This page is an archive of the Deep Learning Paper Reading study.
- Personal review of papers will be updated in https://velog.io/@kunha98
| Title | Field | Link | Performance Task | Review | publication |
|---|---|---|---|---|---|
| Word2Vec(Efficient Estimation of Word Representations in Vector Space) | NLP | Paper github |
Word Similarity (benchmark) | Review | ICLR 2013 |
| ELMo(Deep contextualized word representations) | NLP | Paper github |
9 NLP tasks (benchmark) | Review | NAACL 2018 |
| Seq2Seq(Sequence to Sequence Learning with Neural Networks) | NLP | Paper github |
Machine Translation, Time Series Forecasting, Traffic Prediction (benchmark) | Review | NeurIPS 2014 |
| Transformer(Attention Is All You Need) | NLP | Paper github |
10 NLP tasks (benchmark) | Review | NeurIPS 2017 |
| GPT-1(Improving Language Understanding by Generative Pre-Training) | NLP | Paper github |
8 NLP tasks (benchmark) | Review | Preprint 2018 |
| BERT(Pre-training of Deep Bidirectional Transformers for Language Understanding) | NLP | Paper github |
18 NLP tasks (benchmark) | Review | NAACL 2019 |
| CRAFT(Character Region Awareness for Text Detection) | CV | Paper github |
Scene Text Detection (benchmark) | Review | CVPR 2019 |
| GPT-2(Language Models are Unsupervised Multitask Learners) | NLP | Paper github |
13 NLP tasks (benchmark) | Review | Preprint 2019 |
| LayoutReader: Pre-training of Text and Layout for Reading Order Detection | NLP,CV | Paper github |
Document Layout Analysis, Optical Character Recognition(OCR) (benchmark) | EMNLP 2021 | |
| ResNet(Deep Residual Learning for Image Recognition) | CV | Paper github |
10 CV tasks (benchmark) | Review | CVPR 2016 |
| EfficientNet(Rethinking Model Scaling for Convolutional Neural Networks) | CV | Paper github |
6 NLP tasks (benchmark) | Review | ICML 2019 |
| Faster R-CNN(Towards Real-Time Object Detection with Region Proposal Networks) | CV | Paper github |
Object Detection, Real-Time Object Detection, Region Proposal, Vessel Detection (benchmark) | Review | NeurIPS 2015 |
| YOLO(You Only Look Once: Unified, Real-Time Object Detection) | CV | Paper github |
Object Counting, Object Detection, Real-Time Object Detection (benchmark) | Review | CVPR 2016 |
| FCN(Fully Convolutional Networks for Semantic Segmentation) | CV | Paper github |
Real-Time Object Detection, Scene Segmentation, Semantic Segmentation, Video Semantic Segmentation (benchmark) | Review | CVPR 2015 |
| DeepLabv3+(Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation) | CV | Paper github |
Image Classification, Image Segmentation, Lesion Segmentation, Semantic Segmentation (benchmark) | Review | ECCV 2018 |