LAVCap

Reported on 6 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio6 results

Audio captioningonAudioCaps
BLEU-4· 2025-01-16
0.297
best: 14.3 (Audio Flamingo)
LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport arXiv:2501.09291
Audio captioningonAudioCaps
CIDEr· 2025-01-16
0.849
best: 50.2 (Audio Flamingo)
LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport arXiv:2501.09291
Audio captioningonAudioCaps
METEOR· 2025-01-16
0.262
best: 20.5 (Audio Flamingo)
LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport arXiv:2501.09291
Audio captioningonAudioCaps
ROUGE-L· 2025-01-16
0.51
best: 40.8 (Audio Flamingo)
LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport arXiv:2501.09291
Audio captioningonAudioCaps
SPICE· 2025-01-16
0.185
best: 15.1 (Audio Flamingo)
LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport arXiv:2501.09291
Audio captioningonAudioCaps
SPIDEr· 2025-01-16
0.517
best: 32.6 (Audio Flamingo)
LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport arXiv:2501.09291