Title :
Combining Spatial Proximity and Temporal Continuity for Learning Invariant Representations
Author :
Kursun, O. ; Aytekin, T.
Author_Institution :
Dept. of Comput. Eng., Istanbul Univ., Istanbul, Turkey
Abstract :
Location and time are two critical aspects of most security-related events, and thus, spatiotemporal data analysis plays a central role in many security-related applications. The human brain has great capabilities of developing invariant representations of objects by taking advantage of both spatial similarity of features of objects/events and their relative timings (temporal information). Trace learning rule is one well-known solution for this problem of combining temporal relations with spatial proximity in clustering tasks such as the one performed by self organizing maps. In this work, we investigate a two stage mechanism: i) finding local clusters using spatial proximity, ii) grouping these clusters as suggested by temporal continuity patterns. We show our experimental results on a movie created from face images.
Keywords :
data analysis; face recognition; learning (artificial intelligence); pattern clustering; security of data; clustering tasks; face images; face recognition; human brain; invariant representations; local clusters; security-related events; spatial proximity; spatial similarity; spatiotemporal data analysis; temporal continuity patterns; trace learning rule; two stage mechanism; Conferences; Face; Fires; Indexes; Motion pictures; Security; Vectors; Face recognition; Invariant feature extraction; ORL face-movie; Self-organizing maps (SOM); Spatiotemporal clustering; Trace learning rule;
Conference_Titel :
Advances in Social Networks Analysis and Mining (ASONAM), 2012 IEEE/ACM International Conference on
Conference_Location :
Istanbul
Print_ISBN :
978-1-4673-2497-7
DOI :
10.1109/ASONAM.2012.157