29 August 2016 Investigating factorizations in everyday activity recognition
Author Affiliations +
Proceedings Volume 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016); 100330X (2016); doi: 10.1117/12.2243847
Event: Eighth International Conference on Digital Image Processing (ICDIP 2016), 2016, Chengu, China
The proliferation of portable and even wearable visual sensing devices e.g. SenseCam, Google Glass, etc. is creating opportunities for automatic indexing and management of digitally-recorded everyday behaviour. Although the detection of semantic concepts within narrow domains has now reached a satisfactory performance level based on automatic mapping from low-level features to higher level semantics, in wearable sensing and life-logging, a diversity of everyday concepts are captured by the images and this challenges the performance of automatic concept detection and activity indexing based on this. In this paper, we investigated and compared factorization methods in utilising the semantics of concept re-occurrence and co-occurrence patterns. The factorized results are then input to activity recognition to show the efficacies in enhancing recognition performances.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Peng Wang, "Investigating factorizations in everyday activity recognition", Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 100330X (29 August 2016); doi: 10.1117/12.2243847; http://dx.doi.org/10.1117/12.2243847


Classification systems

Detection and tracking algorithms






CCD focal-plane real-time image processor
Proceedings of SPIE (September 01 1990)
A Portable Image Workstation/Transmission System
Proceedings of SPIE (November 20 1986)
A novel strain sensor based on a pair of fiber...
Proceedings of SPIE (November 11 2008)
Unresolved target detection a detailed case study of a...
Proceedings of SPIE (January 05 2004)
A new two level efficient technique for 2D image patches...
Proceedings of SPIE (September 15 2005)

Back to Top