Audio-visual understanding requires effective alignment between heterogeneous modalities, yet cross-modal correspondence remains challenging when temporally aligned audio and visual signals lack clear semantic correspondence. We propose to use text as a semantic anchor for audio-visual representation learning. To this end, we introduce a parameter-efficient adaptation framework built on frozen audio and visual encoders, centered on Text-Bridged Audio-Visual Adapter (TB-AVA), which enables text-mediated interaction between audio and visual streams. At the core of TB-AVA, Gated Semantic Modulation (GSM) selectively modulates feature channels based on text-inferred semantic relevance. We evaluate the proposed approach on multiple benchmarks, including AVE, AVS, and AVVP, where the proposed framework achieves state-of-the-art performance, demonstrating text as an effective semantic anchor for parameter-efficient fine-tuning (PEFT) in audio-visual learning.
@article{arxiv.2605.11572,
title = {TB-AVA: Text as a Semantic Bridge for Audio-Visual Parameter Efficient Finetuning},
author = {Seongah Kim and Dinh Phu Tran and Hyeontaek Hwang and Saad Wazir and Duc Do Minh and Daeyoung Kim},
journal= {arXiv preprint arXiv:2605.11572},
year = {2026}
}