Domain Adaptive Action Recognition with Integrated Self-Training and Feature Selection
Domain Adaptive Action Recognition with Integrated Self-Training and Feature Selection
复制标题
DOI：
10.1109/acpr.2013.28
复制
发表时间：
2013-11
期刊：
影响因子：
--
通讯作者：
T. Suzuki;Jien Kato;Yu Wang;K. Mase
中科院分区：
文献类型：
--
作者：
T. Suzuki;Jien Kato;Yu Wang;K. Mase
提出了一种领域自适应的动作识别方法，该方法利用一种环境（源领域）下拍摄的已标记训练视频为另一种环境（目标领域）下拍摄的视频训练动作分类器，从而大大降低了训练数据的准备成本。我们提出的方法联合利用自训练和特征选择，逐步选择这些训练数据和特征维度，有助于在目标域的训练。利用所提出的方法，可以有效地学习新环境中的视频分类器，而无需额外的标记工作。我们的方法的优越性已被多个基准数据集所证实。
This paper presents a domain adaptive action recognition approach, which utilizes labeled training videos taken under one environment (source domain) to train an action classifier for the videos taken under another environment (target domain), so that the cost for preparing training data can be greatly alleviated. Our proposed approach jointly utilizes self-training and feature selecting to gradually select these training data and feature dimensions that contribute to the training in target domain. With the proposed approach, classifiers for videos in new environments can be learned efficiently without extra labeling efforts. The superiority of our approach has been confirmed by multiple benchmark dataset.