HTNet: Anchor-free Temporal Action Localization with Hierarchical
TransformersIEEE International Conference on Systems, Man and Cybernetics (SMC), 2022 |
Action Recognition by Hierarchical Mid-level Action ElementsIEEE International Conference on Computer Vision (ICCV), 2015 |
Learning to track for spatio-temporal action localizationIEEE International Conference on Computer Vision (ICCV), 2015 |
Auto-Encoding Variational BayesInternational Conference on Learning Representations (ICLR), 2013 |