Visual Scene Representations: Scaling and Occlusion in Convolutional Architectures.

Stefano Soatto Jingming Dong Nikolaos Karianakis

Published in: ICLR (Workshop) (2015)

Keyphrases

visual scene
vision system
visual information
object recognition
complex scenes
visual attention
natural images
video sequences
machine learning
spatial relations
natural scenes
three dimensional
domain knowledge
natural language processing
higher order
deep belief networks