Multimedia Analysis and Synthesis

We describe novel approaches to multimedia analysis and synthesis problems. We first present the experiential sampling technique which has the ability to focus on the analysis task by making use of the contextual information. Sensor samples are used to gather information about the current environment and attention samples are used to represent the current state of attention. In our framework, the task-attended samples are inferred from experiences and maintained by a sampling based dynamical system. The multimedia analysis task can then focus on the attention samples only. Moreover, past experiences and the current environment can be used to adaptively correct and tune the attention model. This experiential sampling based analysis method appears to be a promising technique for general multimedia analysis problems. We then present the multimedia synthesis technique based on analogies. This method aims to synthesize new media objects based on some existing objects on which appropriate tr...

• Type: Conference
• Year: 2003
• Where: AUSAI
• Authors: Mohan S. Kankanhalli
• Keywords: Artificial Intelligence, Attention Samples, AUSAI 2003, Multimedia Analysis, Multimedia Synthesis Technique