AVS

The 'AVS' dataset is used to evaluate multimodal tasks, specifically focusing on audio-visual interactions.

Papers using AVS (3)

TB-AVA: Text as a Semantic Bridge for Audio-Visual Parameter Efficient Finetuning2026CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks2026CAE-AV: Improving Audio-Visual Learning via Cross-modal Interactive Enrichment2026