Body-form and body-pose recognition with a hierarchical model of the ventral stream
Author(s)Kim, Heejung; Wohlwend, Jeremy; Leibo, Joel Z.; Poggio, Tomaso
Center for Biological and Computational Learning (CBCL)
MetadataShow full item record
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.
Ventral stream, Modularity, Computational neuroscience, HMAX
The following license files are associated with this item: