jfmcarreira/doc_phd_thesis
1
0 Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

minor reviews

Browse Source
This commit is contained in:
jfmcarreira committed 2018-12-15 17:06:33 +00:00
1 parent 9259a6b917
commit 6379be1de2
4 files changed
+202 -271
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

022_ErrorResilience/RobustTransmissionReview.tex
+1 -1
View File
@@ -253,7 +253,7 @@ In the decoder-side, an \ac{ec} method was later used to take advantage of such
A network feedback mechanism was proposed in \cite{ErrorResilienceRPSFeb2009} to reduce error propagation at end-user decoders, by dynamically selecting the reference frame only among those correctly received.
Figure~\ref{fig2:ReferencePictureSelection} shows an example of an error resilience transcoding scheme, where the original temporal predictions (represented by the solid arrows) are transcoded to use only correctly received frames as reference, i.e., prediction represented by the dashed arrow. This is done based on network feedback.
\HIGHLIGHT{As this technique requires transcoding operations, the complexity increase with the \ac{gop} lengths, as reported in~\cite{ErrorResilienceRPSFeb2009}. Typically, the \ac{gop} length is defined taking into consideration the video application (i.e., maximum refresh period allowed) and not by the robust coding scheme.}
\HIGHLIGHT{As this technique requires transcoding operations, the complexity increase with the \ac{gop} lengths, as reported in~\cite{ErrorResilienceRPSFeb2009}. Typically, the \ac{gop} length is defined by taking into consideration the video application (i.e., synchronisation, random-access or maximum refresh period allowed) and not by the robust coding scheme.}
A more advanced scheme may be considered, where only the regions affected by mismatch predictions are processed in the compressed domain, and subsequently transcoded to limit the dependencies from lost frames.
To achieve low complexity, \ac{mv} concatenation can be used, in order to obtain new inter-predictions for error-free frames \cite{MVConcatenationAug2011}.
031_ErrorResilienceEvaluation/QualityEvaluation/PSNRvsIntra.tex
+96 -96
View File
@@ -15,24 +15,24 @@ set key top right
set yrange[28:38]
set ytics 0,2,60
set title '\TitleFont Basketball Drill'
plot '-' using 1:2 title '\KeyFont PLR=3\%' w lp ls 1, '-' using 1:2 title '\KeyFont PLR=5\%' w lp ls 2, '-' using 1:2 title '\KeyFont PLR=10\%' w lp ls 3
8 37.109
16 36.705
32 35.293
64 33.595
128 31.678
plot '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=3\%' w yerrorlines ls 1, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=5\%' w yerrorlines ls 2, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=10\%' w yerrorlines ls 3
8 37.109 0.1051
16 36.705 0.1792
32 35.293 0.2734
64 33.595 0.4373
128 31.678 0.5953
e
8 36.239
16 35.526
32 33.974
64 32.148
128 30.154
8 36.239 0.1120
16 35.526 0.1758
32 33.974 0.2307
64 32.148 0.3147
128 30.154 0.4271
e
8 34.801
16 33.680
32 31.793
64 30.041
128 28.417
8 34.801 0.1123
