Audio-Visual Question Answering on MUSIC-AVQA 1.0 (test)
85.09AV Localis AccuracySparsify
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Sparsify2025.06 | 85.09 | 83.12 | 77.64 | 80.38 | 83.12 | 84.43 | 80.98 | 82.7 | 77.12 | 79.89 | 81.8 | 81.75 | 85.74 | |
| LAVisHMCCD=true2024.04 | 81.31 | — | — | — | — | — | — | 78.86 | — | — | — | 80.1 | — | |
| LAVisHMCCD=false2024.04 | 80.57 | — | — | — | — | — | — | 79.2 | — | — | — | 79.89 | — | |
| LAViTMCCD=true2024.04 | 76.73 | — | — | — | — | — | — | 70.43 | — | — | — | 73.62 | — | |
| MCCDMCCD=true2024.04 | 76.73 | — | — | — | — | — | — | 79.78 | — | — | — | 78.24 | — | |
| STGMCCD=false2024.04 | 76.38 | — | — | — | — | — | — | 71.56 | — | — | — | 74 | — | |
| COCAMCCD=false2024.04 | 76.08 | — | — | — | — | — | — | 72.35 | — | — | — | 74.24 | — | |
| LAVisH2025.06 | 75.81 | 75.59 | 84.13 | 76.86 | 77.45 | 76.29 | 71.91 | 77.52 | 76.75 | 77.62 | 76.31 | 76.1 | 72.91 | |
| LAViTMCCD=false2024.04 | 75.65 | — | — | — | — | — | — | 69.39 | — | — | — | 72.56 | — | |
| AVSDMCCD=true2024.04 | 74.53 | — | — | — | — | — | — | 67.42 | — | — | — | 71.02 | — | |
| AVSDMCCD=false2024.04 | 74.19 | — | — | — | — | — | — | 67.39 | — | — | — | 70.83 | — | |
| CADSource Task Category=AVQA2023.10 | 73.97 | 82.91 | 73.34 | 78.13 | 78.21 | 79.7 | 83.42 | 76.37 | 74.88 | 76.16 | 76.96 | 78.26 | — | |
| SHRIKE2025.11 | 72.72 | 85.84 | 68.01 | 79.27 | 85.3 | 86.09 | 80.26 | 79.05 | 66.76 | 69.83 | 74 | 78.14 | 86.86 | |
| QA-TIGER2025.03 | 72.5 | — | — | — | — | — | 83.1 | 78.58 | 63.94 | 69.59 | 73.74 | 77.62 | — | |
| TSPM2025.03 | 71.85 | — | — | — | — | — | 82.19 | 76.21 | 65.76 | 74.17 | 73.51 | 76.79 | — | |
| TSPM2025.11 | 71.85 | 84.07 | 64.65 | 76.91 | 82.29 | 83.61 | 82.19 | 76.21 | 65.76 | 71.17 | 73.51 | 76.79 | 84.9 | |
| PSTP-Net2025.03 | 71.8 | — | — | — | — | — | 76.18 | 72.23 | 71.79 | 69 | 72.57 | 73.52 | — | |
| PSTP-Net2025.11 | 71.8 | 73.97 | 65.59 | 70.91 | 77.15 | 77.26 | 76.18 | 72.23 | 71.79 | 69 | 72.57 | 73.52 | 77.36 | |
| GRUMCCD=true2024.04 | 71.43 | — | — | — | — | — | — | 67.25 | — | — | — | 69.36 | — | |
| QA-TIGERReproduced=true2025.11 | 71.41 | 85.25 | 68.01 | 78.9 | 84.71 | 85.51 | 82.49 | 78.74 | 63.94 | 68.86 | 73.35 | 77.56 | 86.29 | |
| MCANMCCD=true2024.04 | 71.18 | — | — | — | — | — | — | 71.93 | — | — | — | 71.55 | — | |
| MCANMCCD=false2024.04 | 70.93 | — | — | — | — | — | — | 71.56 | — | — | — | 71.24 | — | |
| GRUMCCD=false2024.04 | 70.11 | — | — | — | — | — | — | 67.72 | — | — | — | 68.93 | — | |
| PSACMCCD=true2024.04 | 69.88 | — | — | — | — | — | — | 69.09 | — | — | — | 69.49 | — | |
| PSACMCCD=false2024.04 | 69.79 | — | — | — | — | — | — | 68.64 | — | — | — | 69.22 | — | |
