AudioSet

anchor

Findings

• IC-124Direct comparison of CLIP image embeddings with CLAP audio embeddings achieves near-chance retrieval, while logsumexp bridging through the shared language modality recovers 62% recall@10 on AudioSet [eval]
• IC-125LanguageBind's direct evaluation achieves 70% recall@10 on AudioSet, empirically validating that the inner product between unpaired modality representations recovers the correct probability ratio [eval]
• IC-126CLIP and CLAP language representations are statistically indistinguishable from a uniform distribution on the hypersphere [eval]
• IC-127ImageBind's direct evaluation closely matches logsumexp for both vision-language and audio-language alignment, validating the law for ImageBind [eval]
• IC-981ImageBind's indirect alignment through images degrades zero-shot performance on non-visual modalities and prevents emergent cross-modal retrieval [eval]