Max-margin structured output regression for spatio-temporal action localization
Structured output learning has been successfully applied to object localization, where the mapping between an image and an object bounding box can be well captured. Its extension to action localization in videos, however, is much more challenging, because one needs to predict the locations of the ac...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2014
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/103011 http://hdl.handle.net/10220/19131 http://papers.nips.cc/paper/4794-max-margin-structured-output-regression-for-spatio-temporal-action-localization |