Semantic Representation and Recognition of Continued and Recursive Human Activities
International Journal of Computer Vision
Human activity analysis: A review
ACM Computing Surveys (CSUR)
Hi-index | 0.00 |
This paper presents a methodology for semantic understanding of complex and continued human activities. A context-free grammar (CFG) based representation scheme developed earlier is extended to construct a description for continued and recursive human activities. New system recognizes recursively described high-level interactions: fighting and greeting. The system understands activities by detecting the time intervals that satisfy their semantic descriptions.