List your company

Audio Captioning on MusicCaps

23.33Captioning ScorePAR (Ours-UTS)
22.019622.359822.723.0402Mar 26, 2026

Evaluation results

MethodLinks
PAR (Ours-UTS)Label=Tag Sequence*, Evaluation Protocol=audio-language alignment2026.0323.33—
MTC (Ours-UTS)Label=Tag*, Evaluation Protocol=audio-language alignment2026.0323.28—
Multi-Task (Ours)Label=Tag*, Caption*, Evaluation Protocol=audio-language alignment2026.0323.09—
MTC (AudioSet)Label=Tag, Evaluation Protocol=audio-language alignment2026.0322.91—
Contrastive-scratch (Ours)Label=Caption*, Evaluation Protocol=audio-language alignment2026.0322.83—
Captioning-scratch (Ours)Label=Caption*, Evaluation Protocol=audio-language alignment2026.0322.83—
Captioning-scratchLabel=Caption, Evaluation Protocol=audio-language alignment2026.0322.62—
Contrastive-scratchLabel=Caption, Evaluation Protocol=audio-language alignment2026.0322.07—
Kimi-Audio-InstructDecoder Size=7B2025.08—35.43
MiDashengLMDecoder Size=7B2025.08—59.71
Qwen2.5-OmniDecoder Size=7B2025.08—43.71