Generalized Zero-Shot Classification on AudioSet ZSL (test)
50.96mAcc (Seen)AVGZSLNet
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| AVGZSLNetTest Modality=both, fusion=with attention2020.05 | 50.96 | 32.73 | 39.86 | |
| CONSETest Modality=video2020.05 | 48.5 | 19.6 | 27.9 | |
| AVGZSLNetTest Modality=video2020.05 | 48.05 | 30.71 | 37.47 | |
| ALETest Modality=video2020.05 | 47.9 | 25.2 | 33 | |
| AVGZSLNetTest Modality=both, fusion=equal weight2020.05 | 46.04 | 33.8 | 38.98 | |
| audio-video concat modelTest Modality=both2020.05 | 45.83 | 27.91 | 34.7 | |
| video only modelTest Modality=video2020.05 | 43.27 | 27.11 | 33.34 | |
| CJMETest Modality=video2020.05 | 41.53 | 28.76 | 33.99 | |
| CJMETest Modality=both, fusion=with attention2020.05 | 41.07 | 29.58 | 34.39 | |
| DEVISETest Modality=video2020.05 | 39.8 | 26 | 31.5 | |
| ESZSLTest Modality=video2020.05 | 33.8 | 19 | 24.3 | |
| AVGZSLNetTest Modality=audio2020.05 | 33.29 | 20.43 | 25.32 | |
| CJMETest Modality=both, fusion=equal weight2020.05 | 30.29 | 31.3 | 30.79 | |
| SAETest Modality=video2020.05 | 29.3 | 19.3 | 23.2 | |
| audio only modelTest Modality=audio2020.05 | 28.35 | 18.35 | 22.22 | |
| CJMETest Modality=audio2020.05 | 25.58 | 20.3 | 22.64 |