BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250822T115805Z
LOCATION:Room 6.0D13
DTSTART;TZID=Europe/Stockholm:20250616T115000
DTEND;TZID=Europe/Stockholm:20250616T122000
UID:submissions.pasc-conference.org_PASC25_sess137_msa107@linklings.com
SUMMARY:Learning and Shape Analysis of Pose Image Manifolds
DESCRIPTION:Anuj Srivastava, Benjamin Beadett, and Shenyuan Liang (Florida
  State University)\n\nDespite the high-dimensionality of images, the sets 
 of images of 3D objects have long been hypothesized to form low-dimensiona
 l manifolds. What is the nature of such manifolds? How do they differ acro
 ss objects and object classes? Answering these questions can provide key i
 nsights in explaining and advancing success of machine learning algorithms
  in computer vision. This paper investigates  dual tasks -- learning and a
 nalyzing shapes of image manifolds -- by revisiting a classical problem of
  manifold learning but from a novel geometrical perspective. It uses geome
 try-preserving transformations to map the pose image manifolds, sets of im
 ages formed by rotating 3D objects, to low-dimensional latent spaces. The 
 pose manifolds of different objects in latent spaces are found to be nonli
 near, smooth manifolds. The paper then compares shapes of these manifolds 
 for different objects using Kendall's shape analysis, modulo rigid motions
  and global scaling, and clusters objects according to these shape metrics
 . Interestingly, pose manifolds for objects from the same classes are freq
 uently clustered together.   The geometries of image manifolds can be expl
 oited to simplify vision and image processing tasks, to predict performanc
 es, and to provide insights into learning methods.\n\nDomain: Chemistry an
 d Materials, Climate, Weather, and Earth Sciences, Life Sciences, Physics,
  Computational Methods and Applied Mathematics\n\nSession Chair: Michael K
 irby (Colorado State University)\n\n
END:VEVENT
END:VCALENDAR