xiaofang.wang@univ-reims.fr
xiaofang.wang@inria.fr
I am chinese citizen, working and living in French. My mother language is chinese, I speak mandarin and two dialects. I speak and undersantd french very well, most of my collegues are French. I use English as reading/writting as well as bussiness language.
Hey! I am currently a Post-doc at University of reims and Inria rennes, working on 3D human performance capture. I am passionate about cutting-edges avances and apply them on real-life.
Research Interest: My research interests focus on 2D/3D image/video understanding with machine learning and deep learning.
Education: During My PhD studies, I worked on the unsupervised image segmentation and multiple objects tracking with Prof. Simon Masnou and Prof. Liming Chen. I completed my M.E. and B.S. majored in Biomedical Engineering in School of Geosciences and Info-physics from Central South University, Changsha, China. I was working on the medical image processing, liver CT image segmentation with Prof. Yuqian Zhao
04/05, 2020: After a wonderful journey in Siradel, I am glad to join University of Reims and Inria Rennes as Post-doc 25/12, 2019: I am happy to get invited by Jiang su University Forum for High-level Overseas Talents 9/12, 2019: Journal paper is accepted: Discriminative and geometry aware unsupervised domain adaptation. IEEE Transactions on Cybernetics (TCYB), Link 23/05, 2019: I was attending Conference JURSE.
Aerial image high-resolution segmentation
After joining Siradel, I am developping a tool based on deep learning for
aeriel image semantic segmentation. Here shows a nice result on the segmentation of high vegetation
Efficient Video Object Detection and Tracking Tool
By Xiaofang WANG
After trying several existing video annotation tools, I have developed an efficient video annotation tool for extreme-density
crowd study. The proposed tool makes it easy to build massive, affordable video data sets.
Here show a video by human-annotated (myself) video in a
given region (in blue). This video is generated by an efficient video annotation tool.
Here illustrates the trace of the annotation
|
Point in, Box out: Beyond Counting Persons in Crowds.
yuting liu, Miaojing Shi, Qijun Zhao, Xiaofang Wang
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'2019) Link |
|
Developmental Bayesian Optimization of Black-Box with Visual Similarity-Based Transfer Learning.
Maxime Petit, Amaury Depierre, Xiaofang Wang, Emmanuel Dellandrea, and Liming Chen. IEEE International Conference on Development and Learning (ICDL) and the International Conference on Epigenetic Robotics (EpiRob), 2018, Tokyo. PDF . |
|
Fusing Generic Objectness and Deformable Part-based Models for Weakly Supervised Object Detection
Yuxing Tang, Xiaofang Wang, Emmanuel Dellandréa, Simon Masnou, Liming Chen
IEEE International Conference on Image Processing (ICIP), Paris, 2014. (Top 10%)
[pdf] |
|
A graph-cut approach to image segmentation using an affinity graph based on ℓ0-sparse representation of features
Xiaofang Wang and Huibin Li and Charles-edmond Bichot and, Simon Masnou, Liming Chen
IEEE International Conference on Image Processing (ICIP), 2013. (Top 10%)
[pdf] |
|
Graph-based image segmentation using weighted color patch
Xiaofang Wang, Chao Zhu, Charles-edmond Bichot, Simon Masnou IEEE International Conference on Image Processing (ICIP), 2013. [pdf] |
|
Sparse Coding and Mid-Level Superpixel-Feature for ℓ0-Graph Based Unsupervised Image Segmentation
Xiaofang Wang , Huibin Li, Simon Masnou, Liming Chen Computer Analysis of Images and Patterns. Springer Berlin Heidelberg (CAIP), 2013. [PDF] |
|
An improved non-local cost aggregation method for stereo matching based on color and boundary cue
Dongming Chen, Mohsen Ardabilian, Xiaofang Wang, Liming Chen IEEE International Conference on Multimedia and Expo (ICME), 2013. [PDF] |
|
Discriminative and geometry aware unsupervised domain adaptation.
Lingkun Luo, Liming Chen, Shiqiang Hu, Ying Lu, Xiaofang Wang Submitted to IEEE Transactions on Cybernetics (TCYB), Link Accepted |
|
A Unified Framework for Interactive Image Segmentation via Fisher Rules.
Lingkun Luo, Xiaofang Wang, Shiqiang Hu, Xing Hu, Huanlong Zhang,Yaohua Liu The Visual Computing, 2018 Link . |
|
Visual and Semantic Knowledge Transfer for Large Scale Semi-Supervised Object Detection
Yuxing Tang, Josiah Wang, Xiaofang Wang, Boyang Gao, Emmanuel Dellandrea,and Liming Chen. IEEE transactions on pattern analysis and machine intelligence (T-PAMI), 2018, vol. 40, no 12, p. 3045-3058. Link . |
|
Interactive image segmentation based on samples reconstruction and FLDA.
Lingkun Luo, Xiaofang Wang, Shiqiang Hu, Xin Hu, Liming Chen Journal of Visual Communication and Image Representation 43 (2017): 138-151. Link |
|
|
Weakly Supervised Learning of Deformable Part-Based Models for Object Detection via Region Proposals |
|
|
Retinal vessels segmentation based on level set and region growing
Yu Qian Zhao and Xiao Hong Wang and Xiaofang Wang, and Frank Y Shih.
Pattern Recognition(PR) vol.47(7), pp. 2437-2446,2014
[PDF]
|
|
Level-set Mehod Based On Global and Local Regions For Image Segmentation
Yuqian Zhao, Xiaofang Wang, Frank Y.Shih, Gang Yu International Journal of Pattern Recognition and Artificial Intelligence, vol. 26(01), 2013. [PDF] |
Robust Data Geometric Structure Aligned Close yet Discriminative Domain Adaptation [link]
Lingkun Luo, Xiaofang Wang, Shiqiang Hu, Liming Chen
Sumitted, Under revision
Close Yet Distinctive Domain Adaptation
Lingkun Luo, Xiaofang Wang, Shiqiang Hu, Chao Wang, Yuxing Tang, Liming Chen
Project, PDF . Submitted, Under revision
INF-TC1: Introduction to algorithms (1st year Ecole Centrale de Lyon, TD/TP, 84h), Fall 2015 and Spring 2016.
INF-TC2: Object-oriented programming (1st year Ecole Centrale de Lyon, TD/TP, 63h), Fall 2015 and Spring 2016.
INF-TC3: Web and Database Project (1st year Ecole Centrale de Lyon, TD/TP, 32h), Fall 2015 and Spring 2016.
IEEE Transactions on Image Processing [LINK]
IEEE Transactions on Knowledge and Data Engineering [LINK]
Pattern Recognition
ACM 2019
French learning notes [LINK]