Dec 27, 2021 [paper-review] Donut: Document Understanding Transformer without OCR Dec 23, 2021 [paper-review] DocFormer: End-to-End Transformer for Document Understanding Dec 15, 2021 [paper-review] Learning to Understand Traffic Signs Nov 22, 2021 [paper-review] Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting Oct 07, 2021 [paper-review] EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks Sep 30, 2021 [project-review] ArcFace를 활용한 한국인 안면 인식 Aug 27, 2021 [paper-review] Swin Transformer: Hierarchical Vision Transformer using Shifted Windows Aug 10, 2021 [paper-review] An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale May 29, 2021 TFRecord 파일 읽고 쓰기