Learning discriminative space–time action parts from weakly labelled videos
Current state-of-the-art action classification methods aggregate space–time features globally, from the entire video clip under consideration. However, the features extracted may in part be due to irrelevant scene context, or movements shared amongst multiple action classes. This motivates learning...
| Main Authors: | , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Springer
2013
|