| COCA2025.03 | 69.72 | — | — | — | — | — | 83.5 | 66.63 | 64.12 | 65.57 | 69.96 | 72.33 | — | |
| COCA2025.11 | 69.72 | 79.35 | 67.68 | 75.42 | 75.1 | 75.23 | 83.5 | 66.63 | 64.12 | 65.57 | 69.96 | 72.33 | 75.43 | |
| HMEMCCD=false2024.04 | 69.46 | — | — | — | — | — | — | 67.97 | — | — | — | 68.76 | — | |
| HMEMCCD=true2024.04 | 69.31 | — | — | — | — | — | — | 68.76 | — | — | — | 69.03 | — | |
| APL2025.03 | 66.68 | — | — | — | — | — | 82.99 | 73.29 | 64.76 | 65.95 | 70.96 | 74.53 | — | |
| APL2025.11 | 66.68 | 82.4 | 70.71 | 78.09 | 76.52 | 79.69 | 82.99 | 73.29 | 64.76 | 65.95 | 70.96 | 74.53 | 82.74 | |
| HCAttnMCCD=false2024.04 | 66.37 | — | — | — | — | — | — | 64.05 | — | — | — | 65.22 | — | |
| LAVISH2025.03 | 66.13 | — | — | — | — | — | 81.71 | 75.51 | 63.77 | 67.96 | 71.26 | 74.46 | — | |
| LAVISH2025.11 | 66.13 | 82.09 | 65.56 | 75.97 | 78.98 | 80.22 | 81.71 | 75.51 | 63.77 | 67.96 | 71.26 | 74.46 | 81.43 | |
| DG-SCT2025.06 | 65.91 | 83.27 | 64.56 | 76.34 | 81.57 | 82.08 | 81.61 | 72.84 | 64.22 | 67.48 | 70.56 | 74.62 | 82.57 | |
| HCAttnMCCD=true2024.04 | 65.47 | — | — | — | — | — | — | 63.99 | — | — | — | 64.74 | — | |
| LAVisHMCCD=false2024.04 | 65.22 | — | — | — | — | — | 83.4 | 72.96 | 64.03 | 66.18 | — | 70.57 | — | |
| LAVisHMCCD=true2024.04 | 65.22 | — | — | — | — | — | 73.91 | 73.91 | 64.31 | 66.55 | — | 70.8 | — | |
| ST-AVQASource Task Category=AVQA, Publication Year=20222023.10 | 64.51 | 78.18 | 67.05 | 74.06 | 71.56 | 74 | 81.81 | 70.8 | 66.01 | 63.23 | 69.54 | 71.52 | — | |
| STGMCCD=false2024.04 | 64.51 | — | — | — | — | — | 81.81 | 70.8 | 66.01 | 63.23 | — | 69.54 | — | |
| ST-AVQA2025.03 | 64.51 | — | — | — | — | — | 81.81 | 70.8 | 66.01 | 63.23 | 69.54 | 71.17 | — | |
| ST-AVQA2025.11 | 64.51 | 78.18 | 67.05 | 74.06 | 71.56 | 74 | 81.81 | 70.8 | 66.01 | 63.23 | 69.54 | 71.52 | 76.38 | |
| BiLSTM AttnMCCD=false2024.04 | 64.33 | — | — | — | — | — | — | 64.64 | — | — | — | 64.48 | — | |
| AVST2025.06 | 64.24 | 77.78 | 67.17 | 73.87 | 73.52 | 74.4 | 82.49 | 69.88 | 64.67 | 65.82 | 69.53 | 71.59 | 75.27 | |
| COCAMCCD=false2024.04 | 64.02 | — | — | — | — | — | 83.5 | 70.99 | 63.4 | 64.48 | — | 69.47 | — | |
| HCRNMCCD=false2024.04 | 61.81 | — | — | — | — | — | — | 64.39 | — | — | — | 63.08 | — | |
| HCRNMCCD=true2024.04 | 60.82 | — | — | — | — | — | — | 67.42 | — | — | — | 64.08 | — | |
| LAViTMCCD=true2024.04 | 60.33 | — | — | — | — | — | 81.38 | 65.3 | 62.49 | 62.29 | — | 66.42 | — | |
| GRUMCCD=true2024.04 | 60.11 | — | — | — | — | — | 81.98 | 63.08 | 62.76 | 61.19 | — | 65.84 | — | |
| GRUSource Task Category=VisualQA, Publication Year=20152023.10 | 59.44 | 72.21 | 66.89 | 70.24 | 67.72 | 68.93 | 81.71 | 62.64 | 61.88 | 60.07 | 65.18 | 67.07 | — | |
