Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

MUSIC-AVQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Audio-Visual Question AnsweringMUSIC-AVQA 1.0 (test)
AV Localis Accuracy85.09
96
Audio-Visual Question AnsweringMUSIC-AVQA (test)
Acc (Avg)80.7
59
Audio Question AnsweringMUSIC-AVQA 1.0 (test)
Counting Accuracy84.86
43
Audio-Visual Question AnsweringMusic-AVQA
Accuracy81.3
21
Overall Audio-Visual Question AnsweringMUSIC-AVQA (test)
Overall Accuracy71.52
21
Audio-Video Question AnsweringMUSIC-AVQA
AV Temporal Acc51.77
19
Audio-Visual Question AnsweringMUSIC-AVQA Bias v2.0 (test)
Total Accuracy77.33
18
Audio-Visual Question AnsweringMUSIC-AVQA balanced v2.0 (test)
Total Accuracy75.44
18
Audio Question AnsweringMUSIC-AVQA (test)
Accuracy (Avg)80.51
17
Visual Question AnsweringMUSIC-AVQA v1.0 (test)
Accuracy (Count)0.8396
16
Audio-Visual Question AnsweringMUSIC-AVQA-R (test)
Audio QA Count (Head)82.67
13
Visual Question AnsweringMUSIC-AVQA (test)
Accuracy (Counting)71.56
12
Audio-Visual Question AnsweringMUSIC-AVQA balanced (test)
Existential Score83.62
8
Audio-Visual Question AnsweringMusic-AVQA 2000 samples
ASR Rate13.8
7
Audio Visual Question AnsweringMusic-AVQA
Music-AVQA Clean Accuracy80.7
7
Audio-Visual Question AnsweringMusic-AVQA 30 (test)
Overall Accuracy84.3
7
Audio-Visual Question AnsweringMUSIC-AVQA 2.0 (test)
Accuracy (Audio, Count)83.82
4
Audio-Visual Question AnsweringMUSIC-AVQA Contrasting Binary QA pairs v2.0
Total Accuracy58.86
4
Video Question AnsweringMUSIC-AVQA
Accuracy80.7
2
Showing 19 of 19 rows