Welcome to Song Bai's Homepage

Song Bai

Media and Communication Lab
School of Electronic Information and Communications
Huazhong University of Science and Technology (HUST)
Luoyu Road 1037, Wuhan, China

* As I have graduated from Huazhong University of Science and Technology, I will not use the email with suffix "hust.edu.cn" anymore.

* I have moved my personal homepage to http://songbai.site, and this page will not be updated in time.


Short Bio 

I am currently a Ph.D. candidate at Huazhong University of Science and Technology (HUST), supervised by Prof. Xiang Bai.  Now, I am working with Prof. Alan Yuille as a visiting scholar at the CCVL (Computational Cognition, Vision, and Learning) research group, Johns Hopkins University. From December 2015 to December 2016, I was a visiting scholar at the University of Texas at San Antonio, supervised by Prof. Qi Tian. I have received the B.S. degree in electronics and information engineering from Huazhong University of Science and Technology, Wuhan, China, in 2013.  

My research interests include computer vision and machine learning. In particular, I focus on 2D/3D shape recognition, image search and classification, person re-identification, deep learning, and its applications.

Recent News 

  • On April 2018, one paper about object retrieval is accepted by TPAMI (Project). It proposes a generic re-ranking algorithm, which can deal with most commonly-used retrieval settings.
  • On March 2017, one paper about person re-identification is accepted by CVPR 2017. The proposed algorithm, called Supervised Smoothed Manifold (SSM), addresses person re-identification using affinity learning (or re-ranking, post-ranking).

Academic Activities

Reviewer for the following conferences and journals:
  • IEEE Transactions on Multimedia (TMM)
  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
  • ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)
  • Pattern Recognition (PR)
  • Computer Vision and Image Understanding (CVIU)
  • Information Sciences
  • Pattern Recognition Letters (PRL)
  • IEEE Signal Processing Letters (SPL)
  • Neurocomputing 
  • CVPR 2017/2018
  • ICCV 2017
  • ECCV 2018
  • NIPS 2016
  • ICIP 2016/2017/2018
  • ICPR 2018

Publications (full list in Google Scholar)

  • Song Bai, Xiang Bai, Qi Tian, Longin Jan Latecki. "Regularized Diffusion Process on Bidirectional Context for Object Retrieval". IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018. (PDF) (Project)
  • Song Bai, Zhichao Zhou, Jingdong Wang, Xiang Bai, Longin Jan Latecki, Qi Tian. "Ensemble Diffusion for Retrieval". IEEE Conference on Computer Vision (ICCV), Oral, 2017. (PDF(CODE)
  • Song Bai, Xiang Bai, Qi Tian. "Scalable Person Re-identification on Supervised Smoothed Manifold". IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Spotlight, 2017. (PDF(CMC_Curves(Results on GRID and Market-1501 datasets) 
  • Song Bai, Xiang Bai, Zhichao Zhou, Zhaoxiang Zhang, Qi Tian, Longin Jan Latecki. "GIFT: Towards Scalable 3D Shape Retrieval". IEEE Transactions on Multimedia (TMM), 2017. (PDF(an extension of CVPR 2016 - GIFT)  
  • Song Bai, Xiang Bai, Qi Tian, Longin Jan Latecki. "Regularized Diffusion Process for Visual Retrieval". AAAI Conference on Artificial Intelligence (AAAI), Oral, 2017. (PDF (Project)
  • Song Bai, Zhiyong Liu, Xiang  Bai. "Co-spectral for Robust Shape Clustering". Pattern Recognition Letters (PRL), 2016. (PDF)
  • Song Bai, Shaoyan  Sun, Xiang  Bai, Zhaoxiang Zhang, Qi Tian. "Smooth Neighborhood Structure Mining on Multiple Affinity Graphs with Applications to Context-sensitive Similarity". European Conference on Computer Vision (ECCV), 2016. (PDF)
  • Song Bai, Xiang Bai, Longin Jan Latecki, Qi Tian. "Multidimensional Scaling on Multiple Input Distance Matrices", 2016. (arXiv)
  • Song Bai, Xiang Bai, Wenyu Liu. "Multiple Stage Residual Model for Image Classification and Vector Compression". IEEE Transactions on Multimedia (TMM),  2016. (PDF(an extension of ACCV 2014 paper)
  • Song Bai, Xiang Bai. "Sparse Contextual Activation for Efficient Visual Re-ranking". IEEE Transactions on Image Processing (TIP), 2016. (PDF(CODE
  • Xiang Bai, Song Bai, Zhuotun Zhu, Longin Jan Latecki. "3D Shape Matching via Two Layer Coding". IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015. (PDF)
  • Xiang Bai, Song Bai, Xinggang Wang. "Neighbor Set Similarity for Fast Re-ranking". Information Sciences (INS), 2015. (PDF)
  • Song Bai, Xiang Bai, Wenyu Liu, Fabio Roli. "Neural Shape Codes for 3D Model Retrieval". Pattern Recognition Letters (PRL), 2015. (PDF)
  • Song Bai, Xinggang Wang, Cong Yao, Xiang Bai. "Multiple Stage Residual Model for Accurate Image Classification". Asian Conference on Computer Vision (ACCV), 2014. (PDF)
  • Song Bai, Xinggang Wang, Xiang Bai. "Aggregating Contour Fragments for Shape Classification". International Conference on Image Processing (ICIP), 2014. (PDF)