# Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering

arXiv: https://arxiv.org/abs/2310.06238 · HTML: https://mlsanity.com/paper/2310.06238/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 49 references that are in the map.
- First posted on arXiv 10 Oct 2023.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering](https://mlsanity.com/paper/1712.00377/) (2017)
- [YouTube-8M: A Large-Scale Video Classification Benchmark](https://mlsanity.com/paper/1609.08675/) (2016)
- [The Sound of Pixels](https://mlsanity.com/paper/1804.03160/) (2018)
- [Learning Individual Styles of Conversational Gesture](https://mlsanity.com/paper/1906.04160/) (2019)
- [Learning to Answer Questions in Dynamic Audio-Visual Scenarios](https://mlsanity.com/paper/2203.14072/) (2022)
- [RUBi: Reducing Unimodal Biases in Visual Question Answering](https://mlsanity.com/paper/1906.10169/) (2019)
- [Audio-Visual Segmentation](https://mlsanity.com/paper/2207.05042/) (2022)
- [The Sound of Motions](https://mlsanity.com/paper/1904.05979/) (2019)
- [Contrastive Audio-Visual Masked Autoencoder](https://mlsanity.com/paper/2210.07839/) (2022)
- [Learning to Separate Object Sounds by Watching Unlabeled Video](https://mlsanity.com/paper/1804.01665/) (2018)
- [Music Gesture for Visual Sound Separation](https://mlsanity.com/paper/2004.09476/) (2020)
- [Co-Separating Sounds of Visual Objects](https://mlsanity.com/paper/1904.07750/) (2019)
- [Yin and Yang: Balancing and Answering Binary Visual Questions](https://mlsanity.com/paper/1511.05099/) (2015)
- [Learning Representations from Audio-Visual Spatial Alignment](https://mlsanity.com/paper/2011.01819/) (2020)
- [Pano-AVQA: Grounded Audio-Visual Question Answering on 360^circ Videos](https://mlsanity.com/paper/2110.05122/) (2021)
- [Foley Music: Learning to Generate Music from Videos](https://mlsanity.com/paper/2007.10984/) (2020)
- [Robust Audio-Visual Instance Discrimination](https://mlsanity.com/paper/2103.15916/) (2021)
- [Vision Transformers are Parameter-Efficient Audio-Visual Learners](https://mlsanity.com/paper/2212.07983/) (2022)
- [Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation](https://mlsanity.com/paper/2104.02026/) (2021)

## Built on by (most cited first, 29 of 29)

- [OmniBench: Towards The Future of Universal Omni-Language Models](https://mlsanity.com/paper/2409.15272/) (2024)
- [Tell What You Hear From What You See -- Video to Audio Generation Through Text](https://mlsanity.com/paper/2411.05679/) (2024)
- [Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding](https://mlsanity.com/paper/2502.06020/) (2025)
- [Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time](https://mlsanity.com/paper/2407.01851/) (2024)
- [From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation](https://mlsanity.com/paper/2409.19132/) (2024)
- [UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models](https://mlsanity.com/paper/2411.01703/) (2024)
- [Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering](https://mlsanity.com/paper/2404.12020/) (2024)
- [Learning Musical Representations for Music Performance Question Answering](https://mlsanity.com/paper/2502.06710/) (2025)
- [SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing](https://mlsanity.com/paper/2506.05414/) (2025)
- [Question-Aware Gaussian Experts for Audio-Visual Question Answering](https://mlsanity.com/paper/2503.04459/) (2025)
- [Hedge Fund Portfolio Construction Using PolyModel Theory and iTransformer](https://mlsanity.com/paper/2408.03320/) (2024)
- [Journey into Automation: Image-Derived Pavement Texture Extraction and Evaluation](https://mlsanity.com/paper/2501.02414/) (2025)
- [Mamba Fusion: Learning Actions Through Questioning](https://mlsanity.com/paper/2409.11513/) (2024)
- [Music Audio-Visual Question Answering Requires Specialized Multimodal Designs](https://mlsanity.com/paper/2505.20638/) (2025)
- [Learning Sparsity for Effective and Efficient Music Performance Question Answering](https://mlsanity.com/paper/2506.01319/) (2025)
- [AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering](https://mlsanity.com/paper/2510.18346/) (2025)
- [SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering](https://mlsanity.com/paper/2411.04933/) (2024)
- [Do Modern Video-LLMs Need to Listen? A Benchmark Audit and Scalable Remedy](https://mlsanity.com/paper/2509.17901/) (2025)
- [Knowing When to Answer: Adaptive Confidence Refinement for Reliable Audio-Visual Question Answering](https://mlsanity.com/paper/2602.04924/) (2026)
- [ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction](https://mlsanity.com/paper/2503.20978/) (2025)
- [Unveiling Modality Bias: Automated Sample-Specific Analysis for Multimodal Misinformation Benchmarks](https://mlsanity.com/paper/2511.05883/) (2025)
- [ChromouVQA: Benchmarking Vision-Language Models under Chromatic Camouflaged Images](https://mlsanity.com/paper/2512.05137/) (2025)
- [FairFlow: Mitigating Dataset Biases through Undecided Learning](https://mlsanity.com/paper/2503.17632/) (2025)
- [Empathetic Cascading Networks: A Multi-Stage Prompting Technique for Reducing Social Biases in Large Language Models](https://mlsanity.com/paper/2511.18696/) (2025)
- [Multi-Modal Scene Graph with Kolmogorov-Arnold Experts for Audio-Visual Question Answering](https://mlsanity.com/paper/2511.23304/) (2025)
- [CogniRoute: Learning to Route Social Evidence in Omni-Modal Models](https://mlsanity.com/paper/2606.20970/) (2026)
- [Q-TriM: Question-Guided Tri-Modal Attention for Audio-Visual Question Answering](https://mlsanity.com/paper/2607.03825/) (2026)
- [The Platonic brain bridge hypothesis: human brain networks as an architectural prior for multimodal large language models](https://mlsanity.com/paper/2609.10947/) (2026)
- [Text-Centric Post-Training for Omni-Modal Reasoning](https://mlsanity.com/paper/2610.02819/) (2026)

## Abstract (arXiv)

In recent years, there has been a growing emphasis on the intersection of audio, vision, and text modalities, driving forward the advancements in multimodal research. However, strong bias that exists in any modality can lead to the model neglecting the others. Consequently, the model's ability to effectively reason across these diverse modalities is compromised, impeding further advancement. In this paper, we meticulously review each question type from the original dataset, selecting those with pronounced answer biases. To counter these biases, we gather complementary videos and questions, ensuring that no answers have outstanding skewed distribution. In particular, for binary questions, we strive to ensure that both answers are almost uniformly spread within each question category. As a result, we construct a new dataset, named MUSIC-AVQA v2.0, which is more challenging and we believe could better foster the progress of AVQA task. Furthermore, we present a novel baseline model that delves deeper into the audio-visual-text interrelation. On MUSIC-AVQA v2.0, this model surpasses all the existing benchmarks, improving accuracy by 2% on MUSIC-AVQA v2.0, setting a new state-of-the-art performance.