A survey of video datasets for human action and activity recognition
Computer Vision and Image Understanding
| Hi-index | 0.00 |
This paper describes a task-independent controller that allowsfor an easy implementation of vision systems for processingvideo sequences. The controller does not have a fixed dataflowor any fixed steps. The dataflow is constructed by the modulesby describing themselves for the controller. During operationthe modules and their parameters are selected using anindependent decision module. This makes the system flexibleand allows comparison of different learning techniques anddecision strategies. The controller is being used by the CAVIARsystem and its current decision module is a rule-based system writtenin Clips.