# Retrieving to Recover: Towards Incomplete Audio-Visual Question Answering via Semantic-consistent Purification

arXiv: https://arxiv.org/abs/2604.10695 · HTML: https://mlsanity.com/paper/2604.10695/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 42 references that are in the map.
- First posted on arXiv 12 Apr 2026.

## Builds on (most cited first, 15 of 15)

- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Learning to Answer Questions in Dynamic Audio-Visual Scenarios](https://mlsanity.com/paper/2203.14072/) (2022)
- [Are Multimodal Transformers Robust to Missing Modality?](https://mlsanity.com/paper/2204.05454/) (2022)
- [Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling](https://mlsanity.com/paper/2307.14126/) (2023)
- [Deep Multimodal Learning with Missing Modality: A Survey](https://mlsanity.com/paper/2409.07825/) (2024)
- [FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mamba](https://mlsanity.com/paper/2404.09498/) (2024)
- [I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts](https://mlsanity.com/paper/2505.19190/) (2025)
- [UniEmo: Unifying Emotional Understanding and Generation with Learnable Expert Queries](https://mlsanity.com/paper/2507.23372/) (2025)
- [H-GAR: A Hierarchical Interaction Framework via Goal-Driven Observation-Action Refinement for Robotic Manipulation](https://mlsanity.com/paper/2511.17079/) (2025)
- [DeltaVLA: Prior-Guided Vision-Language-Action Models via World Knowledge Variation](https://mlsanity.com/paper/2603.08361/) (2026)
- [Synergistic Prompting for Robust Visual Recognition with Missing Modalities](https://mlsanity.com/paper/2507.07802/) (2025)
- [When Eyes and Ears Disagree: Can MLLMs Discern Audio-Visual Confusion?](https://mlsanity.com/paper/2511.10059/) (2025)
- [SVC 2025: the First Multimodal Deception Detection Challenge](https://mlsanity.com/paper/2508.04129/) (2025)
- [Learning Trimodal Relation for Audio-Visual Question Answering with Missing Modality](https://mlsanity.com/paper/2407.16171/) (2024)
- [I3-MRec: Invariant Learning with Information Bottleneck for Incomplete Modality Recommendation](https://mlsanity.com/paper/2508.04247/) (2025)

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

- [MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding](https://mlsanity.com/paper/2606.09641/) (2026)

## Abstract (arXiv)

Recent Audio-Visual Question Answering (AVQA) methods have advanced significantly. However, most AVQA methods lack effective mechanisms for handling missing modalities, suffering from severe performance degradation in real-world scenarios with data interruptions. Furthermore, prevailing methods for handling missing modalities predominantly rely on generative imputation to synthesize missing features. While partially effective, these methods tend to capture inter-modal commonalities but struggle to acquire unique, modality-specific knowledge within the missing data, leading to hallucinations and compromised reasoning accuracy. To tackle these challenges, we propose R2ScP, a novel framework that shifts the paradigm of missing modality handling from traditional generative imputation to retrieval-based recovery. Specifically, we leverage cross-modal retrieval via unified semantic embeddings to acquire missing domain-specific knowledge. To maximize semantic restoration, we introduce a context-aware adaptive purification mechanism that eliminates latent semantic noise within the retrieved data. Additionally, we employ a two-stage training strategy to explicitly model the semantic relationships between knowledge from different sources. Extensive experiments demonstrate that R2ScP significantly improves AVQA and enhances robustness in modal-incomplete scenarios.