Human action recognition based on comparative similarity
Human action recognition is a key issue in computer vision. This thesis aims to solve the problem of human action recognition, especially when there are few or no positive examples. This case is very important due to the intrinsic long-tailed distribution of categories in real world, which...
| Autor principal: | |
|---|---|
| Outros Autores: | |
| Formato: | Tese |
| Idioma: | English |
| Publicado em: |
2013
|
| Assuntos: | |
| Acesso em linha: | http://hdl.handle.net/10356/54714 |