THE DCASE 2021 CHALLENGE TASK 6 SYSTEM: AUTOMATED AUDIO CAPTIONING WITH WEAKLY SUPERVISED PRE-TRAING AND WORD SELECTION METHODS
Open paper
Benchmark
Model
Rank
Results
audio-captioning-on-clotho
Ensemble
–
SPIDEr: 0.318
CIDEr: 0.400
SPICE: 0.137
Rank counts only results with a code link.