# Teacher-Guided Pseudo Supervision and Cross-Modal Alignment for Audio-Visual Video Parsing

arXiv: https://arxiv.org/abs/2509.14097 · HTML: https://mlsanity.com/paper/2509.14097/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 17 Sep 2025.

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing](https://mlsanity.com/paper/2007.10558/) (2020)
- [Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline](https://mlsanity.com/paper/2303.12930/) (2023)
- [Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing](https://mlsanity.com/paper/2204.11573/) (2022)
- [Audio-Visual Instance Segmentation](https://mlsanity.com/paper/2310.18709/) (2023)
- [Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser](https://mlsanity.com/paper/2305.17343/) (2023)
- [Boosting Audio Visual Question Answering via Key Semantic-Aware Cues](https://mlsanity.com/paper/2407.20693/) (2024)
- [CoLeaF: A Contrastive-Collaborative Learning Framework for Weakly Supervised Audio-Visual Video Parsing](https://mlsanity.com/paper/2405.10690/) (2024)
- [CM-PIE: Cross-modal perception for interactive-enhanced audio-visual video parsing](https://mlsanity.com/paper/2310.07517/) (2023)
- [Reinforced Label Denoising for Weakly-Supervised Audio-Visual Video Parsing](https://mlsanity.com/paper/2412.19563/) (2024)

## Built on by (most cited first, 1 of 1)

- [EAR: Enhancing Uni-Modal Representations for Weakly Supervised Audio-Visual Video Parsing](https://mlsanity.com/paper/2605.08723/) (2026)

## Abstract (arXiv)

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.