jaeyun's Projects
R-VQA: Visual Question Answering with Relation Facts
Scene Graphs with Permutation-Invariant Structured Prediction
This is a implementation of SDNE (Structural Deep Network embedding)
Jiphyeonjeon Season 1
Sentence Embeddings with BERT & XLNet
Unsupervised text tokenizer for Neural Network-based text generation.
Chatbot in 200 lines of code using TensorLayer
SK NUGU play kit ์ฉ ์ฑ๋ด ๋ชจ์ / 2019๋
NUGU๊ฐ๋ฐ๊ณต๋ชจ์ ๋ค์์ ์์.
์ฌ์ง์ ํต์์คํ
Code for using and evaluating SpanBERT.
Deep recommender models using PyTorch.
Reproducing the paper โ Deep Short Text Classification with Knowledge Powered Attention
T-Academy summary
Tags, Attributes and joint Embedding model for Visual Commonsense Reasoning
๐ถ๐ป ์ ์
๊ฐ๋ฐ์ ์ ๊ณต ์ง์ & ๊ธฐ์ ๋ฉด์ ๋ฐฑ๊ณผ์ฌ์ ๐
Technology Semantic Network (TechNet)
An Open Source Machine Learning Framework for Everyone
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
Text Classification Algorithms: A Survey
๐ฅFast State-of-the-Art Tokenizers optimized for Research and Production
Multi-head attention in PyTorch
๐ค Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
Name
Research code for "UNITER: Learning UNiversal Image-TExt Representations"
The official pytorch implementation of CVPR 2020 ``Visual Commonsense R-CNN''
Code and data of our AAAI2021 paper "A Case Study of the Shortcut Effects in Visual Commonsense Reasoning"
Code for the Scene Graph Generation part of CVPR 2019 oral paper: "Learning to Compose Dynamic Tree Structures for Visual Contexts"
VideoGraph: Recognizing Minutes-Long Human Activities in Videos, ICCV 2019 Workshop