Uncertainty sampling for action recognition via maximizing expected average precision

12Citations
Citations of this article
15Readers
Mendeley users who have this article in their library.

Abstract

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 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.

References Powered by Scopus

HMDB: A large video database for human motion recognition

3140Citations
N/AReaders
Get full text

Action recognition with improved trajectories

3017Citations
N/AReaders
Get full text

Action recognition by dense trajectories

1938Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Pair-based uncertainty and diversity promoting early active learning for person re-identification

31Citations
N/AReaders
Get full text

Bounding uncertainty for active batch selection

13Citations
N/AReaders
Get full text

Learning adaptive criteria weights for active semi-supervised learning

12Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Wang, H., Chang, X., Shi, L., Yang, Y., & Shen, Y. D. (2018). Uncertainty sampling for action recognition via maximizing expected average precision. In IJCAI International Joint Conference on Artificial Intelligence (Vol. 2018-July, pp. 964–970). International Joint Conferences on Artificial Intelligence. https://doi.org/10.24963/ijcai.2018/134

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 7

88%

Researcher 1

13%

Readers' Discipline

Tooltip

Computer Science 6

60%

Medicine and Dentistry 2

20%

Chemistry 1

10%

Engineering 1

10%

Save time finding and organizing research with Mendeley

Sign up for free