Face detection/alignment methods have reached a satisfactory state in static images captured under arbitrary conditions. Such methods typically perform (joint) fitting for each frame and are used in commercial applications; however in the majority of the real-world scenarios the dynamic scenes are of interest. We argue that generic fitting per frame is suboptimal (it discards the informative correlation of sequential frames) and propose to learn person-specific statistics from the video to improve the generic results. To that end, we introduce a meticulously studied pipeline, which we name PD ² T, that performs person-specific detection and landmark localisation. We carry out extensive experimentation with a diverse set of i) generic fitting results, ii) different objects (human faces, animal faces) that illustrate the powerful properties of our proposed pipeline and experimentally verify that PD ² T outperforms all the compared methods.

中文翻译：

---

PD ² T：特定于人的检测，可变形的跟踪

在任意条件下拍摄的静态图像中，脸部检测/对齐方法已达到令人满意的状态。这样的方法通常对每个框架执行（联合）拟合，并用于商业应用中。但是，在大多数实际场景中，动态场景是令人感兴趣的。我们认为每帧的通用拟合次优（它丢弃了顺序帧的信息相关性），并建议从视频中学习特定于人的统计信息以改善通用结果。为此，我们引入了经过精心研究的管道，我们将其命名为PD ^2。 T，执行特定于人的检测和界标定位。我们使用i）通用拟合结果，ii）可以说明拟议管道的强大特性的不同对象（人脸，动物脸）进行广泛的实验，并通过实验验证了PD ² T优于所有比较方法。