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

Source: [Retrieving to Recover: Towards Incomplete Audio-Visual Question Answering via Semantic-consistent Purification](<https://www.sota2.com/research/paper/69ddca1c7d0172140ec79a74>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-16T05:00:04.684Z

Authors: Jiayu Zhang, Shuo Ye, Qilang Ye, Zihan Song, Jiajian Huang, Zitong Yu

Published: 2026-04-12T15:43:30.000Z

## Abstract

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 R$^{2}$ScP, 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 R$^{2}$ScP significantly improves AVQA and enhances robustness in modal-incomplete scenarios.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.10695>)

[PDF](<https://arxiv.org/pdf/2604.10695.pdf>)