Teacher-Guided Pseudo Supervision and Cross-Modal Alignment for Audio-Visual Video Parsing
Yaru Chen, Ruohao Guo, Liting Gao, Zhenbo Li, Wenwu Wang
Abstract
Weakly-supervised audio-visual video parsing (AVVP) seeks to detect audible, visible, and audio-visual events without temporal annotations. Previous work has emphasized refining global predictions through contrastive or collaborative learning, but neglected stable segment-level supervision and class-aware cross-modal alignment. To address this, we propose two strategies: (1) an exponential moving average (EMA)-guided pseudo supervision framework that generates reliable segment-level masks via adaptive thresholds or top-k selection, offering stable temporal guidance beyond video-level labels; and (2) a class-aware cross-modal agreement (CMA) loss that aligns audio and visual embeddings at reliable segment-class pairs, ensuring consistency across modalities while preserving temporal structure. Evaluations on LLP and UnAV-100 datasets shows that our method achieves state-of-the-art (SOTA) performance across multiple metrics.
BibTeX
@inproceedings{icassp2026_teacherguidedpse,
title = {Teacher-Guided Pseudo Supervision and Cross-Modal Alignment for Audio-Visual Video Parsing},
author = {Yaru Chen and Ruohao Guo and Liting Gao and Zhenbo Li and Wenwu Wang},
booktitle = {ICASSP 2026},
year = {2026}
}