Song Bai

I am currently a research fellow in the Department of Engineering Science at the University of Oxford, and a member of Torr Vision Group (TVG) working with Prof. Philip H.S. Torr. My research interests span computer vision and machine learning with a series of topics, such as 3D shape recognition, image retrieval and classification, person re-identification and medical image analysis. In particular, my current research focus is graph neural networks and adversarial learning. I serve as an Associate Editor of Pattern Recognition.

Before that, I received my B.E. degree and Ph.D. degree from [Huazhong University of Science and Technology](http://english.hust.edu.cn) (HUST), under the supervision of Prof. [Xiang Bai](http://122.205.5.5:8071/~xbai/). I was a research scholar at the [University of Texas at San Antonio](https://www.utsa.edu/) (UTSA) supervised by Prof. [Qi Tian](http://www.cs.utsa.edu/~qitian/), and with the [Computational Cognition, Vision, and Learning](https://ccvl.jhu.edu/) (CCVL) research group at the [Johns Hopkins University](https://www.jhu.edu/) (JHU) supervised by Prof. [Alan Yuille](http://www.cs.jhu.edu/~ayuille/).

[Call for Papers] IEEE TPAMI Special Issue on Graphs in Vision and Pattern Analysis (Deadline: October 1, 2019).

Recent News

  • 2019.07.30: I will serve as a program committee member for AAAI 2020.
  • 2019.07.22: seven papers are accepted by ICCV 2019.
  • 2019.05.24: Our team Oxford-CASIA achieves the 2nd place in the 2019 DAVIS Challenge on Unsupervised Video Object Segmentation.
  • 2019.04.17: one paper about object detection (CenterNet: AP 47.0 on MS-COCO test-dev) is available in arXiv.
  • 2019.04.12: one paper about multi-organ segmentation is available in arXiv.
  • 2019.04.01: one paper about adversarial examples is available in arXiv.
  • 2019.03.05: the CODE of “Learning Attraction Field Reprensentation for Robust Line Segment Detection” is available.
  • 2019.02.25: three papers are accepted by CVPR 2019:
    • one paper about object retrieval and person re-identification (PDF);
    • one paper about line segment detection (PDF);
    • one paper about adversarial examples (PDF).
  • 2019.02.08: the CODE of “Adversarial Metric Attack for Person Re-identification” is available.
  • 2019.02.02: I will serve as a reviewer for ICCV 2019.
  • 2019.02.01: the CODE of “Learning Transferable Adversarial Examples via Ghost Networks” is available.
  • 2019.01.31: one paper about adversarial examples is available in arXiv.
  • 2019.01.25: one paper about graph neural networks is available in arXiv.
  • 2019.01.03: I am appointed as an Associate Editor (AE) of Pattern Recognition.
  • 2018.12.29: one paper about deep reinforcement learning is available in arXiv.
  • 2018.12.25: the CODE of “Learn to Interpret Atari Agents” is available.
  • 2018.12.23: I will serve as a program committee member for IJCAI 2019.
  • 2018.12.09: one paper about adversarial examples is available in arXiv.
  • 2018.12.05: one paper about line segment detection is available in arXiv.
  • 2018.10.13: one paper about object detection is accepted by TPAMI (PDF | CODE).
  • 2018.09.22: I will serve as a reviewer for CVPR 2019.
  • 2018.08.31: one paper about 3D multi-organ segmentation is accepted by WACV 2019 as an oral presentation (PDF).
  • 2018.08.29: I join the University of Oxford as a research fellow.
  • 2018.07.30: one paper about image and 3D shape retrieval is accepted by TIP (PDF).
  • 2018.07.03: one paper about person re-identification is accepted by ECCV 2018 (PDF).
  • 2018.06.21: I will serve as a program committee member for AAAI 2019.
  • 2018.06.01: one paper about object retrieval is accepted by PR (PDF).
  • 2018.05.25: I join the Inception Institute of Artificial Intelligence as a research scientist.
  • 2018.04.13: one paper about object retrieval is accepted by TPAMI (PDF | CODE).
  • 2018.03.06: one paper about 3D shape recognition is accepted by CVPR 2018 (PDF).
  • 2018.02.13: I will serve as a reviewer for ECCV 2018.
  • 2017.09.14: I will serve as a reviewer for CVPR 2018.
  • 2017.07.19: one paper about object retrieval is accepted by ICCV 2017 as an oral presentation (PDF).
  • 2017.03.18: one paper about reranking-based person re-identification is accepted by CVPR 2017 as a spotlight presentation (PDF).
  • 2017.02.04: one paper about object retrieval is accepted by AAAI 2017 as an oral presentation (PDF).