v1v2 (latest)

BoundingDocs: a Unified Dataset for Document Question Answering with Spatial Annotations

6 January 2025

Papers citing "BoundingDocs: a Unified Dataset for Document Question Answering with Spatial Annotations"

3 / 3 papers shown

Title
BBox DocVQA: A Large Scale Bounding Box Grounded Dataset for Enhancing Reasoning in Document Visual Question Answer Wenhan Yu Wang Chen Guanqiang Qi Weikang Li Yang Li Lei Sha Deguo Xia Jizhou Huang 9 0 0 19 Nov 2025
Towards Reliable and Interpretable Document Question Answering via VLMs Alessio Chen Simone Giovannini Andrea Gemelli Fabio Coppini S. Marinai 69 0 0 12 Sep 2025
DocVXQA: Context-Aware Visual Explanations for Document Question Answering Mohamed Ali Souibgui Changkyu Choi Andrey Barsky Kangsoo Jung Ernest Valveny Dimosthenis Karatzas 253 1 0 12 May 2025