I am Qingyang Tan. I am a Ph.D. student at University of Maryland, College Park. I received the B.Eng. degree in Computer Science and Technology from University of Chinese Academy of Sciences.

Currently, I am a research assistant at UMIACS advised by Prof. Dinesh Manocha.

Before that, I conducted my undegraduate thesis in VIPL Group at Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), under the supervision of Prof. Xilin Chen and Prof. Xiujuan Chai. Before that, I interned in Human Motion Research Group at ICT, CAS, supervised by Prof. Lin Gao, Prof. Yu-Kun Lai and Prof. Shihong Xia. I also have serveral research experiences in interdisciplinary science, including UROP projects in Institute of Medical Engineering & Science and MIT Sloan School of Management of MIT, and synthetic biology project for the International Genetically Engineered Machine (iGEM) competition.

Here is my resume. Please feel free to contact me.

Interests

  • Computer Graphics
  • Computer Vision
  • Machine Learning

Education

  • Ph.D. Student in Computer Science, 2018-present

    University of Maryland, College Park

  • B.Eng. in Computer Science and Technology, 2014-2018

    University of Chinese Academy of Sciences

  • Special Student in EECS, 2017

    Massachusetts Institute of Technology

Publications

DeepMNavigate: Deep Reinforced Multi-Robot Navigation Unifying Local & Global Collision

We present a novel algorithm (DeepMNavigate) for global multi-agent navigation in dense scenarios using deep reinforcement learning. Our approach uses local and global information for each robot based on motion information maps. We demonstrate the performance on complex, dense benchmarks with narrow passages on environments with tens of agents. We highlight the algorithm’s benefits over prior learning methods and geometric decentralized algorithms in complex scenarios.

Realtime Simulation of Thin-Shell Deformable Materials using CNN-Based Mesh Embedding

We address the problem of accelerating thin-shell deformable object simulations by dimension reduction. We present a new algorithm to embed a high-dimensional configuration space of deformable objects in a low-dimensional feature space, where the configurations of objects and feature points have approximate one-to-one mapping.

Variational Autoencoders for Deforming 3D Mesh Models

We propose a novel framework which we call mesh variational autoencoders, to explore the probabilistic latent space of 3D surfaces. The framework is easy to train, and requires very few training examples. We also propose an extended model which allows flexibly adjusting the significance of different latent variables by altering the prior distribution.

Attention-based Isolated Gesture Recognition with Multi-task Learning

We propose to combine the identification of key temporal and spatial regions and sign language classification into one deep learning network architecture, using attention mechanisms to focus on effective features, and realizing end-to-end automatic sign language recognition. Our proposed architecture can enhance the efficiency of sign language recognition and maintain a comparable recognition accuracy with state-of-art work.

Mesh-based Autoencoders for Localized Deformation Component Analysis

We propose a novel mesh-based autoencoder architecture that is able to cope with meshes with irregular topology. We introduce sparse regularization in this framework, which along with convolutional operations, helps localize mesh deformations. Our framework is capable of extracting localized deformation components from mesh data sets with large-scale deformations and is robust to noise.

Contact

  • qytan@outlook.com
  • qytan@cs.umd.edu