BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:women@CL Talklets (Session 1) - Rainbow group - Marwa Mahmoud\, Fl
 ora P. Tasse
DTSTART:20151029T130000Z
DTEND:20151029T140000Z
UID:TALK61398@talks.cam.ac.uk
CONTACT:Helen Yannakoudakis
DESCRIPTION:This talklets session will feature two speakers from the Rainb
 ow group: \n\n*Speaker: Marwa Mahmoud*\n\nTitle : Automatic analysis of na
 turalistic hand-over-face gestures\n\nAbstract: One of the main factors th
 at limit the accuracy of facial analysis systems is hand occlusion. As the
  face becomes occluded\, facial features are either lost\, corrupted or er
 roneously detected. Hand-over-face occlusions are considered not only very
  common but also very challenging to handle. However\, there is empirical 
 evidence that some of these hand-over-face gestures serve as cues for reco
 gnition of cognitive mental states. In this talk\, I will present an analy
 sis of automatic detection and classification of hand-over-face gestures. 
 The proposed approach detects hand-over-face occlusions and classifies han
 d-over-face gesture descriptors in videos of natural expressions using mul
 ti-modal fusion of different state-of-the-art spatial and spatio-temporal 
 features. The detailed quantitative analysis sheds some light on the chall
 enges of automatic classification of hand-over-face gestures in natural ex
 pressions.\n\n\n*Speaker: Flora P. Tasse*\n\nTitle: 3D Points of Interest 
 and Shape retrieval\n\nAbstract: Shape saliency measures importance of poi
 nts or regions on a 3D surface. It is a useful tool for several shape anal
 ysis tasks such as shape similarity\, simplification\, and viewpoint selec
 tion. We propose a cluster-based approach to point set saliency detection\
 , a challenge since point sets lack topological information.  Our approach
  detects fine-scale salient features and uninteresting regions consistentl
 y have lower saliency values. We also present shape retrieval based on sal
 ient features detected using this method. We compare this shape retrieval 
 system to other systems that use ground-truth points and random keypoints.
  Results show that on average\, selecting many random points on 3D surface
 s produces significantly better retrieval performance than only using poin
 ts of interest. In shape retrieval\, salient points and non-salient points
  both play an important role.\n
LOCATION:Computer Laboratory\, William Gates Building\, Room FW26
END:VEVENT
END:VCALENDAR