Dataset Groups Activity Stream ST-VQA ST-VQA dataset consists of 23,038 images with 31,791 question-answer pairs. BibTex: @dataset{Soumya_Jahagirdar_and_Shankar_Gangisetty_and_Anand_Mishra_2025, abstract = {ST-VQA dataset consists of 23,038 images with 31,791 question-answer pairs.}, author = {Soumya Jahagirdar and Shankar Gangisetty and Anand Mishra}, doi = {10.57702/i4op6alz}, institution = {No Organization}, keyword = {'Scene text visual question answering', 'Visual question answering'}, month = {jan}, publisher = {TIB}, title = {ST-VQA}, url = {https://service.tib.eu/ldmservice/dataset/st-vqa}, year = {2025} }
