Uncertainty Sampling for Action Recognition via Maximizing Expected Average Precision

Recognizing human actions in video clips has been an important topic in computer vision. Sufficient labeled data is one of the prerequisites for the good performance of action recognition algorithms. However, while abundant videos can be collected from the Internet, categorizing each video clip is tedious and even time-consuming. Active learning is one way to alleviate the labeling labor by allowing the classifier to choose the most informative unlabeled instances for manual annotation. Among various active learning algorithms, uncertainty sampling is arguably the most widely-used strategy. Conventional uncertainty sampling strategies such as entropy-based methods are usually tested under accuracy. However, in action recognition Average Precision (AP) is an acknowledged evaluation metric, which is somehow ignored in the active learning community. It is defined as the area under the precision-recall curve. In this paper, we propose a novel uncertainty sampling algorithm for action recognition using expected AP. We conduct experiments on three real-world action recognition datasets and show that our algorithm outperforms other uncertainty-based active learning algorithms.

Authors

• Hanmo Wang
• Xiaojun Chang University of Science and Technology of China Mohamed Bin Zayed University of Artificial Intelligenc
• Lei Shi State Key Laboratory of Media Convergence and Communication, CUC, Beijing 100024, China State Key Laboratory of Intelligent Game, Yangtze River Delta Research Institute of NPU, Taicang 215400, China
• Yi Yang
• Yi-Dong Shen

Keywords

• Computer Vision: Action Recognition
• Machine Learning: Active Learning
• Machine Learning: Classification