WeikaiKong
Just a simple guy who dreamed to do research for the rest of his life and always dreamed big.
University of Hong KongHefei, China
Pinned Repositories
ATBS
Answer Target in Background (ATBS) Dataset
ATBS
Answer Target in Background (ATBS) Dataset
Attempt-Vid2Vid-OpenDS
Final Release for AutomotiveUI'19 WIP "First Attempt to Build Realistic Driving Scenes using Video-to-video Synthesis in OpenDS Framework"
COMP3065_Computer_Vision
COMP3069_Computer_Graphics
Emotion-Estimation
Demo for Emotion Estimations
LLaMA-Adapter
Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
Skin_Disease_AI
A Python-based computer vision and AI system for skin disease recognition and diagnosis. Led end-to-end project pipeline, including data gathering, preprocessing, and training models. Utilized Keras, TensorFlow, OpenCV, and other libraries for image processing and CNN models, showcasing expertise in deep learning and machine learning techniques.
Tune-A-Video
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
VideoQA
WeikaiKong's Repositories
WeikaiKong/COMP3065_Computer_Vision
WeikaiKong/COMP3069_Computer_Graphics
WeikaiKong/ATBS
Answer Target in Background (ATBS) Dataset
WeikaiKong/Attempt-Vid2Vid-OpenDS
Final Release for AutomotiveUI'19 WIP "First Attempt to Build Realistic Driving Scenes using Video-to-video Synthesis in OpenDS Framework"
WeikaiKong/Emotion-Estimation
Demo for Emotion Estimations
WeikaiKong/LLaMA-Adapter
Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
WeikaiKong/Skin_Disease_AI
A Python-based computer vision and AI system for skin disease recognition and diagnosis. Led end-to-end project pipeline, including data gathering, preprocessing, and training models. Utilized Keras, TensorFlow, OpenCV, and other libraries for image processing and CNN models, showcasing expertise in deep learning and machine learning techniques.
WeikaiKong/Tune-A-Video
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
WeikaiKong/VideoQA