This paper addresses the problem of appearance matching across different challenges while doing visual face tracking in real-world scenarios. In this paper, FaceTrack is proposed that utilizes multiple appearance models with its long-term and short-term appearance memory for efficient face tracking. It demonstrates robustness to deformation, in-plane and out-of-plane rotation, scale, distractors and background clutter. It integrates on the advantages of the tracking-by-detection by using a face detector that tackles the drastic scale appearance change of a face. A weighted score-level fusion strategy is proposed to obtain the face tracking output having the highest fusion score by generating candidates around possible face locations. FaceTrack showcases impressive performance when initiated automatically by outperforming several state-of-the-art trackers, except Struck by a very minute margin: 0.001 in precision and 0.017 in success, respectively.

中文翻译：

---

使用多种外观模型和图形关系学习进行可靠的人脸跟踪

本文解决了在现实场景中进行视觉面部跟踪时，应对不同挑战的外观匹配问题。在本文中，提出了FaceTrack，利用其长期和短期外观记忆的多个外观模型来进行有效的面部跟踪。它展示了对变形，平面内和平面外旋转，水垢，干扰物和背景杂波的鲁棒性。它通过使用面部检测器来解决面部跟踪的急剧变化，从而整合了检测跟踪的优势。加权分数水平融合提出了一种通过在可能的面部位置附近生成候选来获得具有最高融合分数的面部跟踪输出的策略。当自动启动时，FaceTrack表现出令人印象深刻的性能，其性能优于数个最先进的跟踪器，但Struck的误差很小：分别为0.001精度和0.017成功。