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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Jiayu, Ye, Shuo, Ye, Qilang, Song, Zihan, Huang, Jiajian, Yu, Zitong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911591260225536
author Zhang, Jiayu
Ye, Shuo
Ye, Qilang
Song, Zihan
Huang, Jiajian
Yu, Zitong
author_facet Zhang, Jiayu
Ye, Shuo
Ye, Qilang
Song, Zihan
Huang, Jiajian
Yu, Zitong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10695
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Retrieving to Recover: Towards Incomplete Audio-Visual Question Answering via Semantic-consistent Purification
Zhang, Jiayu
Ye, Shuo
Ye, Qilang
Song, Zihan
Huang, Jiajian
Yu, Zitong
Computer Vision and Pattern Recognition
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.
title Retrieving to Recover: Towards Incomplete Audio-Visual Question Answering via Semantic-consistent Purification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.10695