LORE: Logical Location Regression Network for Table Structure Recognition

Table structure recognition (TSR) aims at extracting tables in images into machine-understandable formats. Recent methods solve this problem by predicting the adjacency relations of detected cell boxes, or learning to generate corresponding markup sequences from table images. However, they either count on additional heuristic rules recover structures, require a huge amount training data and time-consuming sequential decoders. In paper, we propose an alternative paradigm. We model TSR as logical location regression new framework called LORE, standing for LOgical REgression network, which first time combines together with spatial cells. Our proposed LORE is conceptually simpler, easier train more accurate than previous models other paradigms. Experiments standard benchmarks demonstrate that consistently outperforms prior arts. Code available https:// github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/DocumentUnderstanding/LORE-TSR.