The current work proposes a method for age estimation of face videos. To attenuate the effect of pose, our method is based on facial $uv$ texture maps reconstructed from original frames of videos. A Wasserstein-based GAN is used to restore the full $uv$ texture presentation. Age is then predicted from the completed $uv$ mappings such that the proposed AgeGAN method simultaneously learns to capture the facial $uv$ texture map and age characteristics. To train our method, we have created the UvAge dataset, the largest video dataset of face videos with age annotation (together with identity, gender, and ethnicity labels). The dataset contains videos in-the-wild from celebrities that are recorded in a variety of imaging settings. In total, we collected 6898 video segments (788,640 frames) from 516 celebrities in 57 events. Extensive experiments demonstrate that our proposed method outperforms other advanced age estimation methods.

当前的工作提出了一种用于面部视频的年龄估计的方法。为了减弱姿势的影响，我们的方法是基于面部$üv$从视频原始帧重建的纹理贴图。基于Wasserstein的GAN用于还原全部$üv$纹理演示文稿。然后根据完成的时间预测年龄$üv$ 映射，使拟议的AgeGAN方法同时学习捕获面部 $üv$纹理图和年龄特征。为了训练我们的方法，我们创建了UvAge数据集，这是带有年龄注释（以及身份，性别和种族标签）的面部视频的最大视频数据集。数据集包含来自名人的狂野视频，这些视频以各种成像设置进行记录。我们总共在57个事件中收集了516位名人的6898个视频片段（788,640帧）。大量实验表明，我们提出的方法优于其他高级年龄估计方法。