Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 1 - 10
of
31
Table 2. ER [%] for ZuBuD.
2004
"... In PAGE 3: ... The optimal parameter set for the training data is determined us- ing leaving-one-out and then the test set is classified using these parameters. The results in Table2 show that an appro- priate parameter set improves the results strongly. The first two rows give results obtained in [6] where compact DCT based local representations were used and [8] where local affine invariant regions were used.... ..."
Cited by 12
Table 2. ER [%] for ZuBuD.
2004
"... In PAGE 3: ... The optimal parameter set for the training data is determined us- ing leaving-one-out and then the test set is classified using these parameters. The results in Table2 show that an appro- priate parameter set improves the results strongly. The first two rows give results obtained in [6] where compact DCT based local representations were used and [8] where local affine invariant regions were used.... ..."
Cited by 12
Table 2. Comparison of the accuracy of the three feature sets and Meyer zu Eissen feature set on Meyer zu Eissen collection
2006
"... In PAGE 9: ... The first thought is that their representativeness of Meyer zu Eissen genre palette is not ideal. However, if we compare these accuracy rates with the accuracy results achieved by Meyer zu Eissen and Stein (2004) (see Table2 ), we can notice that accuracy values are very similar and rather close to each other, even if 1_set performs significantly better than Meyer zu Eissen feature set, and the latter performs significantly better than 2_set and 3_set. Chi-square does not say how large this difference in performance is.... ..."
Cited by 3
Table 3. ZuBuD: average subwindow test depth.
2005
Cited by 2
Table 4. ZuBuD: Summary of experimental results.
"... In PAGE 13: ... 4) are compared, the directly stored intensities versus the DCT coefficients. The results are summarised in Table4 . For both methods, recall rR is shown for R = 1 .... In PAGE 13: ... . . . 5. The recall r1 is equivalent to the percentage of correct images retrieved in rank 1. The last column shows the memory required to store the representation of the whole database of 1005 images. The last lines in Table4 show other results. The proposed retrieval system performed well, the retrieval performance was, or was close to, 100% in... ..."
Table 2. ZuBuD: average tree complexity and learning time.
2005
"... In PAGE 5: ... Here, only the ensemble of trees is used for recognition. Learning times for one single decision tree and ensem- bles of T = 25 trees are reported in Table2 , consider- ing that subwindows are in main memory. The com- plexity of tree-based method induction algorithm is of order O(NwlogNw).... ..."
Cited by 2
Table 3 Impact of ICT on higher education: a comparative study between JUST and ZU
2006
"... In PAGE 6: ... The survey was conducted by filling a hardcopy question- naire. Table3 shows the questionnaire and results. It should be noted that in Table 3, the total of agree/disagree answers does not come to 100%.... In PAGE 6: ... Table 3 shows the questionnaire and results. It should be noted that in Table3 , the total of agree/disagree answers does not come to 100%. For this reason, neutral responses were excluded.... ..."
Cited by 1
Table 1. SW/WROI-Evaluation for TSG-20, TSG-60 and ZuBuD database
"... In PAGE 3: ...valuation method (see Sec. 2.3). On the TSG-20 database we achieved the best results, obtaining a positive true accuracy of 57% for coverage of 75% ( Table1 , Section 2.3).... ..."
Results 1 - 10
of
31
