Visual Question Answering on MUSIC-AVQA (test)
71.56Accuracy (Counting)MCAN
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MCANModel Domain=VisualQA2022.03 | 71.56 | 70.93 | 71.24 | |
| Spatio-Temporal Grounded Audio-Visual NetworkModel Domain=AVQA2022.03 | 71.56 | 76.38 | 74 | |
| Pano-AVQAModel Domain=AVQA2022.03 | 69.39 | 75.65 | 72.56 | |
| PSACModel Domain=VisualQA2022.03 | 68.64 | 69.79 | 69.22 | |
| HMEModel Domain=VideoQA2022.03 | 67.97 | 69.46 | 68.76 | |
| GRUModel Domain=AudioQA2022.03 | 67.72 | 70.11 | 68.93 | |
| CONVLSTMModel Domain=AudioQA2022.03 | 67.47 | 54.56 | 60.94 | |
| AVSDModel Domain=AVQA2022.03 | 67.39 | 74.19 | 70.83 | |
| BiLSTM AttnModel Domain=VisualQA2022.03 | 64.64 | 64.33 | 64.48 | |
| HCRNModel Domain=VideoQA2022.03 | 64.39 | 61.81 | 63.08 | |
| HCAttnModel Domain=VisualQA2022.03 | 64.05 | 66.37 | 65.22 | |
| FCNLSTMModel Domain=AudioQA2022.03 | 63.89 | 46.74 | 55.21 |