16 33.680 0.1213
32 31.793 0.1564
64 30.041 0.2126
128 28.417 0.2793
e
set key bottom left
@@ -40,24 +40,24 @@ set key Right
set yrange[19:39]
set ytics 19,4,60
set title '\TitleFont BQSquare'
plot '-' using 1:2 title '\KeyFont PLR=3\%' w lp ls 1, '-' using 1:2 title '\KeyFont PLR=5\%' w lp ls 2, '-' using 1:2 title '\KeyFont PLR=10\%' w lp ls 3
8 37.119
16 36.973
32 35.490
64 32.657
128 28.359
plot '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=3\%' w yerrorlines ls 1, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=5\%' w yerrorlines ls 2, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=10\%' w yerrorlines ls 3
8 37.119 0.1259
16 36.973 0.2384
32 35.490 0.4592
64 32.657 0.7187
128 28.359 1.4404
e
8 36.368
16 35.779
32 33.757
64 29.928
128 24.355
8 36.368 0.1144
16 35.779 0.2227
32 33.757 0.3847
64 29.928 0.7748
128 24.355 1.4234
e
8 34.702
16 33.624
32 30.857
64 26.249
128 19.927
8 34.702 0.1483
16 33.624 0.2208
32 30.857 0.3928
64 26.249 0.5639
128 19.927 0.7955
e
set key bottom left
@@ -65,93 +65,93 @@ set key Right
set yrange[32:38]
set ytics 32,1,38
set title '\TitleFont Cactus'
plot '-' using 1:2 title '\KeyFont PLR=3\%' w lp ls 1, '-' using 1:2 title '\KeyFont PLR=5\%' w lp ls 2, '-' using 1:2 title '\KeyFont PLR=10\%' w lp ls 3
8 37.405
16 37.400
32 37.126
64 36.228
128 34.402
plot '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=3\%' w yerrorlines ls 1, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=5\%' w yerrorlines ls 2, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=10\%' w yerrorlines ls 3
8 37.405 0.0216
16 37.400 0.0361
32 37.126 0.0582
64 36.228 0.1192
128 34.402 0.2462
e
8 37.319
16 37.270
32 36.972
64 35.899
128 33.694
8 37.319 0.0269
16 37.270 0.0355
32 36.972 0.0489
64 35.899 0.0995
128 33.694 0.2061
e
8 37.123
16 36.930
32 36.771
64 35.507
128 32.936
8 37.123 0.0249
16 36.930 0.0395
32 36.771 0.0322
64 35.507 0.0671
128 32.936 0.1456
e
set yrange[32:40]
set ytics 0,2,60
set title '\TitleFont Four People'
plot '-' using 1:2 title '\KeyFont PLR=3\%' w lp ls 1, '-' using 1:2 title '\KeyFont PLR=5\%' w lp ls 2, '-' using 1:2 title '\KeyFont PLR=10\%' w lp ls 3
8 38.133
16 39.406
32 39.348
64 38.679
128 36.869
plot '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=3\%' w yerrorlines ls 1, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=5\%' w yerrorlines ls 2, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=10\%' w yerrorlines ls 3
8 38.133 0.0378
16 39.406 0.0743
32 39.348 0.1364
64 38.679 0.2425
128 36.869 0.4818
e
8 37.945
16 39.005
32 38.656
64 37.630
128 34.773
8 37.945 0.0340
16 39.005 0.0706
32 38.656 0.1423
64 37.630 0.2079
128 34.773 0.4433
e
8 37.553
16 38.115
32 37.104
64 35.689
128 32.253
8 37.553 0.0474
16 38.115 0.0872
32 37.104 0.1742
64 35.689 0.2479
128 32.253 0.5128
e
set ytics 1,2,60
set yrange[29:39]
set title '\TitleFont Park Scene'
plot '-' using 1:2 title '\KeyFont PLR=3\%' w lp ls 1, '-' using 1:2 title '\KeyFont PLR=5\%' w lp ls 2, '-' using 1:2 title '\KeyFont PLR=10\%' w lp ls 3
