Dataset Groups Activity Stream Point-VOS DAVIS The Point-VOS DAVIS dataset consists of 32K videos with 600 objects annotated with points. BibTex: @dataset{F_Perazzi_and_J_Pont-Tuset_and_B_McWilliams_and_L_Van_Gool_and_M_Gross_and_A_Sorkine-Hornung_2024, abstract = {The Point-VOS DAVIS dataset consists of 32K videos with 600 objects annotated with points.}, author = {F. Perazzi and J. Pont-Tuset and B. McWilliams and L. Van Gool and M. Gross and A. Sorkine-Hornung}, doi = {10.57702/v3aszqvc}, institution = {No Organization}, keyword = {'Point-wise annotation', 'Spatio-temporally sparse', 'Video Object Segmentation'}, month = {dec}, publisher = {TIB}, title = {Point-VOS DAVIS}, url = {https://service.tib.eu/ldmservice/dataset/point-vos-davis}, year = {2024} }
