Difference between revisions of "2015:Audio Downbeat Estimation Results"

From MIREX Wiki
Line 52: Line 52:
 
|-
 
|-
 
| FK2
 
| FK2
| 0.556
+
| 0.557
| 0.567
+
| 0.566
| 0.564
+
| 0.568
 
|-
 
|-
 
| FK3*
 
| FK3*
| 0.622
 
 
| 0.631  
 
| 0.631  
| 0.632
+
| 0.642
 +
| 0.638
 
|-
 
|-
 
| FK4
 
| FK4
Line 67: Line 67:
 
|-
 
|-
 
| FK6*
 
| FK6*
| 0.683
+
| 0.726
| 0.669
+
| 0.721
| 0.712
+
| 0.743
 
|}
 
|}
  
Line 92: Line 92:
 
|-
 
|-
 
| FK2*
 
| FK2*
| 0.695
+
| 0.713
| 0.691
+
| 0.708
| 0.718
+
| 0.738
 
|-
 
|-
 
| FK3
 
| FK3
| 0.712
+
| 0.718
| 0.713
+
| 0.715
| 0.728
+
| 0.739
 
|-
 
|-
 
| FK4
 
| FK4
Line 107: Line 107:
 
|-
 
|-
 
| FK6
 
| FK6
| 0.643
+
| 0.665
| 0.616
+
| 0.662
| 0.697
+
| 0.687
 
|-
 
|-
 
|}
 
|}
Line 133: Line 133:
 
|-
 
|-
 
| FK2
 
| FK2
| 0.167
+
| 0.154
| 0.145
+
| 0.133
| 0.225
+
| 0.205
 
|-
 
|-
 
| FK3
 
| FK3
| 0.166
+
| 0.161
| 0.144
+
| 0.140
| 0.226
+
| 0.216
 
|-
 
|-
 
| FK4
 
| FK4
Line 148: Line 148:
 
|-
 
|-
 
| FK6
 
| FK6
| 0.192
+
| 0.173
| 0.156
+
| 0.150
| 0.282
+
| 0.232
 
|}
 
|}
  
Line 173: Line 173:
 
|-
 
|-
 
| FK2
 
| FK2
| 0.295
+
| 0.289
| 0.244
+
| 0.247
| 0.420
+
| 0.393
 
|-
 
|-
 
| FK3
 
| FK3
| 0.281
+
| 0.290
| 0.237
+
| 0.246
| 0.392
+
| 0.400
 
|-
 
|-
 
| FK4
 
| FK4
Line 188: Line 188:
 
|-
 
|-
 
| FK6
 
| FK6
| 0.258
+
| 0.287
| 0.210
+
| 0.239
| 0.391
+
| 0.414
 
|}
 
|}
  
Line 214: Line 214:
 
|-
 
|-
 
| FK2
 
| FK2
| 0.201
 
| 0.301
 
 
| 0.151  
 
| 0.151  
 +
| 0.226
 +
| 0.113
 
|-
 
|-
 
| FK3
 
| FK3
| 0.169
+
| 0.152
| 0.252
+
| 0.228
| 0.127
+
| 0.114
 
|-
 
|-
 
| FK4
 
| FK4
Line 229: Line 229:
 
|-
 
|-
 
| FK6
 
| FK6
| 0.467
+
| 0.423
| 0.698
+
| 0.634
| 0.351
+
| 0.317
 
|}
 
|}
  
Line 254: Line 254:
 
|-
 
|-
 
| FK2
 
| FK2
| 0.846
+
| 0.794
| 0.847
+
| 0.795
| 0.845
+
| 0.794
 
|-
 
|-
 
| FK3
 
| FK3
| 0.755
+
| 0.791
| 0.756
+
| 0.791
| 0.755
+
| 0.790
 
|-
 
|-
 
| FK4
 
| FK4
Line 269: Line 269:
 
|-
 
|-
 
| FK6
 
| FK6
| 0.616
+
| 0.706
| 0.617
+
| 0.706
| 0.616
+
| 0.706
 
|}
 
|}
  

Revision as of 01:40, 6 October 2015

Submitted Algorithms

Algorithms submitted to the Automatic Downbeat Estimation task
Submission code Submission name Abstract Contributors
DBDR2 DB1_no_ballroom PDF Simon Durand, Juan Bello, Bertrand David, Gael Richard
DBDR3 DB2_no_beatles PDF Simon Durand, Juan Bello, Bertrand David, Gael Richard
FK2 mixed_no_ballroom PDF Florian Krebs, Sebastian Böck
FK3 mixed_no_beatles PDF Florian Krebs, Sebastian Böck
FK4 carnatic_tracker PDF Florian Krebs, Sebastian Böck
FK6 2014_tracker_new_ss PDF Florian Krebs, Sebastian Böck

Results

Results ballroom dataset
Algorithm F-Measure Precision Recall
DBDR2 0.756 0.797 0.765
DBDR3* 0.793 0.833 0.801
FK2 0.557 0.566 0.568
FK3* 0.631 0.642 0.638
FK4 0.175 0.197 0.171
FK6* 0.726 0.721 0.743


Results beatles dataset
Algorithm F-Measure Precision Recall
DBDR2* 0.855 0.866 0.874
DBDR3 0.847 0.863 0.862
FK2* 0.713 0.708 0.738
FK3 0.718 0.715 0.739
FK4 0.178 0.191 0.178
FK6 0.665 0.662 0.687


Results carnatic dataset
Algorithm F-Measure Precision Recall
DBDR2 0.221 0.195 0.297
DBDR3 0.216 0.193 0.289
FK2 0.154 0.133 0.205
FK3 0.161 0.140 0.216
FK4 0.474 0.480 0.482
FK6 0.173 0.150 0.232


Results turkish dataset
Algorithm F-Measure Precision Recall
DBDR2 0.472 0.445 0.579
DBDR3 0.446 0.409 0.558
FK2 0.289 0.247 0.393
FK3 0.290 0.246 0.400
FK4 0.142 0.145 0.151
FK6 0.287 0.239 0.414


Results cretan dataset
Algorithm F-Measure Precision Recall
DBDR2 0.415 0.640 0.307
DBDR3 0.449 0.693 0.332
FK2 0.151 0.226 0.113
FK3 0.152 0.228 0.114
FK4 0.233 0.382 0.176
FK6 0.423 0.634 0.317


Results hjdb dataset
Algorithm F-Measure Precision Recall
DBDR2 0.691 0.725 0.676
DBDR3 0.682 0.705 0.672
FK2 0.794 0.795 0.794
FK3 0.791 0.791 0.790
FK4 0.120 0.232 0.096
FK6 0.706 0.706 0.706

*) Rows marked by an asterisk should be taken with care as in those cases overlapping test and training sets were used.

Runtime

All submissions except KSH1 finished the computations in less than 24 hours.