Semi-Supervised Few-Shot Atomic Action Recognition
This addresses the challenge of labor-intensive labeling and high diversity in spatio-temporal appearance for action recognition, though it appears incremental as it builds on existing few-shot and semi-supervised approaches.
The paper tackles the problem of action recognition requiring extensive labeled data by proposing a semi-supervised few-shot model for atomic actions, achieving state-of-the-art classification accuracy on representative datasets in full supervision settings.
Despite excellent progress has been made, the performance on action recognition still heavily relies on specific datasets, which are difficult to extend new action classes due to labor-intensive labeling. Moreover, the high diversity in Spatio-temporal appearance requires robust and representative action feature aggregation and attention. To address the above issues, we focus on atomic actions and propose a novel model for semi-supervised few-shot atomic action recognition. Our model features unsupervised and contrastive video embedding, loose action alignment, multi-head feature comparison, and attention-based aggregation, together of which enables action recognition with only a few training examples through extracting more representative features and allowing flexibility in spatial and temporal alignment and variations in the action. Experiments show that our model can attain high accuracy on representative atomic action datasets outperforming their respective state-of-the-art classification accuracy in full supervision setting.