List your company

Multimodal Abstractive Summarization on MM-Sum mid-high-resource

41.51ROUGE-1SOV-MAS
20.772426.156231.5436.9238Dec 15, 2022

Evaluation results

MethodLinks
SOV-MASTraining Paradigm=Multilingual Training, Language=Chinese, Visual Features=ViT2022.1241.5126.3434.41
SOV-MASTraining Paradigm=Monolingual Training, Language=Chinese, Visual Features=ViT2022.1240.6125.3733.39
VG-mT5Training Paradigm=Monolingual Training, Language=Chinese, Visual Features=ViT2022.1240.3125.4533.51
mT5Training Paradigm=Multilingual Training, Language=Chinese, Visual Features=ViT2022.1240.324.9733.04
mT5Training Paradigm=Monolingual Training, Language=Chinese, Visual Features=ViT2022.1240.225.3933.49
VG-mT5Training Paradigm=Multilingual Training, Language=Chinese, Visual Features=ViT2022.1240.1925.3133.35
SOV-MASTraining Paradigm=Multilingual Training, Language=Urdu, Visual Features=ViT2022.1239.2218.3132.62
mT5Training Paradigm=Monolingual Training, Language=Urdu, Visual Features=ViT2022.1238.2217.2531.37
SOV-MASTraining Paradigm=Monolingual Training, Language=Urdu, Visual Features=ViT2022.1238.1917.1231.38
mT5Training Paradigm=Multilingual Training, Language=Urdu, Visual Features=ViT2022.1238.1517.1231.36
VG-mT5Training Paradigm=Monolingual Training, Language=Urdu, Visual Features=ViT2022.1238.1117.2731.51
VG-mT5Training Paradigm=Multilingual Training, Language=Urdu, Visual Features=ViT2022.1238.0117.2131.55
SOV-MASTraining Paradigm=Multilingual Training, Language=English, Visual Features=ViT2022.1237.7715.1429.81
SOV-MASTraining Paradigm=Multilingual Training, Language=Persian, Visual Features=ViT2022.1237.6516.9230.58
SOV-MASTraining Paradigm=Multilingual Training, Language=Indonesian, Visual Features=ViT2022.1237.4617.1331.18
SOV-MASTraining Paradigm=Monolingual Training, Language=English, Visual Features=ViT2022.1237.2915.1829.82
VG-mT5Training Paradigm=Monolingual Training, Language=English, Visual Features=ViT2022.1237.2514.9729.54
mT5Training Paradigm=Monolingual Training, Language=English, Visual Features=ViT2022.1236.9915.1829.64
VG-mT5Training Paradigm=Multilingual Training, Language=Persian, Visual Features=ViT2022.1236.8816.3429.93
VG-mT5Training Paradigm=Multilingual Training, Language=English, Visual Features=ViT2022.1236.6914.1628.79
mT5Training Paradigm=Multilingual Training, Language=English, Visual Features=ViT2022.1236.6513.9128.53
VG-mT5Training Paradigm=Multilingual Training, Language=Indonesian, Visual Features=ViT2022.1236.5516.3830.19
mT5Training Paradigm=Multilingual Training, Language=Persian, Visual Features=ViT2022.1236.3915.8429.45
SOV-MASTraining Paradigm=Monolingual Training, Language=Persian, Visual Features=ViT2022.1236.3715.7529.35
SOV-MASTraining Paradigm=Multilingual Training, Language=Hindi, Visual Features=ViT2022.1236.3314.9129.68
mT5Training Paradigm=Monolingual Training, Language=Persian, Visual Features=ViT2022.1236.1415.5529.25
VG-mT5Training Paradigm=Monolingual Training, Language=Persian, Visual Features=ViT2022.1236.0115.4529.08
mT5Training Paradigm=Multilingual Training, Language=Indonesian, Visual Features=ViT2022.1235.8415.6629.4
VG-mT5Training Paradigm=Multilingual Training, Language=Hindi, Visual Features=ViT2022.1235.6614.2628.97
