Kinetics

doi:doi:10.57702/mez1o413

Kinetics

The Kinetics dataset is a large-scale human action dataset, which consists of 400 action classes where each category has more than 400 videos.

BibTex:

@dataset{Will_Kay_and_Joao_Carreira_and_Karen_Simonyan_and_Brian_Zhang_and_Chloe_Hillier_and_Sudheendra_Vijayanarasimhan_and_Fabio_Viola_and_Tim_Green_and_Trevor_Back_and_Paul_Natsev_2024,
    abstract = {The Kinetics dataset is a large-scale human action dataset, which consists of 400 action classes where each category has more than 400 videos.},
    author = {Will Kay and Joao Carreira and Karen Simonyan and Brian Zhang and Chloe Hillier and Sudheendra Vijayanarasimhan and Fabio Viola and Tim Green and Trevor Back and Paul Natsev},
    doi = {10.57702/mez1o413},
    institution = {No Organization},
    keyword = {'Action', 'Action Recognition', 'Human Action', 'Human action recognition', 'Kinetics', 'Recognition', 'Video', 'Video Action Recognition', 'Video Analysis', 'Video Benchmark', 'Video Understanding', 'Video clips', 'action recognition', 'audio-visual features', 'continual learning', 'human action', 'human actions', 'kinetics dataset', 'large-scale video dataset', 'motion', 'self-supervised learning', 'temporal synchronization', 'video action recognition', 'video analysis', 'video recognition', 'videos', 'zero-shot learning'},
    month = {dec},
    publisher = {TIB},
    title = {Kinetics},
    url = {https://service.tib.eu/ldmservice/dataset/kinetics},
    year = {2024}
}