Cosmo Du // Legal name: Yu Du, 杜宇

2017-    : Google
2011-2017: Ph.D. student of State Key Lab of CAD&CG
           College of Computer Science
           Zhejiang University

  Contact: answeror [att] gmail [dot] com 
Interests: Weakly supervised learning
    Ph.D.: Perceptual user interface & deep learning,
           with an emphasis on
           (1) vision-based human pose estimation and
           (2) EMG-based gesture recognition.

           CV

Publications

Semi-supervised Learning for Surface EMG-based Gesture Recognition

Yu Du, Yongkang Wong, Wenguang Jin, Wentao Wei, Yu Hu, Mohan Kankanhalli and Weidong Geng

International Joint Conference on Artificial Intelligence (IJCAI), 2017

Surface EMG-based Inter-session Gesture Recognition Enhanced by Deep Domain Adaptation

Yu Du, Wenguang Jin, Wentao Wei, Yu Hu and Weidong Geng

Sensors, 2017

We present a benchmark database of HD-sEMG recordings of hand gestures performed by 23 participants, based on an 8×16 electrode array, and propose a deep-learning-based domain adaptation framework to enhance sEMG-based inter-session gesture recognition.

Gesture Recognition by Instantaneous Surface EMG Images

Weidong Geng, Yu Du, Wenguang Jin, Wentao Wei, Yu Hu and Jiajun Li

Scientific Reports (Nature Publishing Group), 2016

We present that the patterns inside the instantaneous values of high-density sEMG enables gesture recognition to be performed merely with sEMG signals at a specific instant.

Marker-less 3D Human Motion Capture with Monocular Image Sequence and Height-Maps

Yu Du, Yongkang Wong, Yonghao Liu, Feilin Han, Yilin Gui, Zhen Wang, Mohan Kankanhalli and Weidong Geng

European Conference on Computer Vision (ECCV), 2016

We propose height-map as a type of built-in prior knowledge to detect the anatomical landmarks of a human body with a single-view calibrated camera, as well as enforce the temporal constraints on the camera and 3D poses for improved skeleton-based human pose estimation.