nano-JEPA: Democratizing Video Understanding with Personal Computers
The Video Joint Embedding Predictive Architecture (V-JEPA) has shown great promise in self-supervised video representation learning. However, its substantial computational demands, often necessitates powerful GPU clusters, limit accessibility for many researchers. We introduce nano-JEPA, a streamlin...
Guardado en:
| Autores principales: | Rostagno, Adrián, Iparraguirre, Javier, Ermantraut, Joel, Tobio, Lucas, Foissac, Segundo, Aggio, Santiago, Friedrich, Guillermo Rodolfo |
|---|---|
| Formato: | Objeto de conferencia |
| Lenguaje: | Inglés |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/176281 |
| Aporte de: |
Ejemplares similares
-
On the Assessment of Information Quality in Spanish Wikipedia
por: Urquiza, Guido, et al.
Publicado: (2016) -
Teamwork Quality Prediction Using Speech-Based Features
por: Meza, Martín, et al.
Publicado: (2023) -
Graph representations for reinforcement learning
por: Schab, Esteban, et al.
Publicado: (2024) -
Towards Information Quality Assurance in Spanish: Wikipedia
por: Ferretti, Edgardo, et al.
Publicado: (2017) -
Una mirada hacia el siglo XXI : desarrollo, paz y cultura en América Latina y el Caribe /
Publicado: (1995)