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.
Original language | English |
---|---|
Title of host publication | Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018 |
Editors | Jérôme Lang |
Place of Publication | Marina del Rey CA USA |
Publisher | Association for the Advancement of Artificial Intelligence (AAAI) |
Pages | 964-970 |
Number of pages | 7 |
ISBN (Electronic) | 9780999241127 |
DOIs | |
Publication status | Published - 2018 |
Externally published | Yes |
Event | International Joint Conference on Artificial Intelligence 2018 - Stockholm, Sweden Duration: 13 Jul 2018 → 19 Jul 2018 Conference number: 27th https://www.ijcai.org/proceedings/2018/ https://www.ijcai.org/proceedings/2018/ (Proceedings) |
Conference
Conference | International Joint Conference on Artificial Intelligence 2018 |
---|---|
Abbreviated title | IJCAI 2018 |
Country/Territory | Sweden |
City | Stockholm |
Period | 13/07/18 → 19/07/18 |
Internet address |
Keywords
- Active Learning
- Classification
- Action Recognition
- Machine Learning
- Computer Vision