Dataset Groups Activity Stream VQA-CP v2 and VQA 2.0 The dataset used in the paper is VQA-CP v2 and VQA 2.0, which are two standard datasets for visual question answering. BibTex: @dataset{Yusuke_Hirota_and_Chenhui_Chu_and_Noa_Garcia_and_Mayu_Otani_and_Ittetsu_Taniguchi_and_Yuta_Nakashima_and_Takao_Onoye_2024, abstract = {The dataset used in the paper is VQA-CP v2 and VQA 2.0, which are two standard datasets for visual question answering.}, author = {Yusuke Hirota and Chenhui Chu and Noa Garcia and Mayu Otani and Ittetsu Taniguchi and Yuta Nakashima and Takao Onoye}, doi = {10.57702/k4gebcsa}, institution = {No Organization}, keyword = {'Image Description', 'Textual Representation', 'Visual Question Answering'}, month = {dec}, publisher = {TIB}, title = {VQA-CP v2 and VQA 2.0}, url = {https://service.tib.eu/ldmservice/dataset/vqa-cp-v2-and-vqa-2-0}, year = {2024} }
