π§ββοΈ Biography
I am currently a student majoring in Statistics at National Cheng Kung University (NCKU) in Tainan, Taiwan, and Iβm an enthusiastic researcher in the field of computer vision and deep learning.
I work as a research assistant at the Advanced Computer Vision Laboratory (ACVLAB) at the Institute of Data Science, National Cheng Kung University (NCKU), Tainan, Taiwan. I am fortunate to be advised by and work with Prof. Chih-Chung Hsu (NCKU).
Find my resume here (last updated May 23, 2024).
My research interests include:
- Image/Video Processing and Restoration
- Multi-Modal Learning and Modeling
In addition, I also enjoy cookingπ², travelingπ and playing pianoπΉ, feel free to chat with me about it if you share the same interest! π
π₯ News
- 2024/08/05: Β ππ One paper is accepted by ACMMM 2024!
- 2024/07/31: Β ππ Three papers are accepted by CVGIP 2024.
- 2024/06/12: Β ππ Our βDRCTβ have been selected for Oral Presentation in CVPR - NTIRE!
- 2024/06/06: Β ππ I receive the Top Performance Award in ACMMM 2024 (Social Media Prediction Challenge)!
- 2024/05/25: Β ππ I receive the top3% ranking (after Xiaomi, Kuaishou corp.) in SISR Challenge, CVPR 2024 (NTIRE workshop).
- 2024/05/21: Β ππ Two paper are accepted by MIPR 2024 (Acceptance rate: 19.5%).
- 2024/04/11: Β ππ Two paper are accepted by CVPRW 2024.
- 2024/03/23: Β ππ I receive the 3rd place in COVID-19 detection Challange, in conjuncted with CVPR 2024 (DEF-AI-MIA workshop).
π Selected Publications
Revisiting CLIP-Features for Learning Multi-Modal Representations from Social Posts
Submitted to ACM International Conference on Multimedia (ACMMM2024)
Chih-Chung Hsu, Chia-Ming Lee, Yu-Fan Lin, Yi-Shiuan Chou, Chih-Yu Jiang, Chi-Han Tsai
Keywords
- Vision-Language Model
-
Social Media Analysis
GRACE: Graph-Regularized Attentive Convolutional Entanglement with Laplacian Smoothing for Robust DeepFake Video Detection
Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence
Chih-Chung Hsu, Shao-Ning Chen, Mei-Hsuan Wu, Yi-Fang Wang, Chia-Ming Lee, Yi-Shiuan Chou
Keywords
- Adversarial Attack
- Robust DeepFake Detection
- Graph Convolution Network
-
Forgery Detection
DRCT: Saving Image Super-Resolution away from Information Bottleneck
IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR2024), New Trends in Image Restoration and Enhancement (NTIRE) Workshop
Chih-Chung Hsu, Chia-Ming Lee, Yi-Shiuan Chou
Keywords
- Image Super-resolution
- Information Bottleneck
A Closer Look at Spatial-Slice Features for COVID-19 Detection
IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR2024), Domain adaptation, Explainability, Fairness in AI for Medical Image Analysis (DEF-AI-MIA) Workshop
Chih-Chung Hsu, Chia-Ming Lee, Yang Fan Chiang, Yi-Shiuan Chou, Chih-Yu Jiang, Shen-Chieh Tai, Chi-Han Tsai
Keywords
- Semi-supervised learning
- COVID-19 Recognition
-
Image/Video Processing and Understanding
π Honors and Awards
- 2024.05: Top Performance Award, Socia Media Popularity Prediction Challenge, ACM International Conference on Multimedia (ACMMM).
- 2024.03: 6th place (6/195), NTIRE 2024 Image Super-Resolution (x4), IEEE Computer Vision & Pattern Recognition (CVPR).
- 2024.03: 3rd place (3/21), COVID-19 Detection Challange, Domain adaptation, Explainability and Fairness in AI for Medical Image Analysis, IEEE Computer Vision & Pattern Recognition (CVPR).
πΌ Projects
i-pet
Our project goal is to create a line bot tailored for pet owners, utilizing real-time interactions with a chatbot to assist pet owners in finding pet-friendly restaurants and attractions when they go out. In emergency situations, it can also swiftly locate nearby animal hospitals.
Pikachu Volleyball
"Pikachu Volleyball" is a game we've designed to offer you a unique volleyball experience. In this charming game, you'll join forces with friends to form teams and engage in thrilling volleyball matches against your opponents.s.
π Educations
- 2022.02 - (now), B.S. National Cheng Kung University (NCKU), the Department of Statistics, Taiwan.