# FMANet: A Novel Dual-Phase Optical Flow Approach with Fusion Motion Attention Network for Robust Micro-expression Recognition

arXiv: https://arxiv.org/abs/2510.07810 · HTML: https://mlsanity.com/paper/2510.07810/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 58 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Builds on (most cited first, 17 of 17)

- [Video-based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms](https://mlsanity.com/paper/2201.12728/) (2022)
- [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)
- [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)
- [Spatiotemporal Recurrent Convolutional Networks for Recognizing Spontaneous Micro-expressions](https://mlsanity.com/paper/1901.04656/) (2019)
- [Feature Representation Learning with Adaptive Displacement Generation and Transformer Fusion for Micro-Expression Recognition](https://mlsanity.com/paper/2304.04420/) (2023)
- [An Overview of Facial Micro-Expression Analysis: Data, Methodology and Challenge](https://mlsanity.com/paper/2012.11307/) (2020)
- [Micro-Attention for Micro-Expression recognition](https://mlsanity.com/paper/1811.02360/) (2018)
- [MOL: Joint Estimation of Micro-Expression, Optical Flow, and Landmark via Transformer-Graph-Style Convolution](https://mlsanity.com/paper/2506.14511/) (2025)
- [MERANet: Facial Micro-Expression Recognition using 3D Residual Attention Network](https://mlsanity.com/paper/2012.04581/) (2020)
- [MPFNet: A Multi-Prior Fusion Network with a Progressive Training Strategy for Micro-Expression Recognition](https://mlsanity.com/paper/2506.09735/) (2025)
- [A Multi-stream Convolutional Neural Network for Micro-expression Recognition Using Optical Flow and EVM](https://mlsanity.com/paper/2011.03756/) (2020)
- [MELLM: A Flow-Guided Large Language Model for Micro-Expression Understanding](https://mlsanity.com/paper/2505.07007/) (2025)
- [Transferring Dual Stochastic Graph Convolutional Network for Facial Micro-expression Recognition](https://mlsanity.com/paper/2203.05208/) (2022)
- [MERba: Multi-Receptive Field MambaVision for Micro-Expression Recognition](https://mlsanity.com/paper/2506.14468/) (2025)
- [Apex-Centered Spatio-Temporal Rank Pooling and Gradient Attention for Micro-Expression Recognition](https://mlsanity.com/paper/2509.00056/) (2025)

## Abstract (arXiv)

Facial micro-expressions, characterized by their subtle and brief nature, are valuable indicators of genuine emotions. Despite their significance in psychology, security, and behavioral analysis, micro-expression recognition remains challenging due to the difficulty of capturing subtle facial movements. Optical flow has been widely employed as an input modality for this task due to its effectiveness. However, most existing methods compute optical flow only between the onset and apex frames, thereby overlooking essential motion information in the apex-to-offset phase. To address this limitation, we first introduce a comprehensive motion representation, termed Magnitude-Modulated Combined Optical Flow (MM-COF), which integrates motion dynamics from both micro-expression phases into a unified descriptor suitable for direct use in recognition networks. Building upon this principle, we then propose FMANet, a novel end-to-end neural network architecture that internalizes the dual-phase analysis and magnitude modulation into learnable modules. This allows the network to adaptively fuse motion cues and focus on salient facial regions for classification. Experimental evaluations on the MMEW, SMIC, CASME-II, and SAMM datasets, widely recognized as standard benchmarks, demonstrate that our proposed MM-COF representation and FMANet outperforms existing methods, underscoring the potential of a learnable, dual-phase framework in advancing micro-expression recognition.