8 38.358
16 38.385
32 37.981
64 36.489
128 33.335
plot '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=3\%' w yerrorlines ls 1, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=5\%' w yerrorlines ls 2, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=10\%' w yerrorlines ls 3
8 38.358 0.0332
16 38.385 0.0779
32 37.981 0.0899
64 36.489 0.1813
128 33.335 0.3957
e
8 38.166
16 38.069
32 37.657
64 35.836
128 31.918
8 38.166 0.0441
16 38.069 0.0711
32 37.657 0.0818
64 35.836 0.1715
128 31.918 0.3667
e
8 37.747
16 37.561
32 37.237
64 34.992
128 30.270
8 37.747 0.0478
16 37.561 0.0583
32 37.237 0.0573
64 34.992 0.1182
128 30.270 0.2580
e
set ytics 19,4,60
set yrange[19:35]
set title '\TitleFont People On Street'
plot '-' using 1:2 title '\KeyFont PLR=3\%' w lp ls 1, '-' using 1:2 title '\KeyFont PLR=5\%' w lp ls 2, '-' using 1:2 title '\KeyFont PLR=10\%' w lp ls 3
8 34.174
16 33.795
32 32.959
64 30.096
128 25.043
plot '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=3\%' w yerrorlines ls 1, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=5\%' w yerrorlines ls 2, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont PLR=10\%' w yerrorlines ls 3
8 34.174 0.0508
16 33.795 0.0956
32 32.959 0.1146
64 30.096 0.2403
128 25.043 0.4908
e
8 33.830
16 33.225
32 32.469
64 29.101
128 23.017
8 33.830 0.0442
16 33.225 0.0866
32 32.469 0.0902
64 29.101 0.1853
128 23.017 0.3838
e
8 33.188
16 32.404
32 31.783
64 27.646
128 20.037
8 33.188 0.0415
16 32.404 0.0550
32 31.783 0.0549
64 27.646 0.1079
128 20.037 0.2181
e
\end{gnuplot}
031_ErrorResilienceEvaluation/QualityEvaluation/PSNRvsSlices.tex
+103 -172
View File
@@ -9,81 +9,33 @@ set key width -1
set ytics 0,2,60
# set yrange[28:42]
# set ytics 0,2,60
# set title '\TitleFont Basketball Drill'
# plot '-' using 1:2 title '\KeyFont Single Slice/Frame' w lp ls 1, '-' using 1:2 title '\KeyFont 1200 Bytes/Slice' w lp ls 2, '-' using 1:2 title '\KeyFont 2400 Bytes/Slice' w lp ls 3
# 0.0 40.080
# 1.0 39.198
# 3.0 37.351
# 5.0 35.953
# 10.0 33.024
# e
# 0.0 39.900
# 1.0 38.462
# 3.0 36.705
# 5.0 35.526
# 10.0 33.680
# e
# 0.0 39.970
# 1.0 37.988
# 3.0 34.884
# 5.0 32.921
# 10.0 29.059
# e
# set yrange[31:41]
# set ytics 31,2,60
# set title '\TitleFont BQSquare'
# plot '-' using 1:2 title '\KeyFont Single Slice/Frame' w lp ls 1, '-' using 1:2 title '\KeyFont 1200 Bytes/Slice' w lp ls 2, '-' using 1:2 title '\KeyFont 2400 Bytes/Slice' w lp ls 3
# 0.0 39.430
# 1.0 38.946
# 3.0 37.851
# 5.0 36.991
# 10.0 35.078
# e
# 0.0 39.300
# 1.0 38.486
# 3.0 36.973
# 5.0 35.779
# 10.0 33.624
# e
# 0.0 39.350
# 1.0 38.468
# 3.0 36.429
# 5.0 34.475
# 10.0 31.059
# e
set yrange[30:42]
set ytics 30,2,60
set title '\TitleFont Kendo'
plot '-' using 1:2 title '\KeyFont 1200 B/S' w lp ls 1, '-' using 1:2 title '\KeyFont 2400 B/S' w lp ls 2, '-' using 1:2 title '\KeyFont 4800 B/S' w lp ls 3, '-' using 1:2 title '\KeyFont SS' w lp ls 4
