Seong Hyeon Park's repositories
coot-videotext
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning
CSrankings
A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.
dino
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
icml2020
Notebook for comprehensive analysis of authors, organizations, and countries of ICML 2020 papers.
ifseg
IFSeg: Image-free Semantic Segmentation via Vision-Language Model (CVPR 2023)
img2dataset
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
jemdoc_mathjax
jemdoc with MathJax support and more
mae
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
Motionformer
Code + pre-trained models for the paper Keeping Your Eye on the Ball Trajectory Attention in Video Transformers
PatchOFA
Based on the official repository of OFA (ICML 2022)
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
pytorch_cluster
PyTorch Extension Library of Optimized Graph Cluster Algorithms
rtctunnel
build network tunnels over WebRTC
siren
Official implementation of "Implicit Neural Representations with Periodic Activation Functions"
SortNeurIPS
Sort NeurIPS by # of citations.
sshx
P2P SSH using WebRTC
tensorflow
An Open Source Machine Learning Framework for Everyone
TimeSformer
The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"
tmux-plugin-gpu
tmux plugin showing GPU usage