Visual Information Extraction • Table Structure Recognition • Layout Analysis
This section is dedicated to collecting the performance SOTA models on public benchmarks within the research fields of visual information extraction (VIE) and table structure recognition (TSR). By clicking the link above, you can access detailed information about these benchmarks, including the metrics employed, and the performance achieved by the SOTA models. This compilation aims to provide a comprehensive resource for researchers and practitioners interested in evaluating and comparing the performance of different models in these domains.