Sooksatra Sorn, Watcharapinchai Sitapa
National Electronic and Computer Technology Center, National Science and Technology Development Agency, Khlong Nueng, Khlong Luang District, Pathum Thani 12120, Thailand.
J Imaging. 2024 Nov 29;10(12):307. doi: 10.3390/jimaging10120307.
Temporal action proposal generation is a method for extracting temporal action instances or proposals from untrimmed videos. Existing methods often struggle to segment contiguous action proposals, which are a group of action boundaries with small temporal gaps. To address this limitation, we propose incorporating an attention mechanism to weigh the importance of each proposal within a contiguous group. This mechanism leverages the gap displacement between proposals to calculate attention scores, enabling a more accurate localization of action boundaries. We evaluate our method against a state-of-the-art boundary-based baseline on ActivityNet v1.3 and Thumos 2014 datasets. The experimental results demonstrate that our approach significantly improves the performance of short-duration and contiguous action proposals, achieving an average recall of 78.22%.
时态动作提议生成是一种从未经剪辑的视频中提取时态动作实例或提议的方法。现有方法常常难以分割连续的动作提议，连续的动作提议是一组具有小时空间隙的动作边界。为解决这一局限性，我们建议纳入一种注意力机制，以权衡连续组内每个提议的重要性。该机制利用提议之间的间隙位移来计算注意力分数，从而更准确地定位动作边界。我们在ActivityNet v1.3和Thumos 2014数据集上，将我们的方法与基于边界的最新基线进行了评估。实验结果表明，我们的方法显著提高了短时长和连续动作提议的性能，平均召回率达到78.22%。