| GRUMCCD=false2024.04 | 59.44 | — | — | — | — | — | 81.71 | 62.64 | 61.88 | 60.07 | — | 65.18 | — | |
| PanoAVQASource Task Category=AVQA, Publication Year=20212023.10 | 59.33 | 74.36 | 64.56 | 70.73 | 69.39 | 72.56 | 81.21 | 64.91 | 64.22 | 63.23 | 66.64 | 68.93 | — | |
| LAViTMCCD=false2024.04 | 59.33 | — | — | — | — | — | 81.21 | 64.91 | 64.22 | 63.23 | — | 66.64 | — | |
| Pano-AVQA2025.03 | 59.33 | — | — | — | — | — | 81.21 | 64.91 | 64.22 | 63.23 | 66.64 | 68.93 | — | |
| AVSDMCCD=true2024.04 | 59.13 | — | — | — | — | — | 81.17 | 63.08 | 62.49 | 63.5 | — | 65.82 | — | |
| FCNLSTMMCCD=true2024.04 | 59.02 | — | — | — | — | — | — | 66.08 | — | — | — | 62.51 | — | |
| AVSDSource Task Category=AVQA, Publication Year=20192023.10 | 58.79 | 72.41 | 61.9 | 68.52 | 67.39 | 70.83 | 81.61 | 63.89 | 61.52 | 61.41 | 65.49 | 67.44 | — | |
| AVSDMCCD=false2024.04 | 58.79 | — | — | — | — | — | 81.61 | 63.89 | 61.52 | 61.41 | — | 65.49 | — | |
| AVSD2025.03 | 58.79 | — | — | — | — | — | 81.61 | 63.89 | 61.52 | 61.41 | 65.49 | 67.44 | — | |
| AVSD2025.11 | 58.79 | 72.41 | 61.9 | 68.52 | 67.39 | 70.83 | 81.61 | 63.89 | 61.52 | 61.41 | 65.49 | 67.44 | 74.19 | |
| CONVLSTMMCCD=true2024.04 | 58.12 | — | — | — | — | — | — | 69.59 | — | — | — | 63.79 | — | |
| FCNLSTMMCCD=true2024.04 | 57.17 | — | — | — | — | — | 83.5 | 60.47 | 61.58 | 57.54 | — | 64.11 | — | |
| CONVLSTMMCCD=true2024.04 | 56.09 | — | — | — | — | — | 82.69 | 62.13 | 62.03 | 55.11 | — | 63.87 | — | |
| BiLSTM AttnMCCD=true2024.04 | 55.92 | — | — | — | — | — | — | 61.65 | — | — | — | 58.75 | — | |
| PSACSource Task Category=VideoQA, Publication Year=20192023.10 | 55.02 | 75.64 | 66.06 | 72.09 | 68.64 | 69.22 | 77.59 | 63.42 | 61.17 | 59.47 | 63.52 | 66.54 | — | |
| PSACMCCD=false2024.04 | 55.02 | — | — | — | — | — | 77.59 | 63.42 | 61.17 | 59.47 | — | 63.52 | — | |
| PSAC2025.03 | 55.02 | — | — | — | — | — | 77.59 | 63.42 | 61.17 | 59.47 | 63.52 | 66.54 | — | |
| CONVLSTMMCCD=false2024.04 | 54.56 | — | — | — | — | — | — | 67.47 | — | — | — | 60.94 | — | |
| MCANSource Task Category=VisualQA, Publication Year=20192023.10 | 54.48 | 77.5 | 55.24 | 69.25 | 71.56 | 71.24 | 80.4 | 64.91 | 57.22 | 47.57 | 61.58 | 65.49 | — | |
| MCANMCCD=false2024.04 | 54.48 | — | — | — | — | — | 80.4 | 64.91 | 57.22 | 47.57 | — | 61.58 | — | |
| MCAN2025.03 | 54.48 | — | — | — | — | — | 80.4 | 64.91 | 57.22 | 47.57 | 61.58 | 65.49 | — | |
| MCANMCCD=true2024.04 | 54.24 | — | — | — | — | — | 81.48 | 65.77 | 55.86 | 46.84 | — | 61.54 | — | |
| HMESource Task Category=VideoQA, Publication Year=20192023.10 | 53.18 | 74.76 | 63.56 | 70.61 | 67.97 | 68.76 | 80.3 | 63.19 | 62.69 | 59.83 | 64.05 | 66.45 | — | |
