Abstract
Parsing continuous human motion into meaningful segments plays an essential role in various applications. In this work, we propose a hierarchical dynamic clustering framework to derive action clusters from a sequence of local features in an unsupervised bottom-up manner. We systematically investigate the modules in this framework and particularly propose diverse temporal pooling schemes, in order to realize accurate temporal action localization. We demonstrate our method on two motion parsing tasks: temporal action segmentation and abnormal behavior detection. The experimental results indicate that the proposed framework is significantly more effective than the other related state-of-the-art methods on several datasets.
Original language | English |
---|---|
Title of host publication | Proceedings of the 29th British Machine Vision Conference (BMVC 2018) |
Number of pages | 13 |
Publication status | Published - 3 Sept 2018 |
Event | 29th British Machine Vision Conference (BMVC) - Northumbria University, Newcastle upon Tyne, United Kingdom Duration: 3 Sept 2018 → 6 Sept 2018 http://www.bmvc2018.org/index.html |
Conference
Conference | 29th British Machine Vision Conference (BMVC) |
---|---|
Abbreviated title | BMVC 2018 |
Country/Territory | United Kingdom |
City | Newcastle upon Tyne |
Period | 3/09/18 → 6/09/18 |
Internet address |