mT5Training Paradigm=Multilingual Training, Language=Hindi, Visual Features=ViT2022.1235.513.9128.52
VG-mT5Training Paradigm=Monolingual Training, Language=Indonesian, Visual Features=ViT2022.1235.1615.4929.09
SOV-MASTraining Paradigm=Monolingual Training, Language=Indonesian, Visual Features=ViT2022.1235.1415.3128.81
mT5Training Paradigm=Monolingual Training, Language=Indonesian, Visual Features=ViT2022.1235.115.4428.91
SOV-MASTraining Paradigm=Monolingual Training, Language=Hindi, Visual Features=ViT2022.1234.7813.5528.11
SOV-MASTraining Paradigm=Multilingual Training, Language=Vietnamese, Visual Features=ViT2022.1234.7517.8227.09
SOV-MASTraining Paradigm=Multilingual Training, Language=Arabic, Visual Features=ViT2022.1234.6914.3928.54
VG-mT5Training Paradigm=Monolingual Training, Language=Hindi, Visual Features=ViT2022.1234.5513.4728.26
mT5Training Paradigm=Multilingual Training, Language=Arabic, Visual Features=ViT2022.1234.3414.328.43
SOV-MASTraining Paradigm=Multilingual Training, Language=Avg., Visual Features=ViT2022.1233.8715.2727.69
SOV-MASTraining Paradigm=Monolingual Training, Language=Arabic, Visual Features=ViT2022.1233.8614.5328.06
VG-mT5Training Paradigm=Monolingual Training, Language=Arabic, Visual Features=ViT2022.1233.7914.1127.95
VG-mT5Training Paradigm=Multilingual Training, Language=Vietnamese, Visual Features=ViT2022.1233.7917.0826.34
mT5Training Paradigm=Multilingual Training, Language=Vietnamese, Visual Features=ViT2022.1233.7116.7225.97
mT5Training Paradigm=Monolingual Training, Language=Arabic, Visual Features=ViT2022.1233.6714.0627.83
mT5Training Paradigm=Monolingual Training, Language=Hindi, Visual Features=ViT2022.1233.6613.1427.71
VG-mT5Training Paradigm=Multilingual Training, Language=Arabic, Visual Features=ViT2022.1233.413.4927.51
VG-mT5Training Paradigm=Multilingual Training, Language=Avg., Visual Features=ViT2022.1232.8914.5326.84
mT5Training Paradigm=Multilingual Training, Language=Avg., Visual Features=ViT2022.1232.8814.326.61
SOV-MASTraining Paradigm=Monolingual Training, Language=Vietnamese, Visual Features=ViT2022.1232.8716.5925.24
SOV-MASTraining Paradigm=Multilingual Training, Language=Turkish, Visual Features=ViT2022.1232.6715.728.77
SOV-MASTraining Paradigm=Monolingual Training, Language=Avg., Visual Features=ViT2022.1232.4914.2626.4
VG-mT5Training Paradigm=Monolingual Training, Language=Avg., Visual Features=ViT2022.1232.2514.1626.32
VG-mT5Training Paradigm=Monolingual Training, Language=Vietnamese, Visual Features=ViT2022.1232.1915.9924.87
mT5Training Paradigm=Monolingual Training, Language=Vietnamese, Visual Features=ViT2022.1232.1815.8424.83
mT5Training Paradigm=Monolingual Training, Language=Avg., Visual Features=ViT2022.1232.1414.1626.26
mT5Training Paradigm=Multilingual Training, Language=Turkish, Visual Features=ViT2022.1231.9314.6927.76
SOV-MASTraining Paradigm=Multilingual Training, Language=Portuguese, Visual Features=ViT2022.1231.7711.7623.79
SOV-MASTraining Paradigm=Monolingual Training, Language=Russian, Visual Features=ViT2022.1231.5812.7724.96
SOV-MASTraining Paradigm=Multilingual Training, Language=Russian, Visual Features=ViT2022.1231.5713.1225.21
