jaeyun's Projects
Vision and Language and Knowledge Pretrained Model
Multi Task Vision and Language
Vision and Language Embedding model for Tasks(i use this for Visual Commonsense Reasoning)
Research Code for NeurIPS 2020 Spotlight paper "Large-Scale Adversarial Training for Vision-and-Language Representation Learning": UNITER adversarial training part
Implementation for "Large-scale Pretraining for Visual Dialog" https://arxiv.org/abs/1912.02379
Datasets, Transforms and Models specific to Computer Vision
Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"
Extract visual common sense knowledge from Flickr to expand ConceptNet and Freebase
Repository for VisualSem: a high-quality knowledge graph to support research in vision and language.
Code for the paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".
Code accompanying the CVPR 2019 paper: https://arxiv.org/abs/1812.04155
word2vec, doc2vec, GloVe implementation with Python
Computer Educational Theory Project
Pre-trained word vectors of 30+ languages
XLNet: Generalized Autoregressive Pretraining for Language Understanding
ImageNet classification using binary Convolutional Neural Networks