Sentiment Analysis on CMU-MOSI
77.02AUCConfSMoE-T
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| ConfSMoE-TVideo=true, Text=false, Audio=true, Experiment setting=III2025.05 | 77.02 | — | — | — | — | — | — | — | |
| ConfSMoE-TVideo=false, Text=false, Audio=true, Experiment setting=III2025.05 | 77.02 | — | — | — | — | — | — | — | |
| ConfSMoE-EVideo=true, Text=false, Audio=true, Experiment setting=III2025.05 | 76.96 | — | — | — | — | — | — | — | |
| ConfSMoE-EVideo=false, Text=false, Audio=true, Experiment setting=III2025.05 | 76.47 | — | — | — | — | — | — | — | |
| LlMoEVideo=false, Text=true, Audio=false, Experiment setting=III2025.05 | 75.73 | — | — | — | — | — | — | — | |
| LlMoEVideo=true, Text=false, Audio=true, Experiment setting=III2025.05 | 75.59 | — | — | — | — | — | — | — | |
| ConfSMoE-TVideo=false, Text=true, Audio=false, Experiment setting=III2025.05 | 75.58 | — | — | — | — | — | — | — | |
| ConfSMoE-TVideo=true, Text=true, Audio=false, Experiment setting=III2025.05 | 75.57 | — | — | — | — | — | — | — | |
| ConfSMoE-EVideo=true, Text=true, Audio=false, Experiment setting=III2025.05 | 75.56 | — | — | — | — | — | — | — | |
| FlexMoEVideo=true, Text=false, Audio=true, Experiment setting=III2025.05 | 75.55 | — | — | — | — | — | — | — | |
| ConfSMoE-EVideo=false, Text=true, Audio=false, Experiment setting=III2025.05 | 75.5 | — | — | — | — | — | — | — | |
| FlexMoEVideo=false, Text=false, Audio=true, Experiment setting=III2025.05 | 75.34 | — | — | — | — | — | — | — | |
| ConfSMoE-EVideo=true, Text=false, Audio=false, Experiment setting=III2025.05 | 75.11 | — | — | — | — | — | — | — | |
| ConfSMoE-TVideo=true, Text=false, Audio=false, Experiment setting=III2025.05 | 75.07 | — | — | — | — | — | — | — | |
| LlMoEVideo=true, Text=false, Audio=false, Experiment setting=III2025.05 | 74.73 | — | — | — | — | — | — | — | |
| LlMoEVideo=true, Text=true, Audio=false, Experiment setting=III2025.05 | 74.63 | — | — | — | — | — | — | — | |
| FlexMoEVideo=true, Text=true, Audio=false, Experiment setting=III2025.05 | 74.59 | — | — | — | — | — | — | — | |
| FlexMoEVideo=false, Text=true, Audio=false, Experiment setting=III2025.05 | 74.42 | — | — | — | — | — | — | — | |
| FlexMoEVideo=true, Text=false, Audio=false, Experiment setting=III2025.05 | 74.35 | — | — | — | — | — | — | — | |
| mmFormerVideo=false, Text=true, Audio=false, Experiment setting=III2025.05 | 73.77 | — | — | — | — | — | — | — | |
| LlMoEVideo=false, Text=false, Audio=true, Experiment setting=III2025.05 | 73.29 | — | — | — | — | — | — | — | |
| mmFormerVideo=true, Text=true, Audio=false, Experiment setting=III2025.05 | 72.72 | — | — | — | — | — | — | — | |
| mmFormerVideo=true, Text=false, Audio=true, Experiment setting=III2025.05 | 71.96 | — | — | — | — | — | — | — | |
| mmFormerVideo=true, Text=false, Audio=false, Experiment setting=III2025.05 | 71.01 | — | — | — | — | — | — | — | |
| mmFormerVideo=false, Text=false, Audio=true, Experiment setting=III2025.05 | 69.04 | — | — | — | — | — | — | — | |
| ShaSpecVideo=false, Text=false, Audio=true, Experiment setting=III2025.05 | 66.85 | — | — | — | — | — | — | — | |
| ShaSpecVideo=true, Text=false, Audio=true, Experiment setting=III2025.05 | 65.22 | — | — | — | — | — | — | — | |
| ShaSpecVideo=true, Text=true, Audio=false, Experiment setting=III2025.05 | 62.18 | — | — | — | — | — | — | — | |
| ShaSpecVideo=false, Text=true, Audio=false, Experiment setting=III2025.05 | 61.6 | — | — | — | — | — | — | — | |
