"... In PAGE 9: ...4% of precision but gains 3% of recall in comparison with the former. Table4 summaries the total performance of our creation title recognition system.... ..."

"... In PAGE 7: ...06 TBimodal systems. Table3 shows the fusion results for two bimodal systems: a prosody based system fused with the voice spectral recognition system, and a voice spectrum based system fused with the face recognition system, using the same fusion methods as above. As in the monomodal systems (Table 2), matcher weighting fusion is slightly worse than the support vector machines.... ..."

"... In PAGE 7: ... Table 3 shows the fusion results for two bimodal systems: a prosody based system fused with the voice spectral recognition system, and a voice spectrum based system fused with the face recognition system, using the same fusion methods as above. As in the monomodal systems ( Table2 ), matcher weighting fusion is slightly worse than the support vector machines. Table 3.... ..."

"... In PAGE 6: ...1%). Thus, also in recognition systems that are accelerated to near real-time ( Table5 ) we observe a signi cantly improved WER of 24.8% from VTN compared to 26.... ..."

"... In PAGE 5: ... A simple integrating winner-take-all mechanism detects the correct model (see Figure 2). The equations of the system are given in Table1 ; the respective symbols are listed in Table 2. In the following sections, we will explain the system step by step: blob formation, blob mobilization, interaction between two layers, link dynamics, attention dynamics, and recognition dynamics.... ..."

"... In PAGE 5: ... It interacts with the running blob, restricts its region of motion, and can be shifted by it to the actual face position. The equations of the system are given in Table1 ; the respective symbols are listed in Table 2. In the following sections, we will explain the system step by step: blob formation, blob mobilization, interaction between two layers, link dynamics, attention dynamics, and recognition dynamics; in order to make the description clearer, parts of the equations in Table 1 corresponding to these functions will be repeated.... In PAGE 5: ... The equations of the system are given in Table 1; the respective symbols are listed in Table 2. In the following sections, we will explain the system step by step: blob formation, blob mobilization, interaction between two layers, link dynamics, attention dynamics, and recognition dynamics; in order to make the description clearer, parts of the equations in Table1 corresponding to these functions will be repeated. 2.... ..."

"... In PAGE 9: ... A preliminary test has been performed with a small training (115 images) and test (113 images) set. The results are summarized in Table1 . As we can see, results are very good, but we have to remark one important aspect.... ..."