plot '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 1200 B/S' w yerrorlines ls 1, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 2400 B/S' w yerrorlines ls 2, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 4800 B/S' w yerrorlines ls 3, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont SS' w yerrorlines ls 4
0.0 41.150
1.0 39.809
3.0 37.264
5.0 34.900
10.0 30.713
1.0 39.809 0.2367
3.0 37.264 0.3724
5.0 34.900 0.4403
10.0 30.713 0.3786
e
0.0 41.240
1.0 40.124
3.0 37.752
5.0 35.788
10.0 32.144
1.0 40.124 0.2416
3.0 37.752 0.4022
5.0 35.788 0.4852
10.0 32.144 0.3687
e
0.0 41.290
1.0 40.297
3.0 38.161
5.0 36.641
10.0 33.139
1.0 40.297 0.2204
3.0 38.161 0.3491
5.0 36.641 0.4578
10.0 33.139 0.4211
e
0.0 41.320
1.0 40.405
3.0 38.475
5.0 37.084
10.0 34.076
1.0 40.405 0.2244
3.0 38.475 0.3496
5.0 37.084 0.3491
10.0 34.076 0.5232
e
# unset yrange
@@ -91,169 +43,148 @@ e
set yrange[36.5:43.5]
set ytics 37,1,60
set title '\TitleFont Kimono'
plot '-' using 1:2 title '\KeyFont 1200 B/S' w lp ls 1, '-' using 1:2 title '\KeyFont 2400 B/S' w lp ls 2, '-' using 1:2 title '\KeyFont 4800 B/S' w lp ls 3, '-' using 1:2 title '\KeyFont SS' w lp ls 4
plot '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 1200 B/S' w yerrorlines ls 1, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 2400 B/S' w yerrorlines ls 2, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 4800 B/S' w yerrorlines ls 3, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont SS' w yerrorlines ls 4
0.0 42.880
1.0 42.247
3.0 41.587
5.0 41.109
10.0 40.637
1.0 42.247 0.0967
3.0 41.587 0.0914
5.0 41.109 0.0858
10.0 40.637 0.0675
e
0.0 42.900
1.0 42.140
3.0 41.143
5.0 40.650
10.0 39.841
1.0 42.140 0.1362
3.0 41.143 0.1339
5.0 40.650 0.0864
10.0 39.841 0.1008
e
0.0 42.910
1.0 42.001
3.0 40.519
5.0 39.585
10.0 38.254
1.0 42.001 0.1211
3.0 40.519 0.1781
5.0 39.585 0.1673
10.0 38.254 0.1458
e
0.0 42.940
1.0 42.180
3.0 40.589
5.0 39.315
10.0 36.789
1.0 42.180 0.1794
3.0 40.589 0.2942
5.0 39.315 0.3178
10.0 36.789 0.4394
e
# set title '\TitleFont Kristen Sara'
# plot '-' using 1:2 title '\KeyFont Single Slice/Frame' w lp ls 1, '-' using 1:2 title '\KeyFont 1200 Bytes/Slice' w lp ls 2, '-' using 1:2 title '\KeyFont 2400 Bytes/Slice' w lp ls 3
# 0.0 40.650
# 1.0 40.488
# 3.0 40.121
# 5.0 39.782
# 10.0 38.861
# e
# 0.0 40.500
# 1.0 40.328
# 3.0 39.840
# 5.0 39.395
# 10.0 38.567
# e
# 0.0 40.550
# 1.0 40.316
# 3.0 39.861
# 5.0 39.241
# 10.0 38.111
# e
set yrange[34:41]
set ytics 34,1,60
set title '\TitleFont Park Scene'
plot '-' using 1:2 title '\KeyFont 1200 B/S' w lp ls 1, '-' using 1:2 title '\KeyFont 2400 B/S' w lp ls 2, '-' using 1:2 title '\KeyFont 4800 B/S' w lp ls 3, '-' using 1:2 title '\KeyFont SS' w lp ls 4
plot '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 1200 B/S' w yerrorlines ls 1, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 2400 B/S' w yerrorlines ls 2, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 4800 B/S' w yerrorlines ls 3, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont SS' w yerrorlines ls 4
0.0 39.470
1.0 38.905
3.0 38.385
5.0 38.069
