Label Distribution Learning by Regularized Sample Self-Representation

Table 7

Cosine   (mean std) × 10³ of different algorithms on the twelve datasets. The best results are enlightened in bold and the second best results are italicized.

Algorithms	PT-SVM	AA-BP	SA-IIS	SA-BFGS	RSSR-LDL2	RSSR-LDL21
Movie	766.2 53.3	901.0 2.4	922.5 3.1	923.0 3.6	936.9 0.6	934.4 4.7
SBU-3DFE	912.9 5.4	902.6 8.2	921.8 3.4	947.2 3.7	931.8 3.6	943.4 1.6
SJAFFE	927.3 8.9	902.8 20.6	934.3 7.1	939.8 13.9	953.8 15.7	957.9 7.8
Yeast-alpha	994.1 0.3	945.1 6.0	991.5 0.2	994.6 0.3	994.6 0.3	994.6 0.3
Yeast-cdc	992.5 0.5	957.5 3.2	990.2 0.4	993.3 0.2	993.3 0.3	993.3 0.3
Yeast-cold	985.5 1.9	985.6 1.2	986.1 1.0	988.6 0.9	988.6 0.8	988.6 1.0
Yeast-diau	983.8 2.6	978.2 2.0	985.1 0.8	988.0 0.8	988.0 0.6	988.0 0.6
Yeast-dtt	993.4 0.8	991.1 0.9	991.6 0.7	994.1 0.7	994.1 0.4	994.1 0.7
Yeast-elu	993.4 0.3	961.8 5.0	990.9 0.6	994.0 0.3	994.1 0.3	994.1 0.3
Yeast-heat	986.8 0.6	978.9 3.3	985.4 0.7	988.0 0.5	988.0 0.8	988.0 0.5
Yeast-spo	971.3 2.1	970.2 2.2	974.5 1.2	977.0 2.0	977.0 1.7	977.0 1.7
Yeast-spo5	973.1 2.1	971.4 2.7	972.3 1.1	974.1 1.6	974.3 2.0	974.2 1.5