Domain Adaptation for Upper Body Pose Tracking in Signed TV Broadcasts
Domain Adaptation for Upper Body Pose Tracking in Signed TV Broadcasts
复制标题
DOI：
10.5244/c.27.47
复制
发表时间：
2013
影响因子：
23.6
通讯作者：
James Charles;Tomas Pfister;D. Magee;David C. Hogg;Andrew Zisserman
中科院分区：
文献类型：
--
作者：
James Charles;Tomas Pfister;D. Magee;David C. Hogg;Andrew Zisserman
这项工作的目的是估计在电视广播中签名者的上身姿势。给定合适的训练数据，使用随机森林身体关节检测器来估计姿势。然而，获得这样的训练数据可能是昂贵的。本文的新奇在于一种迁移学习方法，它能够利用现有的训练数据并将其用于新的领域。我们的贡献是：（i）一种用于调整现有训练数据以通过针对具有不同外观的签名者的合成来生成新训练数据的方法，以及（ii）一种用于个性化训练数据的方法。作为一个案例研究，我们展示了如何为不同的衣服，特别是短袖和长袖衣服的手臂的外观，可以建模，以获得个人特定的跟踪器。我们证明了迁移学习和个人特定的跟踪器显着提高姿态估计性能。
The objective of this work is to estimate upper body pose for signers in TV broadcasts. Given suitable training data, the pose is estimated using a random forest body joint detector. However, obtaining such training data can be costly. The novelty of this paper is a method of transfer learning which is able to harness existing training data and use it for new domains. Our contributions are: (i) a method for adapting existing training data to generate new training data by synthesis for signers with different appearances, and (ii) a method for personalising training data. As a case study we show how the appearance of the arms for different clothing, specifically short and long sleeved clothes, can be modelled to obtain person-specific trackers. We demonstrate that the transfer learning and person specific trackers significantly improve pose estimation performance.