Saved in:
Bibliographic Details
Main Authors: Feng, Yigui, Wang, Qinglin, Liu, Yang, Liu, Ke, Mo, Haotian, Huang, Enhao, Liu, Gencheng, Liu, Mingzhe, Liu, Jie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.22575
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912670743003136
author Feng, Yigui
Wang, Qinglin
Liu, Yang
Liu, Ke
Mo, Haotian
Huang, Enhao
Liu, Gencheng
Liu, Mingzhe
Liu, Jie
author_facet Feng, Yigui
Wang, Qinglin
Liu, Yang
Liu, Ke
Mo, Haotian
Huang, Enhao
Liu, Gencheng
Liu, Mingzhe
Liu, Jie
contents Accurately analyzing spontaneous, unconscious micro-expressions is crucial for revealing true human emotions, but this task remains challenging in wild scenarios, such as natural conversation. Existing research largely relies on datasets from controlled laboratory environments, and their performance degrades dramatically in the real world. To address this issue, we propose three contributions: the first micro-expression dataset focused on conversational-in-the-wild scenarios; an end-to-end localization and detection framework, MELDAE; and a novel boundary-aware loss function that improves temporal accuracy by penalizing onset and offset errors. Extensive experiments demonstrate that our framework achieves state-of-the-art results on the WDMD dataset, improving the key F1_{DR} localization metric by 17.72% over the strongest baseline, while also demonstrating excellent generalization capabilities on existing benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22575
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MELDAE: A Framework for Micro-Expression Spotting, Detection, and Automatic Evaluation in In-the-Wild Conversational Scenes
Feng, Yigui
Wang, Qinglin
Liu, Yang
Liu, Ke
Mo, Haotian
Huang, Enhao
Liu, Gencheng
Liu, Mingzhe
Liu, Jie
Computer Vision and Pattern Recognition
Accurately analyzing spontaneous, unconscious micro-expressions is crucial for revealing true human emotions, but this task remains challenging in wild scenarios, such as natural conversation. Existing research largely relies on datasets from controlled laboratory environments, and their performance degrades dramatically in the real world. To address this issue, we propose three contributions: the first micro-expression dataset focused on conversational-in-the-wild scenarios; an end-to-end localization and detection framework, MELDAE; and a novel boundary-aware loss function that improves temporal accuracy by penalizing onset and offset errors. Extensive experiments demonstrate that our framework achieves state-of-the-art results on the WDMD dataset, improving the key F1_{DR} localization metric by 17.72% over the strongest baseline, while also demonstrating excellent generalization capabilities on existing benchmarks.
title MELDAE: A Framework for Micro-Expression Spotting, Detection, and Automatic Evaluation in In-the-Wild Conversational Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.22575