# FVQ: A Large-Scale Dataset and an LMM-based Method for Face Video Quality Assessment

arXiv: https://arxiv.org/abs/2504.09255 · HTML: https://mlsanity.com/paper/2504.09255/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 81 references that are in the map.
- First posted on arXiv 12 Apr 2025.

## Builds on (most cited first, 30 of 43)

- [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)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [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)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives](https://mlsanity.com/paper/2211.04894/) (2022)
- [CelebV-HQ: A Large-Scale Video Facial Attributes Dataset](https://mlsanity.com/paper/2207.12393/) (2022)
- [Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization](https://mlsanity.com/paper/2411.10442/) (2024)
- [FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling](https://mlsanity.com/paper/2207.02595/) (2022)
- [Quality Assessment of In-the-Wild Videos](https://mlsanity.com/paper/1908.00375/) (2019)
- [Patch-VQ: 'Patching Up' the Video Quality Problem](https://mlsanity.com/paper/2011.13544/) (2020)
- [Robust High-Resolution Video Matting with Temporal Guidance](https://mlsanity.com/paper/2108.11515/) (2021)
- [A Deep Learning based No-reference Quality Assessment Model for UGC Videos](https://mlsanity.com/paper/2204.14047/) (2022)
- [Large-Scale Study of Perceptual Video Quality](https://mlsanity.com/paper/1803.01761/) (2018)
- [SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness](https://mlsanity.com/paper/2003.09373/) (2020)
- [CelebV-Text: A Large-Scale Facial Text-Video Dataset](https://mlsanity.com/paper/2303.14717/) (2023)
- [RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content](https://mlsanity.com/paper/2101.10955/) (2021)
- [Face Image Quality Assessment: A Literature Survey](https://mlsanity.com/paper/2009.01103/) (2020)
- [CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability](https://mlsanity.com/paper/2112.06592/) (2021)
- [SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distance](https://mlsanity.com/paper/2103.05977/) (2021)

## Built on by (most cited first, 13 of 13)

- [AGHI-QA: A Subjective-Aligned Dataset and Metric for AI-Generated Human Images](https://mlsanity.com/paper/2504.21308/) (2025)
- [RGC-VQA: An Exploration Database for Robotic-Generated Video Quality Assessment](https://mlsanity.com/paper/2506.23852/) (2025)
- [Engagement Prediction of Short Videos with Large Multimodal Models](https://mlsanity.com/paper/2508.02516/) (2025)
- [Efficient Face Image Quality Assessment via Self-training and Knowledge Distillation](https://mlsanity.com/paper/2507.15709/) (2025)
- [DHQA-4D: Perceptual Quality Assessment of Dynamic 4D Digital Human](https://mlsanity.com/paper/2510.03874/) (2025)
- [VTONQA: A Multi-Dimensional Quality Assessment Dataset for Virtual Try-on](https://mlsanity.com/paper/2601.02945/) (2026)
- [Q-Bench-Portrait: Benchmarking Multimodal Large Language Models on Portrait Image Quality Perception](https://mlsanity.com/paper/2601.18346/) (2026)
- [Multi-Dimensional Quality Assessment for AI-Generated Human-Centric Videos: Dataset and Model](https://mlsanity.com/paper/2607.16742/) (2026)
- [Exploring Instruction Data Quality for Explainable Image Quality Assessment](https://mlsanity.com/paper/2510.03880/) (2025)
- [VideoAesBench: Benchmarking the Video Aesthetics Perception Capabilities of Large Multimodal Models](https://mlsanity.com/paper/2601.21915/) (2026)
- [FMReward: Aligning and Evaluating Audio-Driven 3D Facial Animation with Human Preferences](https://mlsanity.com/paper/2608.15296/) (2026)
- [Employing Vision-Language Models for Face Image Quality Assessment](https://mlsanity.com/paper/2605.17489/) (2026)
- [CamWorldQA: Perceptual Quality Assessment of Camera-Controlled World Video Generation](https://mlsanity.com/paper/2608.18710/) (2026)

## Abstract (arXiv)

Face video quality assessment (FVQA) deserves to be explored in addition to general video quality assessment (VQA), as face videos are the primary content on social media platforms and human visual system (HVS) is particularly sensitive to human faces. However, FVQA is rarely explored due to the lack of large-scale FVQA datasets. To fill this gap, we present the first large-scale in-the-wild FVQA dataset, FVQ-20K, which contains 20,000 in-the-wild face videos together with corresponding mean opinion score (MOS) annotations. Along with the FVQ-20K dataset, we further propose a specialized FVQA method named FVQ-Rater to achieve human-like rating and scoring for face video, which is the first attempt to explore the potential of large multimodal models (LMMs) for the FVQA task. Concretely, we elaborately extract multi-dimensional features including spatial features, temporal features, and face-specific features (i.e., portrait features and face embeddings) to provide comprehensive visual information, and take advantage of the LoRA-based instruction tuning technique to achieve quality-specific fine-tuning, which shows superior performance on both FVQ-20K and CFVQA datasets. Extensive experiments and comprehensive analysis demonstrate the significant potential of the FVQ-20K dataset and FVQ-Rater method in promoting the development of FVQA.