ICCV2023论文汇总:Document Analysis and Understanding(文档分析与理解)
———
A Benchmark for Chinese-English Scene Text Image Super-Resolution
中英场景文本图像超分辨率基准
Vision Grid Transformer for Document Layout Analysis
用于文档布局分析的 Vision Grid Transformer
Self-Supervised Character-to-Character Distillation for Text Recognition
用于文本识别的自监督字符到字符蒸馏
ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction
ICL-D3IE:具有多种演示更新的情境学习,用于文档信息提取
ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer
ESTextSpotter:通过 Transformer 中的显式协同实现更好的场景文本识别
Few Shot Font Generation via Transferring Similarity Guided Global Style and Quantization Local Style
通过传输相似性引导的全局样式和量化局部样式生成少镜头字体
Attention where it Matters: Rethinking Visual Document Understanding with Selective Region Concentration
注意重要的地方:通过选择性区域集中重新思考视觉文档理解
Document Understanding Dataset and Evaluation (DUDE)
文档理解数据集和评估(DUDE)
LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition
LISTER:用于长度不敏感场景文本识别的邻居解码
MolGrapher: Graph-based Visual Recognition of Chemical Structures
MolGrapher:基于图形的化学结构视觉识别
SCOB: Universal Text Understanding via Character-Wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap
SCOB:通过字符监督对比学习和在线文本渲染来弥合领域差距的通用文本理解
DocTr: Document Transformer for Structured Information Extraction in Documents
DocTr:用于文档中结构化信息提取的文档转换器
猜您喜欢
评论