10.0 37.561
1.0 38.905 0.0851
3.0 38.385 0.0779
5.0 38.069 0.0711
10.0 37.561 0.0583
e
0.0 39.510
1.0 38.934
3.0 38.304
5.0 37.856
10.0 37.133
1.0 38.934 0.1008
3.0 38.304 0.0769
5.0 37.856 0.0932
10.0 37.133 0.0879
e
0.0 39.530
1.0 38.806
3.0 37.747
5.0 37.014
10.0 35.329
1.0 38.806 0.1230
3.0 37.747 0.1497
5.0 37.014 0.1269
10.0 35.329 0.1546
e
0.0 39.570
1.0 39.033
3.0 37.859
5.0 36.923
10.0 34.945
1.0 39.033 0.1272
3.0 37.859 0.2170
5.0 36.923 0.2133
10.0 34.945 0.3538
e
set yrange[28:36.5]
set ytics 28,2,60
set title '\TitleFont People On Street'
plot '-' using 1:2 title '\KeyFont 1200 B/S' w lp ls 1, '-' using 1:2 title '\KeyFont 2400 B/S' w lp ls 2, '-' using 1:2 title '\KeyFont 4800 B/S' w lp ls 3, '-' using 1:2 title '\KeyFont SS' w lp ls 4
plot '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 1200 B/S' w yerrorlines ls 1, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 2400 B/S' w yerrorlines ls 2, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 4800 B/S' w yerrorlines ls 3, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont SS' w yerrorlines ls 4
0.0 35.900
1.0 34.736
3.0 33.795
5.0 33.225
10.0 32.404
1.0 34.736 0.1227
3.0 33.795 0.0956
5.0 33.225 0.0866
10.0 32.404 0.0550
e
0.0 35.970
1.0 34.583
3.0 33.228
5.0 32.490
10.0 31.323
1.0 34.583 0.1546
3.0 33.228 0.1361
5.0 32.490 0.1016
10.0 31.323 0.0896
e
0.0 36.030
1.0 34.236
3.0 31.765
5.0 30.494
10.0 28.042
1.0 34.236 0.2135
3.0 31.765 0.2166
5.0 30.494 0.1649
10.0 28.042 0.1494
e
0.0 36.140
1.0 35.257
3.0 33.619
5.0 32.391
10.0 29.845
1.0 35.257 0.2181
3.0 33.619 0.4112
5.0 32.391 0.4491
10.0 29.845 0.4880
e
set yrange[30:40.5]
set ytics 30,2,60
set title '\TitleFont Race Horses'
plot '-' using 1:2 title '\KeyFont 1200 B/S' w lp ls 1, '-' using 1:2 title '\KeyFont 2400 B/S' w lp ls 2, '-' using 1:2 title '\KeyFont 4800 B/S' w lp ls 3, '-' using 1:2 title '\KeyFont SS' w lp ls 4
plot '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 1200 B/S' w yerrorlines ls 1, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 2400 B/S' w yerrorlines ls 2, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 4800 B/S' w yerrorlines ls 3, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont SS' w yerrorlines ls 4
0.0 39.870
1.0 38.724
3.0 37.661
5.0 37.118
10.0 36.218
1.0 38.724 0.1311
3.0 37.661 0.1030
5.0 37.118 0.0872
10.0 36.218 0.0881
e
0.0 39.920
1.0 38.269
3.0 36.467
5.0 35.580
10.0 34.204
1.0 38.269 0.1917
3.0 36.467 0.1768
5.0 35.580 0.1186
10.0 34.204 0.1144
e
0.0 39.960
1.0 37.729
3.0 34.768
5.0 32.972
10.0 30.390
1.0 37.729 0.2426
3.0 34.768 0.2522
5.0 32.972 0.2399
10.0 30.390 0.1767
e
0.0 40.030
1.0 38.846
3.0 36.403
5.0 34.608
10.0 30.944
1.0 38.846 0.2708
3.0 36.403 0.4255
5.0 34.608 0.3914
10.0 30.944 0.6286
e
set yrange[27:42]
set ytics 27,2,60
set title '\TitleFont Tennis'
plot '-' using 1:2 title '\KeyFont 1200 B/S' w lp ls 1, '-' using 1:2 title '\KeyFont 2400 B/S' w lp ls 2, '-' using 1:2 title '\KeyFont 4800 B/S' w lp ls 3, '-' using 1:2 title '\KeyFont SS' w lp ls 4
