhu in Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkssee. For example in paper:
Image Dense Prediction
Focus on image dense prediction, such as semantic segmantation, saliency and edge detection. During this period, we finished 4 relative papers, two papers accepted by CVPR 2017 and one paper accepted by IJCV 2017. More details can be found in Publication.
Focus on deep learning-based detectors including R-CNN, Fast/Faster RCNN and RFCN, and complete an overview as the bachelor’s thesis.
Learning Hybrid Convolutional Features for Edge Detection
Xiaowei Hu, Yun Liu, Kai Wang and Ming-Ming Cheng
Deeply supervised salient object detection with short connections
Qibin Hou, Ming-Ming Cheng, Xiaowei Hu, Ali Borji, Zhuowen Tu and Philip Torr
CVPR 2017 Paper
Richer Convolutional Features for Edge Detection
Yun Liu, Ming-Ming Cheng, Xiaowei Hu, Kai Wang and Xiang Bai
CVPR 2017 Paper
Salient Object Detection: A Discriminative Regional Feature Integration Approach
Jingdong Wang, Huaizu Jiang, Zejian Yuan, Ming-Ming Cheng, Xiaowei Hu and Nanning Zheng
IJCV 2016 Paper
Programming Languages: Python & C++
Deep Learning Libraries: Tensorflow & Caffe
Address: 13#411, Computer Science, Nankai University Jinnan Campus, Tianjin, P.R.China, 300350