Name
Abstract | ||
|---|---|---|
This paper presents an improved neural architecture for gaze movement control in target searching. Compared with the four-layer neural structure proposed in [14], a new movement coding neuron layer is inserted between the third layer and the fourth layer in previous structure for finer gaze motion estimation and control. The disadvantage of the previous structure is that all the large responding neurons in the third layer were involved in gaze motion synthesis by transmitting weighted responses to the movement control neurons in the fourth layer. However, these large responding neurons may produce different groups of movement estimation. To discriminate and group these neurons' movement estimation in terms of grouped connection weights form them to the movement control neurons in the fourth layer is necessary. Adding a new neuron layer between the third layer and the fourth lay is the measure that we solve this problem. Comparing experiments on target locating showed that the new architecture made the significant improvement. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/IJCNN.2011.6033521 | IJCNN |
Keywords | Field | DocType |
motion control,neural net architecture,gaze movement control,neural architecture,gaze motion synthesis,gaze motion estimation,motion estimation,four-layer neural structure,movement coding neuron layer,object detection,target searching | Computer vision,Object detection,Motion control,Architecture,Gaze,Pattern recognition,Computer science,Coding (social sciences),Artificial intelligence,Motion estimation,Neuron,Motion synthesis | Conference |
Volume | Issue | ISSN |
null | null | 2161-4393 |
ISBN | Citations | PageRank |
978-1-4244-9635-8 | 1 | 0.37 |
References | Authors | |
9 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jun Miao | 1 | 220 | 22.17 |
| Lijuan Duan | 2 | 215 | 26.13 |
| Laiyun Qing | 3 | 337 | 24.66 |
| Yuanhua Qiao | 4 | 31 | 6.68 |