Body-form and body-pose recognition with a hierarchical model of the ventral stream
Name
MIT-CSAIL-TR-2013-013.pdf
Size
456.56 KB
Format
Adobe PDF
Checksum (MD5)
f978cc36120db9f408c324c4ac3afabc
Download all files submitted through automated deposit
Author(s)
Kim, Heejung
Wohlwend, Jeremy
Leibo, Joel Z.
Poggio, Tomaso
Advisor(s)
Tomaso Poggio
Date Issued
June 18, 2013
Series/Report no.
MIT-CSAIL-TR-2013-013
CBCL-312
Abstract
When learning to recognize a novel body shape, e.g., a panda bear, we are not misled by changes in its pose. A "jumping panda bear" is readily recognized, despite having no prior visual experience with the conjunction of these concepts. Likewise, a novel pose can be estimated in an invariant way, with respect to the actor's body shape. These body and pose recognition tasks require invariance to non-generic transformations that previous models of the ventral stream do not have. We show that the addition of biologically plausible, class-specific mechanisms associating previously-viewed actors in a range of poses enables a hierarchical model of object recognition to account for this human capability. These associations could be acquired in an unsupervised manner from past experience.
Subjects
Ventral stream
Modularity
Computational neuroscience
HMAX
Terms of Use
Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported
Persistent DSpace Link
