论文标题
对抗域的适应性，以全天候进行动作识别
Adversarial Domain Adaptation for Action Recognition Around the Clock
论文作者
论文摘要
由于视觉监视和夜间驾驶中有许多潜在的应用，在弱光条件下识别人类行动仍然是计算机视觉中的一个困难问题。现有方法将动作识别和黑暗增强分为两个不同的步骤，以完成此任务。但是，隔离识别和增强，阻碍了对视频动作分类的时空表示的端到端学习。本文提出了一种基于领域的适应性动作识别方法，该方法在跨域设置中使用对抗性学习来学习跨域操作识别。监督的学习可以从源域（白天动作序列）上进行大量标记数据进行训练。但是，它使用深层域不变特征来对来自目标域（夜间动作序列）的许多未标记数据进行无监督的学习。可以使用标准的反向传播培训所得的增强模型，即具有附加层的标准反向传播。它可以在基础和XD145动作数据集上实现SOTA性能。
Due to the numerous potential applications in visual surveillance and nighttime driving, recognizing human action in low-light conditions remains a difficult problem in computer vision. Existing methods separate action recognition and dark enhancement into two distinct steps to accomplish this task. However, isolating the recognition and enhancement impedes end-to-end learning of the space-time representation for video action classification. This paper presents a domain adaptation-based action recognition approach that uses adversarial learning in cross-domain settings to learn cross-domain action recognition. Supervised learning can train it on a large amount of labeled data from the source domain (daytime action sequences). However, it uses deep domain invariant features to perform unsupervised learning on many unlabelled data from the target domain (night-time action sequences). The resulting augmented model, named 3D-DiNet can be trained using standard backpropagation with an additional layer. It achieves SOTA performance on InFAR and XD145 actions datasets.
