Samples from the modern dataset have the prefix "cTDaR_t1" and samples from the historical dataset start with "cTDaR_t0".Update Note:We publish a supplement dataset version in ICDAR2019_cTDaR_dataset_supplement, which is a helpful subset in terms of adjacency relations, from Prof. Cheng-Lin ...
Table Detection on ICDAR 2019 Leaderboard Dataset View by WEIGHTED AVERAGE F1-SCOREDiT-L (Cascade)DiT-L (Cascade)Other modelsModels with highest Weighted Average F1-score4. Mar9696.196.296.396.496.596.6 Filter: untagged Edit Leaderboard RankModelWeighted Average F1-scorePaperCodeResultYearTags 1...
Samples from the modern dataset have the prefix "cTDaR_t1" and samples from the historical dataset start with "cTDaR_t0". Update Note: We publish a supplement dataset version inICDAR2019_cTDaR_dataset_supplement, which is a helpful subset in terms of adjacency relations, fromProf. Cheng-Lin ...
ICDAR2019_cTDaR The ICDAR 2019 cTDaR is to evaluate the performance of methods for table detection (TRACK A) and table recognition (TRACK B). For the first track, document images containing one or several tables are provided. For TRACK B two subtracks exist: the first subtrack (B.1) prov...