Enhancing Table Structure Recognition via Bounding Box Guidance

The paper introduces BGTR, a Bounding Box-Guided Table Recognizer that first predicts cell bounding boxes and then uses this information to generate HTML sequences for table structure recognition. It addresses the limitation of current image-to-sequence methods that ignore explicit bounding box data, which can cause errors in complex scenes. To overcome limited natural scene table data, the authors employ progressive training and create the synthetic SNSTab dataset, achieving state‑of‑the‑art results on five benchmark datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

• benchmarks