Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Audio-visual event classification on AudioSet 20K
Loading...
42.4
mAP (Audio-only)
EquiAV
28.256
31.928
35.6
39.272
Mar 14, 2024
Apr 15, 2024
May 18, 2024
Jun 20, 2024
Jul 23, 2024
Aug 25, 2024
Sep 27, 2024
mAP (Audio-only)
mAP (Visual-only)
mAP (Audio-visual)
Updated 4d ago
Evaluation Results
Method
Method
Links
mAP (Audio-only)
mAP (Visual-only)
mAP (Audio-visual)
EquiAV
Pretrain=SSL
2024.03
42.4
25.7
46.6
MAVIL
Pretrain=SSL
2024.03
41.8
24.8
44.9
MAVIL
2024.09
41.8
24.8
44.9
CAV-MAE
Pretrain=SSL
2024.03
37.7
19.8
42
CAV-MAE
2024.09
37.7
19.8
42
MBT*
Pretrain=IN21K SL
2024.03
31.3
27.7
43.9
MBT
2024.09
31.3
27.7
43.9
GBlend
2024.03
29.1
22.1
37.8
G-Blend
2024.09
29.1
22.1
37.8
VAB-Encodec
Audio Tokenizer=Encodec
2024.09
29
29
38.7
VAB-DAC
Audio Tokenizer=DAC
2024.09
28.8
28.3
38.9
Feedback
Search any
task
Search any
task