# AU-Guided Synthetic Video Generation for Micro-Expression Recognition

arXiv: https://arxiv.org/abs/2607.10860 · HTML: https://mlsanity.com/paper/2607.10860/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 12 Jul 2026.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [Investigating Bias and Fairness in Facial Expression Recognition](https://mlsanity.com/paper/2007.10075/) (2020)
- [Understanding the Impact of Negative Prompts: When and How Do They Take Effect?](https://mlsanity.com/paper/2406.02965/) (2024)
- [Deep Learning for Micro-expression Recognition: A Survey](https://mlsanity.com/paper/2107.02823/) (2021)
- [PyTorch Image Quality: Metrics for Image Quality Assessment](https://mlsanity.com/paper/2208.14818/) (2022)
- [SAMM Long Videos: A Spontaneous Facial Micro- and Macro-Expressions Dataset](https://mlsanity.com/paper/1911.01519/) (2019)
- [Spontaneous Facial Micro-Expression Recognition using 3D Spatiotemporal Convolutional Neural Networks](https://mlsanity.com/paper/1904.01390/) (2019)
- [An Overview of Facial Micro-Expression Analysis: Data, Methodology and Challenge](https://mlsanity.com/paper/2012.11307/) (2020)
- [Micro-expression spotting: A new benchmark](https://mlsanity.com/paper/2007.12421/) (2020)
- [Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition](https://mlsanity.com/paper/2303.15889/) (2023)
- [How to Synthesize a Large-Scale and Trainable Micro-Expression Dataset?](https://mlsanity.com/paper/2112.01730/) (2021)
- [Distributional bias compromises leave-one-out cross-validation](https://mlsanity.com/paper/2406.01652/) (2024)

## Abstract (arXiv)

Micro-expression recognition is limited by the small scale, narrow demographic coverage, and restricted emotion labels of existing datasets. We introduce EquiME, a synthetic micro-expression dataset built from AU-guided image-to-video generation. EquiME contains 75K videos generated from 15K source face images across five target emotions, together with automatically inferred demographic metadata and video-quality measurements. We evaluate EquiME using frame-pair similarity, spatial variation, and no-reference perceptual-quality metrics, together with cross-dataset MER experiments on SAMM and CASME II. Models trained on EquiME achieve competitive cross-dataset performance on SAMM and CASME II and show comparatively low variation across the four evaluated architectures. This paper focuses on the dataset design, the structured AU-conditioning pipeline used for video generation, and the empirical evidence needed to assess EquiME as a synthetic MER resource. Project page: https://kirito-blade.github.io/me-vlm/