- 博客(17)
- 收藏
- 关注
RSS订阅原创 【论文笔记】Read Like Humans: Autonomous,Bidirectional and Iterative Language Modeling ...(ABINet)
自然场景文字识别模型ABINet
2022-06-02 16:16:53
1383
原创 【论文笔记】BEIT: BERT Pre-Training of Image Transformers(BEIT)
基于VIT的预训练模型BEIT
2022-06-01 12:56:56
1539
原创 【论文笔记】Towards Accurate Scene Text Recognition with Semantic Resoning Networks(SRN)
自然场景文字识别模型SRN
2022-05-31 23:34:05
621
原创 【论文笔记】Spatial Dual-Modality Graph Reasoning for Key Information Extraction(SDMGR)
文档关键信息抽取模型SDMGR
2022-05-30 12:13:04
1051
原创 【论文笔记】LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
文档信息抽取模型LayoutLMv3
2022-05-29 13:09:08
4130
原创 【论文笔记】LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding
文档信息抽取模型LayoutXLM
2022-05-28 11:00:00
1190
1
原创 【论文笔记】LayoutLMv2: Multi-modal Pre-training for Visually-rich Document Understanding(LayoutLMv2)
文档信息抽取模型LayoutLMv2
2022-05-27 12:23:53
787
原创 【论文笔记】LayoutLM: Pre-training of Text and Layout for Document Image Understanding(LayoutLM)
文档信息抽取模型LayoutLM
2022-05-26 17:13:13
539
原创 【论文笔记】Training data-efficient image transformers & distillation through attention(Deit)
图像分类模型Deit
2022-05-25 12:08:03
685
原创 【论文笔记】Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
图像分类模型，新一代基于transformer的backbone swin transformer
2022-05-24 14:21:28
464
原创 【论文笔记】Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition(SAR)
自然场景文字识别模型SAR
2022-05-23 20:48:52
954
原创 【论文笔记】Tokens-to-Token VIT: Training Vision Transformers from Scratch on ImageNet(T2T-VIT)
图像分类论文T2T-VIT
2022-05-22 11:49:05
1058
原创 【论文笔记】An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale(VIT)
仅用transformer组网并用于图像分类任务的开山之作VIT
2022-05-21 09:48:58
306
原创 【论文笔记】SVTR: Scene Text Recognition with Single Visual Model
自然场景文字识别论文SVTR，PPOCRv3核心识别算法
2022-05-20 10:43:49
5839
2
原创 【论文笔记】Primitive Representation Learning for Scene Text Recognition(PREN)
文字识别论文PREN
2022-05-19 12:43:55
748
1
原创 【论文笔记】On Recognizing Texts of Arbitary Shapes with 2D Self-Attention(SATRN)
自然场景文字识别模型SATRN
2022-05-18 11:53:05
1214
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人