We present a novel framework, Action Progression Network (APN), for temporal
action detection (TAD) in videos. The framework locates actions in videos by
detecting the action evolution process. To encode the action evolution, we
quantify a complete action process into 101 ordered stages (0\%, 1\%, ...,
100\%), referred to as action progressions. We then train a neural network to
recognize the action progressions. The framework detects action boundaries by
detecting complete action processes in the videos, e.g., a video segment with
detected action progressions closely follow the sequence 0\%, 1\%, ..., 100\%.
The framework offers three major advantages: (1) Our neural networks are
trained end-to-end, contrasting conventional methods that optimize modules
separately; (2) The APN is trained using action frames exclusively, enabling
models to be trained on action classification datasets and robust to videos
with temporal background styles differing from those in training; (3) Our
framework effectively avoids detecting incomplete actions and excels in
detecting long-lasting actions due to the fine-grained and explicit encoding of
the temporal structure of actions. Leveraging these advantages, the APN
achieves competitive performance and significantly surpasses its counterparts
in detecting long-lasting actions. With an IoU threshold of 0.5, the APN
achieves a mean Average Precision (mAP) of 58.3\% on the THUMOS14 dataset and
98.9\% mAP on the DFMAD70 dataset.

我们提出了一个新的框架 —— 动作进化网络（APN），用于视频中的时间动作检测（TAD）。该框架通过检测动作演化过程来定位视频中的动作，并通过训练神经网络来识别动作进程。该框架具有三个主要优势：(1) 我们的神经网络端到端地训练，与优化单独模块的传统方法相反；(2) APN 仅使用动作帧进行训练，使模型能够在动作分类数据集上训练并对背景风格与训练不同的视频具有鲁棒性；(3) 我们的框架通过精细和明确地对时间结构进行编码，有效避免了检测不完整的动作，并在检测持久的动作方面表现出色。凭借这些优势，APN 在检测持久的动作方面取得了竞争性的性能，并且明显优于其他方法。在 0.5 的 IoU 阈值下，APN 在 THUMOS14 数据集上达到了 58.3％的均值平均精度（mAP），在 DFMAD70 数据集上达到了 98.9％的 mAP。