Dataset Groups Activity Stream VQAv2 dataset The VQAv2 dataset, containing open-ended questions on 265k images, with 5.4 questions per image on average. BibTex: @dataset{Yash_Goyal_and_Tejas_Khot_and_Douglas_Summers-Stay_and_Dhruv_Batra_and_Devi_Parikh_2025, abstract = {The VQAv2 dataset, containing open-ended questions on 265k images, with 5.4 questions per image on average.}, author = {Yash Goyal and Tejas Khot and Douglas Summers-Stay and Dhruv Batra and Devi Parikh}, doi = {10.57702/i1wkq4n7}, institution = {No Organization}, keyword = {'Image', 'Question Answering', 'VQAv2', 'Visual Question Answering'}, month = {jan}, publisher = {TIB}, title = {VQAv2 dataset}, url = {https://service.tib.eu/ldmservice/dataset/vqav2-dataset}, year = {2025} }
