Zheng-yuan Yang

I am a Ph.D. candidate in Computer Science at University of Rochester, Rochester, NY, advised by Prof. Jiebo Luo. I recieved my B.E. degree from University of Science and Technology of China in 2016.

This site is still under constructing, more projects will be posted.
Last updated on Aug. 2018.

Email  /  CV  /  LinkedIn

Publications

  • Zhengyuan Yang, Yuncheng Li, Jianchao Yang, Wendi Cross, Jiebo Luo, “Pose-based Body Language Recognition for Emotion Interpretation and Psychiatric Symptom Prediction," Under Submission.
  • Zhengyuan Yang, Yixuan Zhang, Jiebo Luo, “Human-Centered Emotion Recognition in Animated GIFs with Facial Landmarks," Under Submission.
  • Zhengyuan Yang, Yuncheng Li, Jianchao Yang, Jiebo Luo, “Action Recognition with Spatio-Temporal Visual Attention on Skeleton Image Sequences," IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). [PDF]
  • Zhengyuan Yang, Yuncheng Li, Jianchao Yang, Jiebo Luo, “Action Recognition with Visual Attention on Skeleton Images," International Conference on Pattern Recognition (ICPR), Beijing, China, August 2018. (oral presentation). [PDF]
  • Zhengyuan Yang, Yixuan Zhang, Jerry Yu, Junjie Cai, Jiebo Luo, “End-to-end Multi-Modal Multi-Task Vehicle Control for Self-Driving Cars with Visual Perceptions," International Conference on Pattern Recognition (ICPR), Beijing, China, August 2018. (oral presentation) Best Industry Related Paper Award (BIRPA). [PDF]
  • Zhengyuan Yang, Wendi Cross, Jiebo Luo, “Personalized pose estimation for body language understanding,” International Conference on Image Processing (ICIP), Beijing, China, September 2017. (oral presentation)
  • Research

    My research focuses on computer vision, image processing, and multimedia. Much of my research is related to understanding human in images and videos, including video action recognition, pose estimation and human parsing. Previous studies also include learning from noisy labels and general video analysis such as emotion recognition, self-driving vehicles and etc. Representative works are highlighted.

  • Click for zooming up.
  • Weakly Supervised Human Part Parsing
    Zhengyuan Yang, Yuncheng Li, Linjie Yang, Ning Zhang, Jiebo Luo
    Under Submission

    Predicting the semantic segmentation mask for each body part with weak supervisions.

  • Click for zooming up.
  • Action Recognition with Spatio-Temporal Visual Attention on Skeleton Image Sequences
    Zhengyuan Yang, Yuncheng Li, Jianchao Yang, Jiebo Luo
    ICPR, 2018; IEEE TCSVT
    Pre-Print/ UCF-Motion-Joints

    We study action recognition with 3D skeleton sequences. We propose a novel CNN based method for skeleton based action recognition. We first redesign the skeleton representations with a depth-first tree traversal order, which enhances the semantic meaning of skeleton images and better preserves the associated structural information. We then propose the idea of a two-branch attention architecture that focuses on spatio-temporal key stages and filters out unreliable joint predictions. A base attention model with the simplest structure is first introduced. By improving the structures in both branches, we further propose a Global Long-sequence Attention Network (GLAN). Furthermore, in order to adjust the kernel's spatio-temporal aspect ratios and better capture long term dependencies, we propose a Sub-Sequence Attention Network (SSAN) that takes sub-image sequences as inputs. Our experiment results on NTU RGB+D and SBU Kinetic Interaction outperforms the state-of-the-art. The model is further validated on noisy estimated poses from UCF101 and Kinetics.

  • Click for zooming up.
  • Human-Centered Emotion Recognition in Animated GIFs with Facial Landmarks
    Zhengyuan Yang, Yixuan Zhang, Jiebo Luo
    Under Submission

    Motivated by the importance of human related information in GIFs, we propose a multi-modal multi-task framework for human-centered GIF emotion recognition.

    Steering Angle Control with End-to-end Neural Networks
    Zhengyuan Yang, Jerry Yu, Junjie Cai, Jiebo Luo
    ICPR, 2018, Best Industry Related Paper Award (BIRPA)
    Demo / Pre-Print

    Taking an image or image sequences as input, predict steering angle and speed simultaneously end-to-end with neural networks.

  • Click for zooming up.
  • Pose-based Body Language Recognition for Emotion Interpretation
    Zhengyuan Yang, Yuncheng Li, Jianchao Yang, Wendi Cross, Jiebo Luo
    Under Submission
    PDF to appear

    Inspired by the human ability to infer emotions from body languages, we propose a pose-based body language recognition framework for body language recognition and emotion interpretation. In order to interpret the emotions expressed in body languages, the proposed system in the first stage generates sequences of body language predictions on untrimmed videos with a new spatio-temporal convolutional pose feature (ST-ConvPose). In the second stage, the predicted sequences are fed into a temporal network for emotion interpretation.

    Personalized Pose Estimation for Body Language Understanding
    Zhengyuan Yang, Wendi Cross, Jiebo Luo
    ICIP, 2017

    A novel model is proposed for analyzing psychiatry conversations with pose estimation methods. Various modifications are designed specific for the target dataset, which include less motion while require higher accuracy and reliability.

  • Click for zooming up.
  • Multi-view Visual Recognition with Knowledge Distillation
    Zhengyuan Yang, Yuncheng li, Jiebo Luo
    PDF to appear

    Propose to use knowledge distillation to fuse the information from the multiple views of data and ground-truth labels. A supervised multi-view learning framework is proposed to train the visual classifiers.

    Internship

    SnapChat, Venice, CA
    May - Aug 2018. Advisor: Yuncheng Li, Linjie Yang, Ning Zhang.
    Project: Weakly Supervised Human Part Parsing.

    SAIC Innovation Center, San Jose
    Jun - Aug 2017. Advisor: Jerry Yu.
    Project: Steering Angle Control with End-to-end Neural Networks.

    Teaching

    TA CS246/446 - Spring 2018
    Machine Learning

    TA CS172 - Fall 2017
    Datastructures and Algorithms

    TA CS242 - Spring 2017
    Intro to Artificial Intelligence


    © 2018 Zhengyuan Yang. All rights reserved.
    Template borrowed from Jon Barron. Thanks!