Dataset Groups Activity Stream Ask-Anything A video-centric multimodal instruction dataset, composed of thousands of videos associated with detailed descriptions and conversations. BibTex: @dataset{Kunchang_Li_and_Yinan_He_and_Yi_Wang_and_Yizhuo_Li_and_Wenhai_Wang_and_Ping_Luo_and_Yali_Wang_and_Limin_Wang_and_Yu_Qiao_2024, abstract = {A video-centric multimodal instruction dataset, composed of thousands of videos associated with detailed descriptions and conversations.}, author = {Kunchang Li and Yinan He and Yi Wang and Yizhuo Li and Wenhai Wang and Ping Luo and Yali Wang and Limin Wang and Yu Qiao}, doi = {10.57702/uey6fn4q}, institution = {No Organization}, keyword = {'multimodal dialogue systems', 'video understanding', 'video-centric instruction'}, month = {dec}, publisher = {TIB}, title = {Ask-Anything}, url = {https://service.tib.eu/ldmservice/dataset/ask-anything}, year = {2024} }
