# MDS-VQA: Model-Informed Data Selection for Video Quality Assessment

arXiv: https://arxiv.org/abs/2603.11525 · HTML: https://mlsanity.com/paper/2603.11525/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 52 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling](https://mlsanity.com/paper/2207.02595/) (2022)
- [Patch-VQ: 'Patching Up' the Video Quality Problem](https://mlsanity.com/paper/2011.13544/) (2020)
- [Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild](https://mlsanity.com/paper/2005.13983/) (2020)
- [Large-Scale Study of Perceptual Video Quality](https://mlsanity.com/paper/1803.01761/) (2018)
- [YouTube UGC Dataset for Video Compression Research](https://mlsanity.com/paper/1904.06457/) (2019)
- [Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception](https://mlsanity.com/paper/2108.08505/) (2021)
- [VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank](https://mlsanity.com/paper/2505.14460/) (2025)
- [Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training](https://mlsanity.com/paper/2011.04263/) (2020)
- [Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models](https://mlsanity.com/paper/2307.13981/) (2023)
- [Pool-Based Sequential Active Learning for Regression](https://mlsanity.com/paper/1805.04735/) (2018)
- [VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning](https://mlsanity.com/paper/2506.18564/) (2025)
- [Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment](https://mlsanity.com/paper/2003.03849/) (2020)
- [AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM](https://mlsanity.com/paper/2411.17221/) (2024)
- [Modular Blind Video Quality Assessment](https://mlsanity.com/paper/2402.19276/) (2024)
- [Deep Ensemble Bayesian Active Learning : Addressing the Mode Collapse issue in Monte Carlo dropout via Ensembles](https://mlsanity.com/paper/1811.03897/) (2018)
- [Towards Free Data Selection with General-Purpose Models](https://mlsanity.com/paper/2309.17342/) (2023)
- [YouTube SFV+HDR Quality Dataset](https://mlsanity.com/paper/2406.05305/) (2024)
- [Assessment of Subjective and Objective Quality of Live Streaming Sports Videos](https://mlsanity.com/paper/2106.08431/) (2021)
- [Image Quality Assessment: Integrating Model-Centric and Data-Centric Approaches](https://mlsanity.com/paper/2207.14769/) (2022)

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

- [Comparison Drives Preference: Reference-Aware Modeling for AI-Generated Video Quality Assessment](https://mlsanity.com/paper/2604.17074/) (2026)

## Abstract (arXiv)

Learning-based video quality assessment (VQA) has advanced rapidly, yet progress is increasingly constrained by a disconnect between model design and dataset curation. Model-centric approaches often iterate on fixed benchmarks, while data-centric efforts collect new human labels without systematically targeting the weaknesses of existing VQA models. Here, we describe MDS-VQA, a model-informed data selection mechanism for curating unlabeled videos that are both difficult for the base VQA model and diverse in content. Difficulty is estimated by a failure predictor trained with a ranking objective, and diversity is measured using deep semantic video features, with a greedy procedure balancing the two under a constrained labeling budget. Experiments across multiple VQA datasets and models demonstrate that MDS-VQA identifies diverse, challenging samples that are particularly informative for active fine-tuning. With only a 5% selected subset per target domain, the fine-tuned model improves mean SRCC from 0.651 to 0.722 and achieves the top gMAD rank, indicating strong adaptation and generalization.