Audio Question Answering on MUSIC-AVQA (test)
80.51Accuracy (Avg)InternVideo2_S2
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| InternVideo2_S2Backbone=InternVideo2_S2, Finetuning setting=true2024.03 | 80.51 | — | — | |
| Spatio-Temporal Grounded Audio-Visual NetworkModel Domain=AVQA2022.03 | 74.06 | 78.18 | 67.05 | |
| CONVLSTMModel Domain=AudioQA2022.03 | 72.15 | 74.07 | 68.35 | |
| Chu et al., 20232024.02 | 72.1 | — | — | |
| PSACModel Domain=VisualQA2022.03 | 72.09 | 75.64 | 66.06 | |
| Audio Flamingo2024.02 | 71.6 | — | — | |
| Pano-AVQAModel Domain=AVQA2022.03 | 70.73 | 74.36 | 64.56 | |
| HMEModel Domain=VideoQA2022.03 | 70.61 | 74.76 | 63.56 | |
| GRUModel Domain=AudioQA2022.03 | 70.24 | 72.21 | 66.89 | |
| MCANModel Domain=VisualQA2022.03 | 69.25 | 77.5 | 55.24 | |
| FCNLSTMModel Domain=AudioQA2022.03 | 68.89 | 70.45 | 66.22 | |
| AVSDModel Domain=AVQA2022.03 | 68.52 | 72.41 | 61.9 | |
| MWAFMBackbone=MWAFM, Finetuning setting=true2024.03 | 67.54 | — | — | |
| AquaNetBackbone=AquaNet, Finetuning setting=true2024.03 | 65.59 | — | — | |
| HCAttnModel Domain=VisualQA2022.03 | 64.57 | 70.25 | 54.91 | |
| BiLSTM AttnModel Domain=VisualQA2022.03 | 62.05 | 70.35 | 47.92 | |
| HCRNModel Domain=VideoQA2022.03 | 62.05 | 68.59 | 50.92 |