MoLa InCar AR: Dataset for Action Recognitionhttps://doi.org/10.34622/datarepositorium/1S8QVPR. P. Rodrigues, NelsonM. C. da Costa, NunoNovais, RitaFonseca, JaimeCardoso, PauloBorges, JoaoRepositório de Dados da Universidade do Minho2022-06-022022-12-07T19:01:04ZWe introduce a dataset to train human action recognition inside the vehicle focusing on violence detection. The dataset was recorded with RGB, Depth, Thermal and Event-based data. Results: The resulting dataset contains 6 400 video samples and more than 3 million frames, collected from sixteen distinct subjects. The dataset contains 58 action classes, including violent and neutral (i.e., non-violent) activities.Computer and Information ScienceEngineeringartificial intelligencecomputer visionaction recognitionEnglishBorges, J., Queirós, S., Oliveira, B. et al. (2021). A system for the generation of in-car human body pose datasets. Machine Vision and Applications, 32., doi, 10.1007/s00138-020-01131-z, https://doi.org/10.1007/s00138-020-01131-zBorges, J., Oliveira, B., Torres, H. et al. (2020). Automated Generation of Synthetic in-Car Dataset for Human Body Pose Detection. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-402-2; ISSN 2184-4321, pages 550-557., doi, 10.5220/0009316205500557, https://doi.org/10.5220/0009316205500557R. P. Rodrigues, NelsonR. P. Rodrigues, NelsonR. P. Rodrigues, NelsonR. P. Rodrigues, NelsonR. P. Rodrigues, NelsonR. P. Rodrigues, Nelson2022-05-31CC0CC0 Waiver