I am a lead research scientist at TwelveLabs. Prior to joining TwelveLabs, I worked as a research scientist at Naver AI LAB and Kakao.
ViLT. Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"
1.5kDynamic-memory-networks-plus-Pytorch. Implementation of Dynamic memory networks plus in Pytorch
127awesome-deep-art. A curated list of deep learning resources for Art
34watcha-doc2vec-regression. Sentiment regression using doc2vec on watcha movie review data
11Wildfire. Wildfire is collection of CV models written in pytorch.
5Temporal-GAN-Pytorch. Temporal Generative Adversarial Nets in Pytorch
5CorpusMaker. Extract Web Community's Corpus
4beer_galaxy. The Galaxy of Beers using doc2vec and t-SNE
4DiscoGAN-Tensorflow. Python
4Tensorflow-ML-AP. Tensorflow implementations for the examples from the book "Machine Learning: An Algorithmic Perspective" written by Stephen Marsland
3SNUBDA. Course supplement for SNU big data academy
2congressperson-sikdan. 국회의원의 식단
2SNNs-Pytorch. Implementations for "Self-normalizing networks" in Pytorch
2deepest-attack-challenge. Perform an adversarial attack on a pre-trained neural network
2paper-galaxy. papers of the galaxy
2transformers. 🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
1vision. Datasets, Transforms and Models specific to Computer Vision
1ViT-pytorch. Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)
1cv_emulate. Academic CVs that you can emulate
1Bigcamp-2017-Winter.
1between. Between of VCNC for Python
1amdim-public. Public repo for Augmented Multiscale Deep InfoMax representation learning
1bartender. HTML
1CMC. Contrastive Multiview Coding (self-supervised learning from multiple sensors/views/modalities)
1vilbert_beta. Jupyter Notebook
1dandelin.github.io. https://wonjae.kim
1