4 datasets found

Groups: Spatio-Temporal Action Detection Organizations: No Organization Formats: JSON

Filter Results

  • UCF101-24 dataset

    The UCF101-24 dataset is a subset of the UCF101 dataset, containing 3207 videos with spatio-temporal annotations on 24 action categories.

  • UCF101D

    The UCF101D dataset is used for spatio-temporal action detection task.

  • J-HMDB

    A video dataset for action recognition, consisting of 920 videos of 21 different actions.

  • Kinetics-400 and Kinetics-600

    The Kinetics-400 and Kinetics-600 datasets are video understanding datasets used for learning rich and multi-scale spatiotemporal semantics from high-dimensional videos.