5 datasets found

Tags: Spatio-temporally sparse

Filter Results

  • Point-VOS YouTube

    The Point-VOS YouTube dataset consists of 4.4K videos with 4.4K objects annotated with points.

  • Point-VOS DAVIS

    The Point-VOS DAVIS dataset consists of 32K videos with 600 objects annotated with points.

  • Point-VOS Kinetics

    The Point-VOS Kinetics dataset consists of 23.9K videos with 120K objects annotated with points.

  • Point-VOS Oops

    The Point-VOS Oops dataset consists of 8.4K videos with 13.1K objects annotated with points.

  • Point-VOS

    Point-VOS: Pointing Up Video Object Segmentation. Current state-of-the-art Video Object Segmentation (VOS) methods rely on dense per-object mask annotations both during training...