# Micro-AU CLIP: Fine-Grained Contrastive Learning from Local Independence to Global Dependency for Micro-Expression Action Unit Detection

arXiv: https://arxiv.org/abs/2603.16302 · HTML: https://mlsanity.com/paper/2603.16302/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 43 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition](https://mlsanity.com/paper/2205.01782/) (2022)
- [JhatAA-Net: Joint Facial Action Unit Detection and Face Alignment via Adaptive Attention](https://mlsanity.com/paper/2003.08834/) (2020)
- [Facial Action Unit Detection Using Attention and Relation Learning](https://mlsanity.com/paper/1808.03457/) (2018)
- [Learning-based Video Motion Magnification](https://mlsanity.com/paper/1804.02684/) (2018)
- [Micron-BERT: BERT-based Facial Micro-Expression Recognition](https://mlsanity.com/paper/2304.03195/) (2023)
- [Less is More: Micro-expression Recognition from Video using Apex Frame](https://mlsanity.com/paper/1606.01721/) (2016)
- [AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors](https://mlsanity.com/paper/2403.04697/) (2024)
- [CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling](https://mlsanity.com/paper/2409.19291/) (2024)
- [Short and Long Range Relation Based Spatio-Temporal Transformer for Micro-Expression Recognition](https://mlsanity.com/paper/2112.05851/) (2021)
- [Objective Class-based Micro-Expression Recognition through Simultaneous Action Unit Detection and Feature Aggregation](https://mlsanity.com/paper/2012.13148/) (2020)
- [Multimodal Emotion Recognition with Vision-language Prompting and Modality Dropout](https://mlsanity.com/paper/2409.07078/) (2024)
- [AU-LLM: Micro-Expression Action Unit Detection via Enhanced LLM-Based Feature Fusion](https://mlsanity.com/paper/2507.21778/) (2025)
- [Geometric Graph Representation with Learnable Graph Structure and Adaptive AU Constraint for Micro-Expression Recognition](https://mlsanity.com/paper/2205.00380/) (2022)
- [Contrastive Learning of Person-independent Representations for Facial Action Unit Detection](https://mlsanity.com/paper/2403.03400/) (2024)
- [MER-CLIP: AU-Guided Vision-Language Alignment for Micro-Expression Recognition](https://mlsanity.com/paper/2505.05937/) (2025)
- [Prior Information based Decomposition and Reconstruction Learning for Micro-Expression Recognition](https://mlsanity.com/paper/2303.01776/) (2023)

## Abstract (arXiv)

Micro-expression (ME) action units (Micro-AUs) provide objective clues for fine-grained genuine emotion analysis. Most existing Micro-AU detection methods learn AU features from the whole facial image/video, which conflicts with the inherent locality of AU, resulting in insufficient perception of AU regions. In fact, each AU independently corresponds to specific localized facial muscle movements (local independence), while there is an inherent dependency between some AUs under specific emotional states (global dependency). Thus, this paper explores the effectiveness of the independence-to-dependency pattern and proposes a novel micro-AU detection framework, micro-AU CLIP, that uniquely decomposes the AU detection process into local semantic independence modeling (LSI) and global semantic dependency (GSD) modeling. In LSI, Patch Token Attention (PTA) is designed, mapping several local features within the AU region to the same feature space; In GSD, Global Dependency Attention (GDA) and Global Dependency Loss (GDLoss) are presented to model the global dependency relationships between different AUs, thereby enhancing each AU feature. Furthermore, considering CLIP's native limitations in micro-semantic alignment, a microAU contrastive loss (MiAUCL) is designed to learn AU features by a fine-grained alignment of visual and text features. Also, Micro-AU CLIP is effectively applied to ME recognition in an emotion-label-free way. The experimental results demonstrate that Micro-AU CLIP can fully learn fine-grained micro-AU features, achieving state-of-the-art performance.