I am a PhD student in the SMU Computer Vision and Machine Learning (CVML) Lab since Aug 2023, greatly honored to be advised by Prof SUN Qianru. Prior to this, I worked as Research Associate in NTU S-Lab (2021-2023), supervised by esteemed Prof LU Shijian. Before that, I have been research intern at Tsinghua University BNSCT Lab (2018-2019), directly advised by Prof LIU Bin. I obtained my graduate and undergraduate degrees from NTU and BUPT, respectively.
- Computer vision: Text recognition & detection, image generation, unsupervised learning.
- Telecommunications: Firewall circumvention, trustable network, switching architecture.
- Art: Logo design, industrial design, Chinese literature.
- Music: Techno & trap (Magnusthemagnus, Rezz).
I am working in image generation for Beyond Visible Vision (i.e., vision out of visible spectrums, like radar and medical imagery). Before that, I have been working on unsupervised domain adaptation and unsupervised pre-training in text detection/recognition.
- Image generation for beyond visible vision [2023]
- Self-supervised learning in hand-writing/scene text recognition [2022 - 2023]
- Domain adaptation in scene text detection [2021 - 2022]
-
🕹 OpenAI-Proxy: OpenAI GPT3/GPT4 api access distribution/control/tracking tool.
-
🪪 LaTexCV: Academic C.V. template in Latex with extensive block examples.
-
🛣 VPGNet-PyTorch: Pytorch implementation of VPG Net (Caffe) for lane and road mark detection.
-
📝 NTU EEE Dissertation: Latex template for Nanyang Technological University M.Sc dissertation report.
-
🩻 SLC: Medical image segmentation & classification framework based on Keras, convenient experiment tracking.
-
🗣 A2SRT: Speech recognition tool for subtitle extracting. Good support for Indian and Singaporean English.
Research discussion via doem1997 {at} gmail.com
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent