论文标题
使用伪3D凝视增强基于图像的相互视线检测
Boosting Image-based Mutual Gaze Detection using Pseudo 3D Gaze
论文作者
论文摘要
相互视线检测，即预测两个人是否相互看着对方，在理解人类相互作用中起着重要作用。在这项工作中，我们专注于基于图像的相互视线检测的任务，并提出了一种简单有效的方法来通过在训练阶段使用辅助3D注视估计任务来提高性能。我们通过使用从相互视线标签推出的伪3D凝视标签训练3D凝视估计分支，实现了性能提升，而无需额外的标签成本。通过在3D凝视估计和相互视线检测分支之间共享头部图像编码器，我们仅通过训练相互凝视检测分支来实现比学到的更好的头部特征。三个图像数据集的实验结果表明，所提出的方法在没有其他注释的情况下显着提高了检测性能。这项工作还引入了一个新的图像数据集，该数据集由33.1k对的人类组成，并在29.2k图像中用相互视线标签注释。
Mutual gaze detection, i.e., predicting whether or not two people are looking at each other, plays an important role in understanding human interactions. In this work, we focus on the task of image-based mutual gaze detection, and propose a simple and effective approach to boost the performance by using an auxiliary 3D gaze estimation task during the training phase. We achieve the performance boost without additional labeling cost by training the 3D gaze estimation branch using pseudo 3D gaze labels deduced from mutual gaze labels. By sharing the head image encoder between the 3D gaze estimation and the mutual gaze detection branches, we achieve better head features than learned by training the mutual gaze detection branch alone. Experimental results on three image datasets show that the proposed approach improves the detection performance significantly without additional annotations. This work also introduces a new image dataset that consists of 33.1K pairs of humans annotated with mutual gaze labels in 29.2K images.