plot '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 1200 B/S' w yerrorlines ls 1, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 2400 B/S' w yerrorlines ls 2, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont 4800 B/S' w yerrorlines ls 3, '-' using 1:2:($2-$3):($2+$3) title '\KeyFont SS' w yerrorlines ls 4
0.0 40.680
1.0 39.242
3.0 37.515
5.0 36.545
10.0 35.064
1.0 39.242 0.1190
3.0 37.515 0.1482
5.0 36.545 0.1277
10.0 35.064 0.0794
e
0.0 40.770
1.0 38.369
3.0 35.105
5.0 33.079
10.0 29.667
1.0 38.369 0.2177
3.0 35.105 0.2529
5.0 33.079 0.2340
10.0 29.667 0.2283
e
0.0 40.830
1.0 38.307
3.0 34.743
5.0 32.276
10.0 27.524
1.0 38.307 0.2612
3.0 34.743 0.3993
5.0 32.276 0.3294
10.0 27.524 0.2569
e
0.0 40.900
1.0 39.773
3.0 37.491
5.0 35.896
10.0 32.303
1.0 39.773 0.2613
3.0 37.491 0.4317
5.0 35.896 0.3389
10.0 32.303 0.5964
e
\end{gnuplot}
043_DynamicErrorRobustness/DynamicErrorRobustness.tex
+2 -2
View File
@@ -272,7 +272,7 @@ However, different network topologies with different number of neurons in each l
To effectively train and validate the \ac{nn}, firstly the cases corresponding to three video sequence were left out, to be used in the performance evaluation of the proposed method.
The remaining data set was randomly partitioned into three different groups: (i) 65\% of the test cases are used for training, (ii) 15\% for validation and (iii) 20\% for testing the \ac{nn} performance.
\HIGHLIGHT{These ratios were chosen to use a relevant number of samples for testing \ac{nn} performance (i.e., 20\%), and the remaining were used mainly for training, leaving a 15\% samples for validation and stop criteria of the supervised training.
The \ac{nn} supervised training uses 557 test conditions and a scaled conjugate gradient algorithm~\cite{NNScaledConjugateTraining_1993} and stop when the cross-entropy obtained with the validation samples increases, revealing that the training starts to over-fit the training samples and is not being general enough to predict new data.
The \ac{nn} supervised training uses 557 test conditions, a scaled conjugate gradient algorithm~\cite{NNScaledConjugateTraining_1993} and stopped when the cross-entropy obtained for the validation samples increases, revealing that the training starts to over-fit the training samples and is not being able to generalise to new data.
Therefore, 129 test conditions were used for \ac{nn} validation.}
Finally, 172 conditions are used to evaluate the accuracy of the proposed method after training with different conditions.
@@ -370,7 +370,7 @@ The quality obtained with the proposed optimal error robustness scheme (\PROP) i
\centering
\input{043_DynamicErrorRobustness/Results/PlotQualty_vs_PLR_Predicted.tex}
\vspace{-2mm}
\caption{Average video quality using different error resilience techniques.}
\caption{Average video quality obtained for the reference HEVC (\REF), the optimal stream (\BEST) and the one selected by the proposed approach (\PROP).}
\label{Figure6:ProposedQuality}
\end{figure}