Avatar of 陳昱希.
Computer Vision Engineer
Avatar of the user.


Computer Vision Engineer
Yu-Hsi Chen has rich experience in developing computer vision and machine learning algorithms. In his recent work at Academia Sinica, he has focused on using machine learning to solve traditional computer vision and image / video processing problems. His developed NeighborTrack is a state-of-the-art single object tracking system in the field. During his school days, he used verilog on FPGA to implement the 3A system of the camera.
Academia Sinica
LUNGHWA university
Taipei City, Taiwan

Professional Background

  • Current status
    Ready to interview
  • Profession
    Software Engineer
    Machine Learning Engineer
  • Fields
    Artificial Intelligence / Machine Learning
  • Work experience
    6-10 years
  • Management
  • Skills
    Provides Feedback
    Team Work
    Machine Learning Algorithms
    Image/Video Processing
    Information Science
    Learning Network
  • Highest level of education

Job search preferences

  • Desired job type
    Interested in working remotely
  • Desired positions
    Computer Vision Engineer
  • Desired work locations
  • Freelance

Work Experience

Computer Vision Engineer

Jan 2015 - Present
. Developed and improved many state-of-the-art deep learning models CNN, C3D, Siamese Network, Transformer, and YOLO series in Python3 and PyTorch. . Top Achievement : NeighborTrack Che 22, the most accurate single-object tracking method in the world. . Research scope : Computer Vision : Object detection/tracking, Person Re-Identification and Video Stabilization. Projects: Single object tracking 03 2021 I.I.S. Research, Framework:python/pytorch • Designed a post-processing method NeighborTrack[Che+22] to introduce neighbor and temporal information to alleviate the error tracking of single object tracking. • Proved NeighborTrack is the state-of-the-art single-object tracking model as the accuracy on LaSOT is 72.2% AUC, this paper was accepted in cvprw 2023. Project page: https://github.com/franktpmvu/NeighborTrack Multiple object tracking 08 2019 I.I.S. Research, Framework:python/pytorch • Used multi-scale features and non-local net in unknown class multiple object tracking to Improve base method accuracy. • Improved the base model by 1.2x Average Precision (33% to 40%) in MOT17 dataset. Video based fall detection 04 2019 I.I.S. Research, Framework:python/tensorflow • Implemented optical flow features and data augmentation to improve the accuracy of C3D-pelee deep learning network in fall detection tasks. • Increased the accuracy of the basic network, UCF101 dataset from 57.1 to 59.5, MCF dataset from 85.4 to 87.5. Video person Re-ID 04 2018 I.I.S. Research, Team work, Framework:python/tensorflow on embedding system Jetson TX2 • Adapted the mobilenetV2 person ReID system to the embedded system Jetson TX2, which has only 7% of the computing power of the desktop computer GPU RTX 1080TI. • Participated in AISlanders’ Show 2018 and CES 2019. Emotion reading system 06 2016 I.I.S. Research, Framework:python/caffee • Combined face detection and emotion recognition to build a speaker assistance system that captures audience emotions in real time and provides feedback. Video Stabilization[CLS14] 08 2014 Master’s Thesis, Framework:MATLAB • Implemented SIFT feature matching to get the camera movement path and update it to a stable path with content-preserving warping. • Submitted to IIHMSP2014 and won the Excellent paper award. High-Dynamic Range image mapping 05 2013 Senior project, Framework:MATLAB • Developed a MATLAB-based HDR system using histogram equalization and entropy to map an HDR. Camera Automatic Exposure and Automatic White Balance 09 2012 Senior project, Team Leader, Framework: quatus verilog on embedding system DE2-70 • Implemented verilog for an AE and AWB camera system on an FPGA-based embedded system. • Led four students to participate in the FPGA contest held by Altera asia.


Master of Science
2013 - 2015
Bachelor of Computer Information and Network Engineering
2009 - 2013

Licenses & Certifications


Credential ID: N3A030123T
Issued Dec 2014
No Expiration Date