DEFT-LLM: Disentangled Expert Feature Tuning for Micro-Expression Recognition

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Ren, Li, Huilai, qi, Chao, Xu, Guoliang, Zhou, Tianyu, wei, Wei, Yin, Jianqin
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908652787466240
author Zhang, Ren
Li, Huilai
qi, Chao
Xu, Guoliang
Zhou, Tianyu
wei, Wei
Yin, Jianqin
author_facet Zhang, Ren
Li, Huilai
qi, Chao
Xu, Guoliang
Zhou, Tianyu
wei, Wei
Yin, Jianqin
contents Micro expression recognition (MER) is crucial for inferring genuine emotion. Applying a multimodal large language model (MLLM) to this task enables spatio-temporal analysis of facial motion and provides interpretable descriptions. However, there are still two core challenges: (1) The entanglement of static appearance and dynamic motion cues prevents the model from focusing on subtle motion; (2) Textual labels in existing MER datasets do not fully correspond to underlying facial muscle movements, creating a semantic gap between text supervision and physical motion. To address these issues, we propose DEFT-LLM, which achieves motion semantic alignment by multi-expert disentanglement. We first introduce Uni-MER, a motion-driven instruction dataset designed to align text with local facial motion. Its construction leverages dual constraints from optical flow and Action Unit (AU) labels to ensure spatio-temporal consistency and reasonable correspondence to the movements. We then design an architecture with three experts to decouple facial dynamics into independent and interpretable representations (structure, dynamic textures, and motion-semantics). By integrating the instruction-aligned knowledge from Uni-MER into DEFT-LLM, our method injects effective physical priors for micro expressions while also leveraging the cross modal reasoning ability of large language models, thus enabling precise capture of subtle emotional cues. Experiments on multiple challenging MER benchmarks demonstrate state-of-the-art performance, as well as a particular advantage in interpretable modeling of local facial motion.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10948
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DEFT-LLM: Disentangled Expert Feature Tuning for Micro-Expression Recognition
Zhang, Ren
Li, Huilai
qi, Chao
Xu, Guoliang
Zhou, Tianyu
wei, Wei
Yin, Jianqin
Computer Vision and Pattern Recognition
Human-Computer Interaction
Micro expression recognition (MER) is crucial for inferring genuine emotion. Applying a multimodal large language model (MLLM) to this task enables spatio-temporal analysis of facial motion and provides interpretable descriptions. However, there are still two core challenges: (1) The entanglement of static appearance and dynamic motion cues prevents the model from focusing on subtle motion; (2) Textual labels in existing MER datasets do not fully correspond to underlying facial muscle movements, creating a semantic gap between text supervision and physical motion. To address these issues, we propose DEFT-LLM, which achieves motion semantic alignment by multi-expert disentanglement. We first introduce Uni-MER, a motion-driven instruction dataset designed to align text with local facial motion. Its construction leverages dual constraints from optical flow and Action Unit (AU) labels to ensure spatio-temporal consistency and reasonable correspondence to the movements. We then design an architecture with three experts to decouple facial dynamics into independent and interpretable representations (structure, dynamic textures, and motion-semantics). By integrating the instruction-aligned knowledge from Uni-MER into DEFT-LLM, our method injects effective physical priors for micro expressions while also leveraging the cross modal reasoning ability of large language models, thus enabling precise capture of subtle emotional cues. Experiments on multiple challenging MER benchmarks demonstrate state-of-the-art performance, as well as a particular advantage in interpretable modeling of local facial motion.
title DEFT-LLM: Disentangled Expert Feature Tuning for Micro-Expression Recognition
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2511.10948