arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.02613cs.CV
收藏

基于类别语义的注意力动作检测

Class Semantics-based Attention for Action Detection

University of Waterloo(滑铁卢大学)

Deepak Sridhar, Niamul Quader, Srikanth Muralidharan, Yaoxin Li, Peng Dai, Juwei Lu

摘要:

动作定位网络通常被构造为特征编码器子网络和定位子网络,其中特征编码器学习将输入视频转换为对定位子网络有用的特征,以生成可靠的动作建议。虽然一些编码特征对于生成动作提议可能更有用,但是现有的动作定位方法不包括使得定位子网络能够更多地关注更重要的特征的任何注意力机制。在本文中,我们提出了一种新的注意力机制,类语义为基础的注意力(CSA),学习的时间分布的语义存在于输入视频中的动作类,找到编码的功能,这是用来提供注意更有用的编码功能的重要性分数。我们在两个流行的动作检测数据集上证明,结合我们的新的注意力机制可以在竞争性动作检测模型上提供相当大的性能增益(例如,在THUMOS-14数据集上获得47.5%的mAP,比BMN动作检测基线提高约6.2%,在ActivityNet v1.3数据集上获得36.25%的mAP。此外,包括BMN-CSA在内的CSA本地化模型系列是2021年ActivityNet行动本地化挑战赛第二名的一部分。我们的注意力机制在动作检测任务中的表现优于先前的自我注意力模块,如挤压和兴奋。我们还观察到,我们的注意力机制与这种自我注意力模块是互补的,因为当两者一起使用时,可以看到性能的改进。

英文摘要:

Action localization networks are often structured as a feature encoder sub-network and a localization sub-network, where the feature encoder learns to transform an input video to features that are useful for the localization sub-network to generate reliable action proposals. While some of the encoded features may be more useful for generating action proposals, prior action localization approaches do not include any attention mechanism that enables the localization sub-network to attend more to the more important features. In this paper, we propose a novel attention mechanism, the Class Semantics-based Attention (CSA), that learns from the temporal distribution of semantics of action classes present in an input video to find the importance scores of the encoded features, which are used to provide attention to the more useful encoded features. We demonstrate on two popular action detection datasets that incorporating our novel attention mechanism provides considerable performance gains on competitive action detection models (e.g., around 6.2% improvement over BMN action detection baseline to obtain 47.5% mAP on the THUMOS-14 dataset), and a new state-of-the-art of 36.25% mAP on the ActivityNet v1.3 dataset. Further, the CSA localization model family which includes BMN-CSA, was part of the second-placed submission at the 2021 ActivityNet action localization challenge. Our attention mechanism outperforms prior self-attention modules such as the squeeze-and-excitation in action detection task. We also observe that our attention mechanism is complementary to such self-attention modules in that performance improvements are seen when both are used together.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