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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nguyen, Luu Tu, Man, Thi Bich Phuong, Khuong, Vu Tram Anh, Le, Thanh Ha, Ngo, Thi Duyen
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918413548388352
author Nguyen, Luu Tu
Man, Thi Bich Phuong
Khuong, Vu Tram Anh
Le, Thanh Ha
Ngo, Thi Duyen
author_facet Nguyen, Luu Tu
Man, Thi Bich Phuong
Khuong, Vu Tram Anh
Le, Thanh Ha
Ngo, Thi Duyen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26849
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Dual-View Optical Flow for 4D Micro-Expression Recognition - A Multi-Stream Fusion Attention Approach
Nguyen, Luu Tu
Man, Thi Bich Phuong
Khuong, Vu Tram Anh
Le, Thanh Ha
Ngo, Thi Duyen
Computer Vision and Pattern Recognition
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.
title Dual-View Optical Flow for 4D Micro-Expression Recognition - A Multi-Stream Fusion Attention Approach
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.26849