VG-mT5Training Paradigm=Multilingual Training, Language=Turkish, Visual Features=ViT2022.1231.4114.7127.7
mT5Training Paradigm=Multilingual Training, Language=Russian, Visual Features=ViT2022.1231.1212.3324.67
VG-mT5Training Paradigm=Multilingual Training, Language=Portuguese, Visual Features=ViT2022.1231.0111.2223.11
VG-mT5Training Paradigm=Monolingual Training, Language=Russian, Visual Features=ViT2022.1231.0112.4324.52
SOV-MASTraining Paradigm=Multilingual Training, Language=Spanish, Visual Features=ViT2022.123111.5623.58
SOV-MASTraining Paradigm=Monolingual Training, Language=Turkish, Visual Features=ViT2022.1230.9114.627.16
mT5Training Paradigm=Multilingual Training, Language=Portuguese, Visual Features=ViT2022.1230.8410.9222.64
VG-mT5Training Paradigm=Multilingual Training, Language=Russian, Visual Features=ViT2022.1230.5512.6524.58
VG-mT5Training Paradigm=Monolingual Training, Language=Turkish, Visual Features=ViT2022.1230.4414.426.77
VG-mT5Training Paradigm=Multilingual Training, Language=Spanish, Visual Features=ViT2022.1230.3710.9423.02
mT5Training Paradigm=Monolingual Training, Language=Turkish, Visual Features=ViT2022.1230.3714.3926.79
mT5Training Paradigm=Monolingual Training, Language=Portuguese, Visual Features=ViT2022.1230.1310.3222.06
mT5Training Paradigm=Monolingual Training, Language=Russian, Visual Features=ViT2022.1230.0112.4724.28
mT5Training Paradigm=Multilingual Training, Language=Spanish, Visual Features=ViT2022.1229.9110.722.66
SOV-MASTraining Paradigm=Monolingual Training, Language=Portuguese, Visual Features=ViT2022.1229.7710.0121.55
mT5Training Paradigm=Monolingual Training, Language=Spanish, Visual Features=ViT2022.1229.5110.4822.51
VG-mT5Training Paradigm=Monolingual Training, Language=Portuguese, Visual Features=ViT2022.1229.469.7221.91
VG-mT5Training Paradigm=Monolingual Training, Language=Spanish, Visual Features=ViT2022.1229.3710.5922.52
SOV-MASTraining Paradigm=Monolingual Training, Language=Spanish, Visual Features=ViT2022.1229.1910.3222.37
SOV-MASTraining Paradigm=Multilingual Training, Language=Tamil, Visual Features=ViT2022.1224.0110.8221.89
SOV-MASTraining Paradigm=Multilingual Training, Language=Ukrainian, Visual Features=ViT2022.1223.849.9420.49
VG-mT5Training Paradigm=Multilingual Training, Language=Tamil, Visual Features=ViT2022.1223.1410.2920.98
mT5Training Paradigm=Multilingual Training, Language=Tamil, Visual Features=ViT2022.1222.9610.0520.75
SOV-MASTraining Paradigm=Monolingual Training, Language=Tamil, Visual Features=ViT2022.1222.810.5120.62
mT5Training Paradigm=Multilingual Training, Language=Ukrainian, Visual Features=ViT2022.1222.799.1319.46
VG-mT5Training Paradigm=Multilingual Training, Language=Ukrainian, Visual Features=ViT2022.1222.799.3919.75
mT5Training Paradigm=Monolingual Training, Language=Tamil, Visual Features=ViT2022.1222.3110.0820.36
VG-mT5Training Paradigm=Monolingual Training, Language=Tamil, Visual Features=ViT2022.1222.2910.1420.38
SOV-MASTraining Paradigm=Monolingual Training, Language=Ukrainian, Visual Features=ViT2022.1221.778.6118.77
VG-mT5Training Paradigm=Monolingual Training, Language=Ukrainian, Visual Features=ViT2022.1221.698.7818.65
mT5Training Paradigm=Monolingual Training, Language=Ukrainian, Visual Features=ViT2022.1221.578.6618.64