Audio-Visual Captioning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
51.52Cs Score
14
May 12, 2026
57CIDEr
11
Jun 11, 2026
16.23Cs
10
May 12, 2026
78Accuracy
7
Feb 26, 2026
81.1Accuracy
7
Feb 26, 2026
16.88BLEU@4
7
Feb 26, 2026
17.2METEOR
5
Apr 16, 2026
63.7ALOHa Score
4
May 12, 2026
38.8ALOHa
4
May 12, 2026
0.529BLEU
4
Mar 11, 2026
40.49BLEU
4
Mar 11, 2026
62.2CIDEr
4
Feb 26, 2026
40.52Cs
2
May 12, 2026