| HMEMCCD=false2024.04 | 53.18 | — | — | — | — | — | 80.3 | 63.19 | 62.69 | 59.83 | — | 64.05 | — | |
| HME2025.03 | 53.18 | — | — | — | — | — | 80.3 | 63.19 | 62.69 | 59.83 | 64.05 | 66.45 | — | |
| PSACMCCD=true2024.04 | 53.04 | — | — | — | — | — | 79.35 | 61.98 | 61.13 | 57.66 | — | 62.85 | — | |
| HMEMCCD=true2024.04 | 52.61 | — | — | — | — | — | 80.77 | 62.92 | 63.03 | 60.71 | — | 64.19 | — | |
| MCCDMCCD=true2024.04 | 51.63 | — | — | — | — | — | 80.87 | 71.46 | 64.67 | 64.6 | — | 67.13 | — | |
| CONVLSTMSource Task Category=AudioQA, Publication Year=20192023.10 | 50.81 | 74.07 | 68.89 | 72.15 | 67.47 | 60.94 | 82.91 | 63.03 | 60.27 | 51.58 | 62.24 | 63.65 | — | |
| CONVLSTMMCCD=false2024.04 | 50.81 | — | — | — | — | — | 82.91 | 63.03 | 60.27 | 51.58 | — | 62.24 | — | |
| HCAttnSource Task Category=VisualQA, Publication Year=20162023.10 | 49.51 | 70.25 | 54.91 | 64.57 | 64.05 | 65.22 | 79.1 | 59.97 | 55.25 | 56.43 | 60.19 | 62.3 | — | |
| HCAttnMCCD=false2024.04 | 49.51 | — | — | — | — | — | 79.1 | 59.97 | 55.25 | 56.43 | — | 60.19 | — | |
| HCAttn2025.03 | 49.51 | — | — | — | — | — | 79.1 | 59.97 | 55.25 | 56.43 | 60.19 | 62.3 | — | |
| HCRNMCCD=true2024.04 | 48.7 | — | — | — | — | — | 79.66 | 65.14 | 61.22 | 55.72 | — | 60.4 | — | |
| HCAttnMCCD=true2024.04 | 47.28 | — | — | — | — | — | 78.64 | 61.11 | 55.86 | 55.72 | — | 60.03 | — | |
| FCNLSTMMCCD=false2024.04 | 46.74 | — | — | — | — | — | — | 63.89 | — | — | — | 55.21 | — | |
| FCNLSTMSource Task Category=AudioQA, Publication Year=20192023.10 | 46.28 | 70.45 | 66.22 | 68.88 | 63.89 | 55.21 | 82.01 | 59.34 | 62.15 | 47.33 | 60.06 | 60.34 | — | |
| FCNLSTMMCCD=false2024.04 | 46.28 | — | — | — | — | — | 82.01 | 59.34 | 62.15 | 47.33 | — | 60.06 | — | |
| FCNLSTM2025.03 | 46.28 | — | — | — | — | — | 82.01 | 59.34 | 62.15 | 47.33 | 60.06 | 60.34 | — | |
| BiLSTM AttnSource Task Category=VisualQA, Publication Year=20162023.10 | 45.85 | 70.35 | 47.92 | 62.05 | 64.64 | 64.48 | 78.39 | 56.91 | 53.09 | 49.76 | 57.1 | 59.92 | — | |
| BiLSTM AttnMCCD=false2024.04 | 45.85 | — | — | — | — | — | 78.39 | 56.91 | 53.09 | 49.76 | — | 57.1 | — | |
| BILSTM2025.03 | 45.85 | — | — | — | — | — | 78.39 | 56.91 | 53.09 | 49.76 | 57.1 | 59.92 | — | |
| BiLSTM AttnMCCD=true2024.04 | 41.96 | — | — | — | — | — | 79.15 | 55.02 | 49.41 | 49.15 | — | 55.18 | — | |
| HCRNSource Task Category=VideoQA, Publication Year=20202023.10 | 41.53 | 68.59 | 50.92 | 62.05 | 64.39 | 63.08 | 54.47 | 53.38 | 52.11 | 47.69 | 50.26 | 55.73 | — | |
| HCRNMCCD=false2024.04 | 41.53 | — | — | — | — | — | 54.47 | 53.38 | 52.11 | 47.69 | — | 50.26 | — | |
| HCRN2025.03 | 41.53 | — | — | — | — | — | 54.47 | 53.38 | 52.11 | 47.69 | 50.26 | 55.73 | — |