TY - JOUR
T1 - Differential geometric representations and algorithms for some pattern recognition and computer vision problems
AU - Li, Ruonan
AU - Turaga, Pavan
AU - Srivastava, Anuj
AU - Chellappa, Rama
N1 - Funding Information:
Pavan Turaga is supported partially by NSF CCF-CIF small grant 1320267 and ONR Grant N00014-12-1-0124 sub-award Z868302. Rama Chellappa is partially supported by a MURI from the Office of Naval Research under the Grant N00014-10-1-0934.
PY - 2014/7/1
Y1 - 2014/7/1
N2 - Scene geometry, imaging laws, as well as computational mechanisms generate mathematical constraints on both raw data and computed features. In many cases, these constraints place the patterns on geometrically well-defined spaces, described as manifolds. In such cases, we argue that exploiting the geometry of these manifolds is important to our understanding of the objects and semantics in the imagery. Statistics and algorithms accounting for manifolds also yield improved performance in many vision applications. We justify these arguments by presenting our recent research efforts based on manifold theory for addressing a variety of pattern recognition and computer vision problems, including hashing on manifolds for efficient search, statistical modeling on Grassmann/Stiefel manifolds for activity recognition, discriminative learning for group motion recognition, stochastic optimization for spatio-temporal alignment, and shape matching. We also discuss the manifolds of re-parameterizations and elastic shapes, as well as applications of manifolds to face recognition and unsupervised adaptation of classification model from one domain to another.
AB - Scene geometry, imaging laws, as well as computational mechanisms generate mathematical constraints on both raw data and computed features. In many cases, these constraints place the patterns on geometrically well-defined spaces, described as manifolds. In such cases, we argue that exploiting the geometry of these manifolds is important to our understanding of the objects and semantics in the imagery. Statistics and algorithms accounting for manifolds also yield improved performance in many vision applications. We justify these arguments by presenting our recent research efforts based on manifold theory for addressing a variety of pattern recognition and computer vision problems, including hashing on manifolds for efficient search, statistical modeling on Grassmann/Stiefel manifolds for activity recognition, discriminative learning for group motion recognition, stochastic optimization for spatio-temporal alignment, and shape matching. We also discuss the manifolds of re-parameterizations and elastic shapes, as well as applications of manifolds to face recognition and unsupervised adaptation of classification model from one domain to another.
KW - Activity recognition
KW - Hashing
KW - Manifold
KW - Shape analysis
KW - Video alignment
UR - http://www.scopus.com/inward/record.url?scp=84899434046&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84899434046&partnerID=8YFLogxK
U2 - 10.1016/j.patrec.2013.09.019
DO - 10.1016/j.patrec.2013.09.019
M3 - Article
AN - SCOPUS:84899434046
SN - 0167-8655
VL - 43
SP - 3
EP - 16
JO - Pattern Recognition Letters
JF - Pattern Recognition Letters
IS - 1
ER -