Novel Kernel-Based Recognizers of Human Actions
<p/> <p>We study unsupervised and supervised recognition of human actions in video sequences. The videos are represented by probability distributions and then meaningfully compared in a probabilistic framework. We introduce two novel approaches outperforming state-of-the-art algorithms when tested o...
Uloženo v:
| Hlavní autoři: | , , |
|---|---|
| Médium: | Artigo |
| Jazyk: | Inglês |
| Vydáno: |
SpringerOpen
2010-01-01
|
| Edice: | EURASIP Journal on Advances in Signal Processing |
| On-line přístup: | http://asp.eurasipjournals.com/content/2010/202768 |
| Tagy: |
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|