Dataset Groups Activity Stream Youtube-VOS The Youtube-VOS dataset is a large-scale benchmark for multi-object video object segmentation, containing 120 videos with dense annotation. BibTex: @dataset{Ning_Xu_and_Linjie_Yang_and_Yuchen_Fan_and_Jianchao_Yang_and_Dingcheng_Yue_and_Yuchen_Liang_and_Brian_Price_and_Scott_Cohen_and_Thomas_Huang_2024, abstract = {The Youtube-VOS dataset is a large-scale benchmark for multi-object video object segmentation, containing 120 videos with dense annotation.}, author = {Ning Xu and Linjie Yang and Yuchen Fan and Jianchao Yang and Dingcheng Yue and Yuchen Liang and Brian Price and Scott Cohen and Thomas Huang}, doi = {10.57702/qzdb98hv}, institution = {No Organization}, keyword = {'Sequence-to-sequence', 'Video Object Segmentation', 'dense annotation', 'multi-object', 'video segmentation'}, month = {dec}, publisher = {TIB}, title = {Youtube-VOS}, url = {https://service.tib.eu/ldmservice/dataset/youtube-vos}, year = {2024} }
