Rethinking Transfer and Auxiliary Learning for Improving Audio Captioning Transformer
Open paper
Benchmark
Model
Rank
Results
audio-captioning-on-audiocaps
Rethink-ACT (AST + TF + MIL)
–
SPIDEr: 0.472
CIDEr: 0.764
SPICE: 0.180
BLEU-4: 0.285
METEOR: 0.242
…
Rank counts only results with a code link.