CMED: A Child Micro-Expression Dataset

2025-03-27

AI Summary

Existing micro-expression research predominantly focuses on adults; studies involving children are severely constrained due to facial anatomical and developmental differences, limited voluntary facial control, and the absence of spontaneous micro-expression datasets for this population. To address this gap, we introduce CMED—the first spontaneous micro-expression video dataset specifically designed for children—collected remotely via video conferencing in naturalistic settings across multiple age groups. Our method integrates handcrafted features (LBP-TOP, HOG) with deep models (ResNet, ST-ResNet), enabling unified support for both micro-expression spotting and recognition. Key contributions include: (1) the first benchmark spontaneous micro-expression dataset for children; (2) a systematic characterization of critical spatiotemporal and intensity-based differences between children’s and adults’ micro-expressions; and (3) reproducible baseline performance across three representative architectures for both spotting and recognition, establishing a foundational resource for automated child micro-expression analysis.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Micro-expressions are short bursts of emotion that are difficult to hide. Their detection in children is an important cue to assist psychotherapists in conducting better therapy. However, existing research on the detection of micro-expressions has focused on adults, whose expressions differ in their characteristics from those of children. The lack of research is a direct consequence of the lack of a child-based micro-expressions dataset as it is much more challenging to capture children's facial expressions due to the lack of predictability and controllability. This study compiles a dataset of spontaneous child micro-expression videos, the first of its kind, to the best of the authors knowledge. The dataset is captured in the wild using video conferencing software. This dataset enables us to then explore key features and differences between adult and child micro-expressions. This study also establishes a baseline for the automated spotting and recognition of micro-expressions in children using three approaches comprising of hand-created and learning-based approaches.

Problem

• Lack of child micro-expression dataset hinders research
• Child and adult micro-expressions differ significantly
• Automated detection for child micro-expressions needs baseline

Innovation

• First child micro-expression dataset compiled
• Captured via video conferencing software
• Combines hand-created and learning-based approaches