-
DAN Lab. in Myongji Univ.
- Korea in yongin
- https://kyh980909.github.io/
- https://orcid.org/0000-0001-7099-4336
Stars
DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding
[ECCV2022] MOTR: End-to-End Multiple-Object Tracking with TRansformer
Generation and evaluation of synthetic time series datasets (also, augmentations, visualizations, a collection of popular datasets) NeurIPS'24
Official Pytorch code for Open World Object Detection in the Era of Foundation Models
End-to-End Object Detection with Transformers
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery π§βπ¬
[CVPR 2023] Official Pytorch code for PROB: Probabilistic Objectness for Open World Object Detection
A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility
Real-time pose estimation accelerated with NVIDIA TensorRT
pytorch implementation of openpose including Hand and Body Pose Estimation.
Rock Paper Scissors Machine using MediaPipe Hands model and KNN.
Transform the depth-anything-v2 model to tensorrt.
Deep learning based hand gesture recognition using LSTM and MediaPipie.
This is demo code written in Python that can make any surface into an interactive touch pad.
Codebase for CVPR2020 A Local-to-Global Approach to Multi-modal Movie Scene Segmentation
[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
Model interpretability and understanding for PyTorch
A re-implementation of "Prototypical Networks for Few-shot Learning"
Riemannian Adaptive Optimization Methods with pytorch optim
λ°±μ€ μλ νΈμ μ΅μ€ν μ (Auto Git Push for BOJ)
This is an auto push repository for Baekjoon Online Judge created with [BaekjoonHub](https://github.com/BaekjoonHub/BaekjoonHub).
PIP-Net: Patch-based Intuitive Prototypes Network for Interpretable Image Classification (CVPR 2023)
Code for the TCAV ML interpretability project
Code for Machine Learning for Algorithmic Trading, 2nd edition.