Abstract
Occlusion is currently at the centre of analysis in machine vision. We present an approach to it that uses attention feedback to an occluded object to obtain its correct recognition. Various simulations are performed using a hierarchical visual attention feedback system, based on contrast gain (which we discuss as to its relation to possible hallucinations that could be caused by feedback). We then discuss implications of our results for object representations per se.
Original language | English |
---|---|
Title of host publication | Artificial Neural Networks – ICANN 2006 |
Subtitle of host publication | 16th International Conference, Athens, Greece, September 10-14, 2006. Proceedings, Part 1 |
Editors | Stefanos D. Kollias, Andreas Stafylopatis, Włodzisław Duch, Erkki Oja |
Place of Publication | Berlin |
Publisher | Springer Verlag |
Pages | 592-601 |
Number of pages | 10 |
ISBN (Electronic) | 978-3-540-38627-8 |
ISBN (Print) | 978-3-540-38625-4 |
DOIs | |
Publication status | Published - 2006 |
Externally published | Yes |
Event | 16th International Conference on Artificial Neural Networks - Athens, Greece Duration: 10 Sept 2006 → 14 Sept 2006 Conference number: 16 |
Publication series
Name | Lecture Notes in Computer Science |
---|---|
Volume | 4131 |
Conference
Conference | 16th International Conference on Artificial Neural Networks |
---|---|
Abbreviated title | ICANN 2006 |
Country/Territory | Greece |
City | Athens |
Period | 10/09/06 → 14/09/06 |