| TFVideo=false, Text=true, Audio=false, Experiment setting=III2025.05 | 60.28 | — | — | — | — | — | — | — | |
| TFVideo=true, Text=true, Audio=false, Experiment setting=III2025.05 | 59.37 | — | — | — | — | — | — | — | |
| ConfSMoE-EVideo=false, Text=true, Audio=true, Experiment setting=III2025.05 | 58.66 | — | — | — | — | — | — | — | |
| TFVideo=true, Text=false, Audio=false, Experiment setting=III2025.05 | 58.57 | — | — | — | — | — | — | — | |
| ConfSMoE-TVideo=false, Text=true, Audio=true, Experiment setting=III2025.05 | 58.42 | — | — | — | — | — | — | — | |
| TFVideo=true, Text=false, Audio=true, Experiment setting=III2025.05 | 57.89 | — | — | — | — | — | — | — | |
| TFVideo=false, Text=true, Audio=true, Experiment setting=III2025.05 | 57.87 | — | — | — | — | — | — | — | |
| FuseMoE-LVideo=false, Text=false, Audio=true, Experiment setting=III2025.05 | 57.85 | — | — | — | — | — | — | — | |
| TFVideo=false, Text=false, Audio=true, Experiment setting=III2025.05 | 57.19 | — | — | — | — | — | — | — | |
| LlMoEVideo=false, Text=true, Audio=true, Experiment setting=III2025.05 | 56.84 | — | — | — | — | — | — | — | |
| FuseMoE-LVideo=false, Text=true, Audio=false, Experiment setting=III2025.05 | 56.58 | — | — | — | — | — | — | — | |
| FuseMoE-LVideo=true, Text=true, Audio=false, Experiment setting=III2025.05 | 56.44 | — | — | — | — | — | — | — | |
| FuseMoE-SVideo=false, Text=true, Audio=true, Experiment setting=III2025.05 | 56.24 | — | — | — | — | — | — | — | |
| FuseMoE-LVideo=true, Text=false, Audio=true, Experiment setting=III2025.05 | 56.1 | — | — | — | — | — | — | — | |
| FuseMoE-SVideo=false, Text=false, Audio=true, Experiment setting=III2025.05 | 56.04 | — | — | — | — | — | — | — | |
| FuseMoE-SVideo=true, Text=false, Audio=false, Experiment setting=III2025.05 | 55.94 | — | — | — | — | — | — | — | |
| ShaSpecVideo=false, Text=true, Audio=true, Experiment setting=III2025.05 | 55.79 | — | — | — | — | — | — | — | |
| FuseMoE-LVideo=true, Text=false, Audio=false, Experiment setting=III2025.05 | 55.66 | — | — | — | — | — | — | — | |
| FuseMoE-SVideo=false, Text=true, Audio=false, Experiment setting=III2025.05 | 55.45 | — | — | — | — | — | — | — | |
| FuseMoE-SVideo=true, Text=true, Audio=false, Experiment setting=III2025.05 | 55.35 | — | — | — | — | — | — | — | |
| FuseMoE-LVideo=false, Text=true, Audio=true, Experiment setting=III2025.05 | 55.11 | — | — | — | — | — | — | — | |
| ShaSpecVideo=true, Text=false, Audio=false, Experiment setting=III2025.05 | 55.1 | — | — | — | — | — | — | — | |
| FuseMoE-SVideo=true, Text=false, Audio=true, Experiment setting=III2025.05 | 54.36 | — | — | — | — | — | — | — | |
| FlexMoEVideo=false, Text=true, Audio=true, Experiment setting=III2025.05 | 52.28 | — | — | — | — | — | — | — | |
| mmFormerVideo=false, Text=true, Audio=true, Experiment setting=III2025.05 | 52.21 | — | — | — | — | — | — | — | |
| BaselineBackbone=Qwen3-VL-4B-Instruct2026.05 | — | — | — | — | — | — | 51.65 | — | |
| CIA2026.01 | — | 38.9 | 79.8 | 79.5 | 0.689 | 0.914 | — | — | |
| CorrKD2026.01 | — | — | — | 83.9 | — | — | — | — | |
| CTC+EF-LSTM2026.01 | — | 31 | 73.6 | 74.5 | 0.542 | 1.078 | — | — | |
| CTC+MCTN2026.01 | — | 32.7 | 75.9 | 76.4 | 0.613 | 0.991 | — | — | |
| CTC+RAVEN2026.01 | — | 31.7 | 72.7 | 73.1 | 0.544 | 1.076 | — | — | |
| EF-LSTM2026.01 | — | 33.7 | 75.3 | 75.2 | 0.608 | 1.023 | — | — | |
| GCNet2026.01 | — | — | — | 83.2 | — | — | — | — | |
