MPT: Motion Prompt Tuning for Micro-Expression Recognition

2025/08/13 by Liu, Jiateng, Shi, Hengcan, Chen, Feng +4
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #I.2.8

paper · doi:10.48550/arxiv.2508.09446

Abstract

Micro-expression recognition (MER) is crucial in the affective computing field due to its wide application in medical diagnosis, lie detection, and criminal investigation. Despite its significance, obtaining micro-expression (ME) annotations is challenging due to the expertise required from psychological professionals. Consequently, ME datasets often suffer from a scarcity of training samples, severely constraining the learning of MER models. While current large pre-training models (LMs) offer general and discriminative representations, their direct application to MER is hindered by an inability to capture transitory and subtle facial movements-essential elements for effective MER. This paper introduces Motion Prompt Tuning (MPT) as a novel approach to adapting LMs for MER, representing a pioneering method for subtle motion prompt tuning. Particularly, we introduce motion prompt generation, including motion magnification and Gaussian tokenization, to extract subtle motions as prompts for LMs. Additionally, a group adapter is carefully designed and inserted into the LM to enhance it in the target MER domain, facilitating a more nuanced distinction of ME representation. Furthermore, extensive experiments conducted on three widely used MER datasets demonstrate that our proposed MPT consistently surpasses state-of-the-art approaches and verifies its effectiveness.

Citations

• Learning to Rank Onset-Occurring-Offset Representations for Micro-Expression Recognition
• Feature Representation Learning with Adaptive Displacement Generation and Transformer Fusion for Micro-Expression Recognition
• Micron-BERT: BERT-based Facial Micro-Expression Recognition
• Efficient Neural Architecture Search for Emotion Recognition
• Visual Prompt Multi-Modal Tracking
• AIM: Adapting Image Models for Efficient Video Action Recognition
• MaPLe: Multi-modal Prompt Learning
• ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning
• Vision Transformer Adapter for Dense Predictions
• Transformer Scale Gate for Semantic Segmentation
• Visual Prompt Tuning
• ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues
• VL-Adapter: Parameter-Efficient Transfer Learning for\n Vision-and-Language Tasks
• Seeking Salient Facial Regions for Cross-Database Micro-Expression Recognition
• Benchmarking Detection Transfer Learning with Vision Transformers
• CLIP-Adapter: Better Vision-Language Models with Feature Adapters
• CLIP-Adapter: Better Vision-Language Models with Feature Adapters
• Learning Transferable Visual Models From Natural Language Supervision
• Feature refinement: An expression-specific feature learning and fusion method for micro-expression recognition
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• End-to-End Object Detection with Transformers
• Parameter-Efficient Transfer Learning for NLP
• OFF-ApexNet on Micro-expression Recognition System
• Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
• Gaussian Error Linear Units (GELUs)
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• ImageNet Large Scale Visual Recognition Challenge
• ImageNet Large Scale Visual Recognition Challenge
• ImageNet classification with deep convolutional neural networks
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• Micro-Expression Recognition by Motion Feature Extraction based on Pre-training
• DEFT-LLM: Disentangled Expert Feature Tuning for Micro-Expression Recognition
• Deep Learning for Micro-expression Recognition: A Survey
• Improving Micro-Expression Recognition with Phase-Aware Temporal Augmentation
• Meta-Auxiliary Learning for Micro-Expression Recognition