MELDAE: A Framework for Micro-Expression Spotting, Detection, and Automatic Evaluation in In-the-Wild Conversational Scenes
This work addresses the problem of micro-expression analysis for applications in emotion recognition, but it is incremental as it builds on existing methods with new data and optimizations.
The paper tackles the challenge of analyzing spontaneous micro-expressions in real-world conversational settings by introducing a new dataset and an end-to-end framework, achieving a 17.72% improvement in F1_{DR} localization metric over baselines.
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.