| HCT-DMGModel Variant=Conven., Number of Parameters=0.78M2026.01 | — | 39.4 | 82.5 | 82.5 | 0.71 | 0.881 | — | — | |
| HCT-DMGModel Variant=LPM, Number of Parameters=0.83M2026.01 | — | 41.8 | 85.1 | 84.8 | 0.732 | 0.855 | — | — | |
| HRLF2026.01 | — | — | — | 84.2 | — | — | — | — | |
| ICL-CAMissing Modality Pattern=100-text-100-audio-100-video2026.06 | — | — | — | — | — | — | — | 71 | |
| ICL-CAMissing Modality Pattern=100-text-100-audio-20-video2026.06 | — | — | — | — | — | — | — | 56 | |
| ICL-CAMissing Modality Pattern=100-text-20-audio-100-video2026.06 | — | — | — | — | — | — | — | 78 | |
| ICL-CAMissing Modality Pattern=100-text-20-audio-20-video2026.06 | — | — | — | — | — | — | — | 56 | |
| ICL-CAMissing Modality Pattern=20-text-100-audio-100-video2026.06 | — | — | — | — | — | — | — | 67 | |
| ICL-CAMissing Modality Pattern=20-text-100-audio-20-video2026.06 | — | — | — | — | — | — | — | 56 | |
| ICL-CAMissing Modality Pattern=20-text-20-audio-100-video2026.06 | — | — | — | — | — | — | — | 65 | |
| ICL-CAMissing Modality Pattern=complex-20-20-20-10-10-10-102026.06 | — | — | — | — | — | — | — | 68 | |
| LF-LSTMNumber of Parameters=1.24M2026.01 | — | 33.7 | 77.6 | 77.8 | 0.624 | 0.988 | — | — | |
| LMF2026.01 | — | 32.8 | 76.4 | 75.7 | 0.668 | 0.912 | — | — | |
| LMF-MulTNumber of Parameters=0.86M2026.01 | — | 34 | 78.5 | 78.5 | 0.681 | 0.957 | — | — | |
| M3CareMissing Modality Pattern=100-text-100-audio-100-video2026.06 | — | — | — | — | — | — | — | 36 | |
| M3CareMissing Modality Pattern=100-text-100-audio-20-video2026.06 | — | — | — | — | — | — | — | 34 | |
| M3CareMissing Modality Pattern=100-text-20-audio-100-video2026.06 | — | — | — | — | — | — | — | 33 | |
| M3CareMissing Modality Pattern=100-text-20-audio-20-video2026.06 | — | — | — | — | — | — | — | 31 | |
| M3CareMissing Modality Pattern=20-text-100-audio-100-video2026.06 | — | — | — | — | — | — | — | 29 | |
| M3CareMissing Modality Pattern=20-text-100-audio-20-video2026.06 | — | — | — | — | — | — | — | 26 | |
| M3CareMissing Modality Pattern=20-text-20-audio-100-video2026.06 | — | — | — | — | — | — | — | 28 | |
| M3CareMissing Modality Pattern=complex-20-20-20-10-10-10-102026.06 | — | — | — | — | — | — | — | 30 | |
| MARN2026.01 | — | 34.7 | 77.1 | 77 | 0.625 | 0.968 | — | — | |
| MCTN2026.01 | — | 35.6 | 79.3 | 79.1 | 0.676 | 0.909 | — | — | |
| MFN2026.01 | — | 34.1 | 77.4 | 77.3 | 0.632 | 0.965 | — | — | |
| MISAFeatures=LPM2026.01 | — | 41.4 | 81.9 | 81.8 | 0.762 | 0.81 | — | — | |
| MMIN2026.01 | — | — | 82.3 | — | — | — | — | — | |
| MRAN2026.01 | — | — | 83.9 | — | — | — | — | — | |
| MTMSA2026.01 | — | — | 84.9 | — | — | — | — | — | |
| MulTNumber of Parameters=1.07M2026.01 | — | 34.3 | 80.3 | 80.4 | 0.645 | 1.008 | — | — | |
| PAIBackbone=Qwen3-VL-4B-Instruct2026.05 | — | — | — | — | — | — | 54.37 | — | |
| RAVEN2026.01 | — | 33.2 | 78 | 76.6 | 0.691 | 0.915 | — | — | |
| RMFN2026.01 | — | 38.3 | 78.4 | 78 | 0.681 | 0.922 | — | — | |
| ShaSpecMissing Modality Pattern=100-text-100-audio-100-video2026.06 | — | — | — | — | — | — | — | 35 | |
| ShaSpecMissing Modality Pattern=100-text-100-audio-20-video2026.06 | — | — | — | — | — | — | — | 33 | |
| ShaSpecMissing Modality Pattern=100-text-20-audio-100-video2026.06 | — | — | — | — | — | — | — | 32 | |
| ShaSpecMissing Modality Pattern=100-text-20-audio-20-video2026.06 | — | — | — | — | — | — | — | 30 | |
| ShaSpecMissing Modality Pattern=20-text-100-audio-100-video2026.06 | — | — | — | — | — | — | — | 28 |