# Addressing Missing and Noisy Modalities in One Solution: Unified Modality-Quality Framework for Low-quality Multimodal Data

arXiv: https://arxiv.org/abs/2603.02695 · HTML: https://mlsanity.com/paper/2603.02695/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 77 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts](https://mlsanity.com/paper/2206.02770/) (2022)
- [Learning Robust Representations via Multi-View Information Bottleneck](https://mlsanity.com/paper/2002.07017/) (2020)
- [Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2102.04830/) (2021)
- [Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)](https://mlsanity.com/paper/1906.01815/) (2019)
- [Learning Factorized Multimodal Representations](https://mlsanity.com/paper/1806.06176/) (2018)
- [UR-FUNNY: A Multimodal Language Dataset for Understanding Humor](https://mlsanity.com/paper/1904.06618/) (2019)
- [Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2109.00412/) (2021)
- [GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation](https://mlsanity.com/paper/2203.02177/) (2022)
- [Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis](https://mlsanity.com/paper/1911.05544/) (2019)
- [Decoupled Multimodal Distilling for Emotion Recognition](https://mlsanity.com/paper/2303.13802/) (2023)
- [Multimodal Representation Learning by Alternating Unimodal Adaptation](https://mlsanity.com/paper/2311.10707/) (2023)
- [HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding](https://mlsanity.com/paper/2501.15111/) (2025)

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

- [Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science](https://mlsanity.com/paper/2603.15381/) (2026)

## Abstract (arXiv)

Multimodal data encountered in real-world scenarios are typically of low quality, with noisy modalities and missing modalities being typical forms that severely hinder model performance and robustness. However, prior works often handle noisy and missing modalities separately. In contrast, we jointly address missing and noisy modalities to enhance model robustness in low-quality data scenarios. We regard both noisy and missing modalities as a unified low-quality modality problem, and propose a unified modality-quality (UMQ) framework to enhance low-quality representations for multimodal affective computing. Firstly, we train a quality estimator with explicit supervised signals via a rank-guided training strategy that compares the relative quality of different representations by adding a ranking constraint, avoiding training noise caused by inaccurate absolute quality labels. Then, a quality enhancer for each modality is constructed, which uses the sample-specific information provided by other modalities and the modality-specific information provided by the defined modality baseline representation to enhance the quality of unimodal representations. Finally, we propose a quality-aware mixture-of-experts module with particular routing mechanism to enable multiple modality-quality problems to be addressed more specifically. UMQ consistently outperforms state-of-the-art baselines on multiple datasets under the settings of complete, missing, and noisy modalities.