profile pic
Ernie Chu
PhD Student
Dept. Computer Science
Johns Hopkins University
Email: schu23 [at] jhu.edu
Quick links: CV / GitHub / Notes

I am a 1st-year PhD Student in Johns Hopkins University, advised by Professor Vishal Patel. My primary research focus is on computer vision, generative models and AI. Before coming into JHU, I was a Research Assistant in CITI at Academia Sinica with Professor Jun-Cheng Chen. I received my undergraduate degree in Computer Science and Engineering from National Sun Yat-sen University, where I got my start on research working with Professor Chia-Ping Chen.

My primary interest lies in machine learning and generative models. I'm currently working on video generation using image Diffusion Models. (Last updated on June 1, 2023)

Before join CITI, I also worked part-time at the Office of International Affairs, NSYSU as a full stack Web developer. I develop Web applications for exchange programs mostly using PHP, Express, Vue, and maintaining all websites across the OIA office.

I've also involved in subjects such as, computer graphics, socket programming, attribute-based encryption, data visualization, compiler design and chrome extension development during my undergraduate study.

Selected Publications

Pixel Is Not A Barrier: An Effective Evasion Attack for Pixel-Domain Diffusion Models

Chun-Yen Shih, Li-Xuan Peng, Jia-Wei Liao, Ernie Chu, Cheng-Fu Chou, Jun-Cheng Chen

AAAI Conference 2025

[Show abstract ]
[arXiv]

Generalized Image-based Deepfake Detection through Foundation Model Adaptation

Tai-Ming Huang, Yue-Hua Han, Ernie Chu, Shu-Tzu Lo, Kai-Lung Hua, Jun-Cheng Chen

ICPR 2024

[Show abstract ]
[Paper]
[GitHub]

MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance

Ernie Chu, Tzuhsuan Huang, Shuo-Yen Lin, Jun-Cheng Chen

AAAI Conference 2024

[Show abstract ]
[Project page]
[Paper]
[arXiv]
[Poster]
[GitHub]

Multi-Task Self-Blended Images for Face Forgery Detection

Po-Han Huang, Yue-Hua Han, Ernie Chu, Jun-Cheng Chen, Kai-Lung Hua

ACM Multimedia Asia 2023

[Show abstract ]
[Paper]
[Talk]

Please refer to my CV and Google Scholar profile for a full list.

Selected Projects

LoLViZ.

  • A League of Legends visualizer that helps the pro players in the challenger league exploring their matches.
  • Use Vue.js along with D3.js to create flexible and informative visualizations.
  • Utilize the Riot API and Google Firebase to retrieve the latest player and match informations.
[Project page]
[Talk]
[GitHub]

TSM-Net: Audio Time-Scale Modification with Temporal Compressing Networks

  • Use an autoencoder to compress the audio into 1024 times smaller latent representation for time-scale modification.
  • Use multi-scale discriminator to train the model for the best audio quality on all frequency bands.
[Paper]
[Project page]
[arXiv]
[Talk]
[GitHub]

NSYSU Captcha Solver

  • Use convolutional neural networks to autofill the captcha verification in the course explorer.
  • Use TensorFlow.js in Chrome extension to implement on-device inference.
[GitHub]

Secure On-line Chatting Service

  • On-line chatting service with console-based UI using ncurses.
  • Socket programming and multi-threading using C++17
  • Use attribute-based encryption to provide secure channel for messages.
[GitHub]
[Demo]
[Paper]

License Plate Verification and Warning System

  • Use ML-based object detection technology to track the license plate.
  • The barrier gate is no longer needed as the system can detect moving target.
  • All of the inferences can be done on end-device, for example Jetson Nano.
[GitHub]
[Demo]