### Table 1: Error statistics for #0Cxed-scale and multi-scale techniques for the OFCE based on the error measure quot;

1998

"... In PAGE 22: ... #5B7#5D, which is based on the spatiotemporal orientation of the measured vector v e relative to that of the correct vector v c #28recall that v = #281; u; v#29#29: quot; = arccos#28b v c #01 b v e #29 with b v = v p v #01 v : #2828#29 Although wehave maintained con#0Cdence measures with velocity estimates, wehave used a threshold on the Frobenius norm to discard uncertain vectors. In Table1 the results are listed for various spatiotem- poral scales. The following conclusions can be drawn: #0F First order approximation does not necessarily perform better than zeroth order for #0Cxed scales.... ..."

Cited by 18

### Table 4: Measures of the spatial localization error when performing simultaneous spatial and scale selection based on scale-space maxima of the normalized Laplacian response using different types of hybrid multi-scale representations and either lp-normalization or variance- based normalization.

2003

Cited by 10

### Table 3: Performance of the scale selection method when performing simultaneous spatial and scale selection based on scale-space maxima of the normalized Laplacian response using different types of hybrid multi-scale representations and either lp-normalization or variance- based normalization.

2003

Cited by 10

### Table 1: Parameters and results of the multi-scale algorithm.

"... In PAGE 9: ...B4CZB5 D6CTCU (in seconds); the number of candidates AC AC CB B4CZB5 AC AC after pruning and merging; and the number AC AC CB B4CZB5 CKCC AC AC of true candidates in that set. Table1 below shows the parameters and results of the test. The minimum length C4 D1CXD2 of candidates to look for was set at 210 pixels (17.... ..."

### Table 1: Parameters and results of the multi-scale algorithm.

"... In PAGE 9: ...D6CTCU (in seconds); the number of candidates AC ACCBB4CZB5AC AC after pruning and merging; and the number AC ACCBB4CZB5 CK CC AC AC of true candidates in that set. Table1 below shows the parameters and results of the test. The minimum length C4D1CXD2 of candidates to look for was set at 210 pixels (17.... ..."

### Table 5.1: Results with multi-scale feature extraction on IRMA. Multi-scale Probability model Error

### Table 1: Segmentation of synthetic tomograms: wrong assignments (%) vs. noise standard deviation and number of interacting scales. 4.3.3 Robustness Energy The robustness energy for X-ray image segmentation includes the same terms as in Equation 4. Unfortu- nately, in this case these terms alone can induce the di usion of the activation of the neurons representing a given structure outside the boundaries of that structure. This happens because Esensitivity does not include any terms which force the neurons of a region to change their state in proximity of the boundaries of the structure represented by that region. This can be overcome by including also the constraint: if a structure is not present in a given pixel, it is not present also nearby. The resulting robustness energy turns out to be

1995

"... In PAGE 7: ... The resulting images were segmented using both the single-scale and multi-scale networks described in the previous sections and then compared with the exact segmentation obtained manually with images in which noise and partial-volume e ect were absent. Table1 shows the average errors obtained in these experiments for several di erent values of and for 1{4 interacting scales. The table reveals that, in the presence of noise with relatively small standard-deviation, there are no advantages in using multi-scale segmentation.... ..."

Cited by 1

### Table 2. Performance of different features in the Brodatz Database. Re- sultsofourmethodsarelistedinthelasttworows. For each test(column),the highest classification accuracy is highlighted in bold. DBWP: Daubechies wavelet packet features; RDBWP: Rotational invariant DBWP; TGF: Tradi- tional Gabor filters; CGF: Circular Gabor filters; GMRF: Gaussian Markov random fields; ACGMRF: Anisotropic circular Gaussian MRFs; MRH: Mu- tiresolution histograms; LBP: Uniform local binary patterns; ALBP: Ad- vanced local binary patterns; SIDP: Spatial Information of Dominant Pat- terns.

"... In PAGE 4: ... The kernel for the SVM was the Gaussian Radial Basis Function (RBF). Experiments on Brodatz Database: The classification ac- curacies of different approaches under different environments are listed in Table2 . According to the experimental results, the proposed ALBP approach can already outperform the other eight methods under different conditions.... ..."

### Table 2. The effect of using a combination of feature types on test equal error rate. Key: KB = Kadir amp; Brady; MSH = Multi-scale Harris; C = Curves. All models had 6 parts and 40 detection/feature-type/image. Figure in bold is combination automatically chosen by train- ing/validation set.

2005

"... In PAGE 11: ... (b) Test equal error rate versus the number of detections/feature- type/image, N, for 8 part star models. In both cases the combinations of feature-types used was picked for each dataset from the results in Table2 and xed. 3.... ..."

Cited by 56

### Table 2: The effect of using a combination of feature types on test equal error rate. Key: KB = Kadir amp; Brady; MSH = Multi-scale Harris; C = Curves. All models had 6 parts and 40 detection/feature-type/image. Figure in bold is com- bination automatically chosen by training/validation set.

2005

"... In PAGE 5: ....3. Heterogeneous part experiments Here we xed all models to use 6 parts and have 40 detections/feature-type/frame. Table2 shows the different combinations of features which were tried, along with the best one picked by means of the training/validation set. We see a dramatic difference in performance between differ- ent feature types.... In PAGE 6: ... (b) Test equal error rate versus the number of detections/feature-type/image, N, for 8 part star mod- els. In both cases the combinations of feature-types used was picked for each dataset from the results in Table2 and xed. 3.... ..."

Cited by 56