论文标题
利用自我监督的培训进行无意的行动识别
Leveraging Self-Supervised Training for Unintentional Action Recognition
论文作者
论文摘要
无意的行动是罕见的事件，难以精确定义，并且高度依赖于动作的时间上下文。在这项工作中，我们探讨了此类行动，并试图确定视频中的观点，使行动从故意到无意识过渡。我们提出了一个多阶段框架，该框架利用了固有的偏见，例如运动速度，运动方向和为了识别无意的行动。为了通过自我监督的训练来增强表示的意外行动识别任务，我们提出了时间转变，称为无意义行为固有偏见（T2IBUA）的时间转变。多阶段方法对各个帧和完整剪辑级别的时间信息进行建模。这些增强的表示表现出强烈的无意行动识别任务的表现。我们对我们的框架进行了广泛的消融研究，并报告结果对最新的结果有了显着改善。
Unintentional actions are rare occurrences that are difficult to define precisely and that are highly dependent on the temporal context of the action. In this work, we explore such actions and seek to identify the points in videos where the actions transition from intentional to unintentional. We propose a multi-stage framework that exploits inherent biases such as motion speed, motion direction, and order to recognize unintentional actions. To enhance representations via self-supervised training for the task of unintentional action recognition we propose temporal transformations, called Temporal Transformations of Inherent Biases of Unintentional Actions (T2IBUA). The multi-stage approach models the temporal information on both the level of individual frames and full clips. These enhanced representations show strong performance for unintentional action recognition tasks. We provide an extensive ablation study of our framework and report results that significantly improve over the state-of-the-art.
