Spatially Grounded Explanations in VisionLanguage Models for Document Visual Question Answering.

@inproceedings{hormazabal-2025-spatially, author = {Maximiliano Hormaz\'{a}bal and H\'{e}ctor Cerezo-Costas and Dimosthenis Karatzas}, editor = {Jorge Carrillo de Albornoz and Alba Garcia Seco de Herrera and Julio Gonzalo and Laura Plaza and Josiane Mothe and Florina Piroi and Paolo Rosso and Damiano Spina and Guglielmo Faggioli and Nicola Ferro}, title = {{Spatially Grounded Explanations in VisionLanguage Models for Document Visual Question Answering}}, booktitle = {{Experimental IR Meets Multilinguality, Multimodality, and Interaction - 16th International Conference of the CLEF Association, CLEF 2025, Madrid, Spain, September 9-12, 2025, Proceedings}}, series = {Lecture Notes in Computer Science}, volume = {16089}, pages = {34--41}, publisher = {Springer}, year = {2025}, url = {https://doi.org/10.1007/978-3-032-04354-2_3}, doi = {https://doi.org/10.1007/978-3-032-04354-2_3} }