We introduce Activity Graph Transformer, an end-to-end learnable model for temporal action localization, that receives a video as input and directly predicts a set of action instances that appear in the video. Detecting and localizing action instances in untrimmed videos requires reasoning over multiple action instances in a video. The dominant paradigms in the literature process videos temporally to either propose action regions or directly produce frame-level detections. However, sequential processing of videos is problematic when the action instances have non-sequential dependencies and/or non-linear temporal ordering, such as overlapping action instances or re-occurrence of action instances over the course of the video. In this work, we capture this non-linear temporal structure by reasoning over the videos as non-sequential entities in the form of graphs. We evaluate our model on challenging datasets: THUMOS14, Charades, and EPIC-Kitchens-100. Our results show that our proposed model outperforms the state-of-the-art by a considerable margin.

该研究提出了一种基于深度学习的Activity Graph Transformer模型，可以对视频进行端到端分析，精确定位和识别视频内的特定事件活动，并通过非线性图推理方法捕获视频内事件之间的复杂时间结构。实验结果显示此方法在三个具有挑战性的数据集上均优于当前领先的方法。

时空动作定位的活动图变换器