# SAC2-Net: Semantic Anchoring and Complementary-Consensus Fusion for Multimodal Micro-Expression Recognition

arXiv: https://arxiv.org/abs/2606.25542 · HTML: https://mlsanity.com/paper/2606.25542/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 24 Jun 2026.

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization](https://mlsanity.com/paper/2303.14189/) (2023)
- [OFF-ApexNet on Micro-expression Recognition System](https://mlsanity.com/paper/1805.08699/) (2018)
- [Deep Learning for Micro-expression Recognition: A Survey](https://mlsanity.com/paper/2107.02823/) (2021)
- [Micron-BERT: BERT-based Facial Micro-Expression Recognition](https://mlsanity.com/paper/2304.03195/) (2023)
- [Shallow Triple Stream Three-dimensional CNN (STSTNet) for Micro-expression Recognition](https://mlsanity.com/paper/1902.03634/) (2019)
- [Less is More: Micro-expression Recognition from Video using Apex Frame](https://mlsanity.com/paper/1606.01721/) (2016)
- [MER-GCN: Micro Expression Recognition Based on Relation Modeling with Graph Convolutional Network](https://mlsanity.com/paper/2004.08915/) (2020)
- [HTNet for micro-expression recognition](https://mlsanity.com/paper/2307.14637/) (2023)
- [Spontaneous Facial Micro-Expression Recognition using 3D Spatiotemporal Convolutional Neural Networks](https://mlsanity.com/paper/1904.01390/) (2019)
- [Feature Representation Learning with Adaptive Displacement Generation and Transformer Fusion for Micro-Expression Recognition](https://mlsanity.com/paper/2304.04420/) (2023)
- [DFME: A New Benchmark for Dynamic Facial Micro-expression Recognition](https://mlsanity.com/paper/2301.00985/) (2023)
- [Stronger Normalization-Free Transformers](https://mlsanity.com/paper/2512.10938/) (2025)
- [MOL: Joint Estimation of Micro-Expression, Optical Flow, and Landmark via Transformer-Graph-Style Convolution](https://mlsanity.com/paper/2506.14511/) (2025)
- [Learning to Rank Onset-Occurring-Offset Representations for Micro-Expression Recognition](https://mlsanity.com/paper/2310.04664/) (2023)
- [FacialFlowNet: Advancing Facial Optical Flow Estimation with a Diverse Dataset and a Decomposed Model](https://mlsanity.com/paper/2409.05396/) (2024)
- [Learning-based Axial Video Motion Magnification](https://mlsanity.com/paper/2312.09551/) (2023)
- [MER-CLIP: AU-Guided Vision-Language Alignment for Micro-Expression Recognition](https://mlsanity.com/paper/2505.05937/) (2025)
- [MPFNet: A Multi-Prior Fusion Network with a Progressive Training Strategy for Micro-Expression Recognition](https://mlsanity.com/paper/2506.09735/) (2025)
- [Evaluating and Correcting Human Annotation Bias in Dynamic Micro-Expression Recognition](https://mlsanity.com/paper/2603.04766/) (2026)

## Abstract (arXiv)

Micro-expression recognition (MER) is challenging due to subtle facial movements, limited data, and the ambiguous relationship between Action Units (AUs) and emotion categories. Optical flow and motion magnification are two widely used representations for making subtle facial dynamics observable. However, many existing methods treat them as separate cues or fuse them without explicitly modeling their dual complementarity. Optical flow encodes displacement-level muscle motion, whereas motion magnification reveals appearance-level changes in facial texture and context. When both modalities are informative, their combination provides a more complete characterization of subtle facial dynamics; when one modality degrades, the other may still preserve discriminative evidence for compensation. This dual complementarity provides richer facial representations, but also introduces two key challenges for multimodal fusion: cross-modal heterogeneity and spatially varying modality reliability. To address these challenges, we propose SAC2-Net, a Semantic Anchoring and Complementary-Consensus Network that first aligns heterogeneous visual representations with semantic anchors and then performs reliability-aware complementary fusion. Specifically, Semantic Anchoring Soft Alignment (SASA) converts activated AUs into textual prompts and uses hierarchical AU-aware soft labels to align motion-magnified and optical-flow representations while preserving semantic proximity among anatomically related samples. Based on the aligned representations, Complementary-Consensus Fusion (CCF) exchanges complementary motion and appearance cues, adaptively enhances unreliable local responses with trustworthy cross-modal evidence, and further encourages a shared spatial focus through consensus refinement.