A paradigm for visual attention and importance modeling is presented. This paradigm is to conjecture some limitations on the image structure and quality, rate of change and rate information delivery needed for typical visual data delivery services. Synthesized examples of scenes coded using this model are give and linkages to related work in compression and quality assessment are described.
|Number of pages||1|
|Publication status||Published - Dec 1997|
|Event||IEEE TENCON '97: IEEE Region 10 Annual Conference. Speech and Image Technologies for Computing and Telecommunications - Queensland University of Technology, Brisbane, Australia|
Duration: 2 Dec 1997 → 4 Dec 1997
|Conference||IEEE TENCON '97|
|Abbreviated title||TENCON '97|
|Period||2/12/97 → 4/12/97|