Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 1 - 10
of
37,483
Table 4. Networks trained with derotated examples, but applied at all 18 orientations.
1998
"... In PAGE 5: ... The detectors were instead applied at 18 different orientations (in incre- ments of 20 ) for each image location. Table 3 shows the results using the standard upright face detection networks of [12], and Table4 shows the results using the detection networks trained with derotated negative examples. Recall that Table 1 showed a larger number of false posi- tives compared with Table 2, due to differences in the train- ing and testing distributions.... ..."
Cited by 117
Table 4: Networks trained with derotated examples, but applied at all 18 orientations.
1998
"... In PAGE 10: ... Table 3 shows the results using the standard upright face detection networks of [Rowley et al., 1998], and Table4 shows the results using the detection networks trained with derotated negative examples. Table 3: Results of applying the standard detector networks [Rowley et al.... ..."
Cited by 117
Table 4: Networks trained with derotated examples, but applied at all 18 orientations.
1998
"... In PAGE 10: ... Table 3 shows the results using the standard upright face detection networks of [Rowley et al., 1998], and Table4 shows the results using the detection networks trained with derotated negative examples. Table 3: Results of applying the standard detector networks [Rowley et al.... ..."
Cited by 117
Table 4: Networks trained with derotated examples, but applied at all 18 orientations.
1998
"... In PAGE 10: ... Table 3 shows the results using the standard upright face detection networks of [Rowley et al., 1998], and Table4 shows the results using the detection networks trained with derotated negative examples. Table 3: Results of applying the standard detector networks [Rowley et al.... ..."
Cited by 117
Table 5.3: Accuracy of the R-C series network approximation versus the contrast real part, as predicted by the asymptotic theory in x3:2 Case A. We note the strong ow concentration around the saddle points of and C and the concentration at the minimum along the interface separating the resistive from the capacitive re- gion. However, around the magnitude of the current increases only along the y direction. Across the interface (x direction), the potential gradient is negligible so we only have weak ow concentration at . Thus, in the circuit approximation, the contribution of this region is equivalent to having a connecting wire of negligible impedance. The resistor-capacitor series network approximation was also tested for di erent locations and orientations of the saddle points in the resistive and capacitive regions. The results are not in uenced much, as expected, because location and orientation of the saddles does not a ect the network. 41
1998
Cited by 6
Table 4.12: Results of applying the upright detector networks from the previous chapter at 18 different image orientations.
1998
Cited by 644
Table 4.13: Networks trained with derotated examples, but applied at all 18 orientations.
1998
Cited by 644
TABLE II RESULTS OF THE COLUMN GENERATION METHOD. Network Node-oriented Link-oriented
Table 3: Results, fixed orientation
"... In PAGE 11: ... These results suggest that it is necessary to allow the algorithm to intelligently backtrack at least the most uncertain (with respect to heuristics) choices, on order for the resulting models to approximate to correctness. Table3 shows the results obtained by both the algorithms in case of fixed orientation. In this case, because of the higher quality of the available information (the normal attribute is used), it has appeared more natural to show the results with respect to the achievement of correct resulting models.... ..."
Table 1 Comparison between terminal and network-oriented architecture
Results 1 - 10
of
37,483
