Human activity analysis is an important area of computer vision and pattern recognition research with the rapid development of computing and sensing technologies such as the emergence of social network and wearable devices. It is becoming more and more critical to develop human-centered multimedia analytics including human behavior recognition, personal data mining, experiences of wearable-device applications, intelligent surveillance, semantic relationship analysis between heterogeneous multimedia.  The development of the Internet of Things opens up great potential.
Many data mining or machine learning techniques have recently been successfully developed and applied to human activity analysis. For example, smart devices (e.g. Microsoft’s SenseCam, Google Glass, smart phone, smart watches, portable EEG acquisition devices, etc.) facilitate the capture and collection of human activity multimedia; sparse representation is widely employed for human activity recognition; multi-view learning algorithms significantly boost the performance of  human re-identify; manifold learning algorithms dramatically enhance the recognition rates in human behavior analysis where there is only a few labeled samples; and deep learning has produced promising results in many human-centered applications.
Motivated by the inclination to collect a set of recent advances and results in these related topics, provide a platform for researchers to exchange their innovative ideas and attractive improvements on human activity analysis, and introduce interesting utilizations of data mining and machine learning algorithms for particular human-centered applications, this workshop will target emergent data mining methods for human activity analysis.
To summarize, this workshop welcomes a broad range of submissions developing and using data mining techniques for human activity analysis. We are especially interested in 1) theoretical advances as well as algorithm developments in data mining for human activity analysis, 2) reports of practical applications and system innovations in human activity analysis, and 3) novel data sets as test bed for new developments, preferably with implemented standard benchmarks.