My research interests lie in the field of Computer Vision, Robotics, and Machine Learning. The specific topics and published papers are listed as follows.

  • Depth, Camera Pose, and Visual SLAM
    1. Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video, Jia-Wang Bian, Zhichao Li, Naiyan Wang, Huangying Zhan, Chunhua Shen, Ming-Ming Cheng, Ian Reid, NeurIPS, 2019. [Project | PDF| Code] (Enable the unsupervised depth learning from only monocular video to perform scale-consistent visual odometry in long sequences.)
    2. Visual Odometry Revisited: What Should Be Learnt?, Huangying Zhan, Chamara Saroj Weerasekera, Jia-Wang Bian, Ian Reid, IEEE ICRA, 2020 [ArXiv | Code | Demo]
  • Correspondence and Epipolar Geometry
    1. GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature correspondence, JW Bian, W Lin, Y Matsushita, SK Yeung, TD Nguyen, MM Cheng, IEEE CVPR, 2017. [Project | PDF |Code | Youtube] (The code was integrated into OpenCV library.)
    2. An Evaluation of Feature Matchers for Fundamental Matrix Estimation, Jia-Wang Bian, Yu-Huan Wu, Ji Zhao, Yun Liu, Le Zhang, Ming-Ming Cheng, Ian Reid, BMVC, 2019. [PDF | Project | Code] (An Evaluation benchmark for feature correspondence related tasks.)
  • Edge, Segmentation, and Low-level Vision
    1. Richer Convolutional Features for Edge Detection, Yun Liu, Ming-Ming Cheng, Xiaowei Hu, Jia-Wang Bian, Le Zhang, Xiang Bai, Jinhui Tang, IEEE TPAMI, 2019. [PDF | Project | Code] (Outperform the human eye’s performance on standard datasets.)
    2. HFS: Hierarchical Feature Selection for Efficient Image Segmentation, Ming-Ming Cheng, Yun Liu, Qibin Hou, Jiawang Bian, Philip Torr,  Shi-Min Hu, Zhuowen Tu, ECCV, 2016. [Project | PDF | Code] (The code was integrated into OpenCV library.)
    3. DEL: Deep Embedding Learning for Efficient Image Segmentation, Yun Liu, Peng-Tao Jiang, Vahan Petrosyan, Shi-Jie Li, Jia-Wang Bian, Le Zhang, Ming-Ming Cheng,  IJCAI, 2018. [PDF | Project |Code] (An enhancement of HFS using deep features.)
  • Regression, Ensemble, and Learning
    1. Nonlinear Regression via Deep NegativeCorrelation Learning, Le Zhang, Zenglin Shi, Ming-Ming Cheng, Yun Liu, Jia-Wang Bian, Joey Tianyi Zhou, Guoyan Zheng, Zeng Zeng, IEEE TPAMI, 2020. [PDF | Project] (Generic regression models for a wide range of applications.)
    2. Ordered or Orderless: A Revisit for Video based Person Re-Identification, Le Zhang, Zenglin Shi, Joey Tianyi Zhou, Ming-Ming Cheng, Yun Liu, Jia-Wang Bian, Zeng Zeng, Chunhua Shen [PDF] (Study the impact of frame orders on video based persion re-id performance.)