# Dual-View Optical Flow for 4D Micro-Expression Recognition - A Multi-Stream Fusion Attention Approach

arXiv: https://arxiv.org/abs/2603.26849 · HTML: https://mlsanity.com/paper/2603.26849/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## Builds on (most cited first, 7 of 7)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [Deep Learning for Micro-expression Recognition: A Survey](https://mlsanity.com/paper/2107.02823/) (2021)
- [Spatiotemporal Recurrent Convolutional Networks for Recognizing Spontaneous Micro-expressions](https://mlsanity.com/paper/1901.04656/) (2019)
- [Improving Micro-Expression Recognition with Phase-Aware Temporal Augmentation](https://mlsanity.com/paper/2510.15466/) (2025)

## Abstract (arXiv)

Micro-expression recognition is vital for affective computing but remains challenging due to the extremely brief, low-intensity facial motions involved and the high-dimensional nature of 4D mesh data. To address these challenges, we introduce a dual-view optical flow approach that simplifies mesh processing by capturing each micro-expression sequence from two synchronized viewpoints and computing optical flow to represent motion. Our pipeline begins with view separation and sequence-wise face cropping to ensure spatial consistency, followed by automatic apex-frame detection based on peak motion intensity in both views. We decompose each sequence into onset-apex and apex-offset phases, extracting horizontal, vertical, and magnitude flow channels for each phase. These are fed into our Triple-Stream MicroAttNet, which employs a fusion attention module to adaptively weight modality-specific features and a squeeze-and-excitation block to enhance magnitude representations. Training uses focal loss to mitigate class imbalance and the Adam optimizer with early stopping. Evaluated on the multi-label 4DME dataset, comprising 24 subjects and five emotion categories, in the 4DMR IJCAI Workshop Challenge 2025, our method achieves a macro-UF1 score of 0.536, outperforming the official baseline by over 50% and securing first place. Ablation studies confirm that both the fusion attention and SE components each contribute up to 3.6 points of UF1 gain. These results demonstrate that dual-view, phase-aware optical flow combined with multi-stream fusion yields a robust and interpretable solution for 4D micro-expression recognition.