Dataset Groups Activity Stream AVQA The AVQA dataset contains 57,015 videos and 57,335 question-and-answer pairs. BibTex: @dataset{Qilang_Ye_and_Zitong_Yu_and_Xin_Liu_2024, abstract = {The AVQA dataset contains 57,015 videos and 57,335 question-and-answer pairs.}, author = {Qilang Ye and Zitong Yu and Xin Liu}, doi = {10.57702/17jatdtu}, institution = {No Organization}, keyword = {'audio-visual', 'multimodal learning', 'question answering'}, month = {dec}, publisher = {TIB}, title = {AVQA}, url = {https://service.tib.eu/ldmservice/dataset/avqa}, year = {2024} }