论文标题
半监督的几射原子动作识别
Semi-Supervised Few-Shot Atomic Action Recognition
论文作者
论文摘要
尽管取得了出色的进步，但行动识别的性能仍然在很大程度上依赖于特定的数据集，由于劳动密集型的标签，很难扩展新的动作类别。此外，时空外观的高度多样性需要鲁棒和代表性的作用特征聚集和注意力。为了解决上述问题，我们将重点放在原子行动上，并提出了一个新型模型，用于半监督几次原子行动识别。我们的模型具有无监督和对比性的视频嵌入，松动的动作对齐，多头功能比较以及基于注意力的聚合，其中仅通过提取更具代表性的特征并允许在空间和时间对齐方面的灵活性来实现动作识别，并在动作中允许灵活性。实验表明，我们的模型可以在代表性的原子动作数据集上获得高度准确性，在完整监督环境中，其表现优于其各自的最新分类精度。
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.
