Dataset Groups Activity Stream MotionFollower The dataset used in the paper is not explicitly described, but it is mentioned that the authors collect 3K videos (60-90 seconds long) from the internet to train their model. BibTex: @dataset{Shuyuan_Tu_and_Qi_Dai_and_Zihao_Zhang_and_Sicheng_Xie_and_Zhi-Qi_Cheng_and_Chong_Luo_and_Xintong_Han_and_Zuxuan_Wu_and_Yu-Gang_Jiang_2024, abstract = {The dataset used in the paper is not explicitly described, but it is mentioned that the authors collect 3K videos (60-90 seconds long) from the internet to train their model.}, author = {Shuyuan Tu and Qi Dai and Zihao Zhang and Sicheng Xie and Zhi-Qi Cheng and Chong Luo and Xintong Han and Zuxuan Wu and Yu-Gang Jiang}, doi = {10.57702/67cr47k0}, institution = {No Organization}, keyword = {'diffusion models', 'motion transfer', 'video editing'}, month = {dec}, publisher = {TIB}, title = {MotionFollower}, url = {https://service.tib.eu/ldmservice/dataset/motionfollower}, year = {2024} }
