EPIR: An Efficient Patch Tokenization, Integration and Representation Framework for Micro-expression Recognition
2026-04-09 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new method called EPIR to better recognize tiny facial expressions that show true emotions, called micro-expressions. Their approach reduces the heavy computing power needed by previous Transformer models by grouping and selecting important image parts (tokens) more efficiently. They tested their method on four well-known datasets and found it works better than current advanced methods. This means EPIR can accurately understand subtle facial emotions while using less computation.
Micro-expression recognitionTransformer modelsTokenizationSelf-attentionDual norm shifted tokenizationToken integrationDynamic token selectionDeep learningFacial emotion analysisPublic datasets
Authors
Junbo Wang, Liangyu Fu, Yuke Li, Yining Zhu, Xuecheng Wu, Kun Hu
Abstract
Micro-expression recognition can obtain the real emotion of the individual at the current moment. Although deep learning-based methods, especially Transformer-based methods, have achieved impressive results, these methods have high computational complexity due to the large number of tokens in the multi-head self-attention. In addition, the existing micro-expression datasets are small-scale, which makes it difficult for Transformer-based models to learn effective micro-expression representations. Therefore, we propose a novel Efficient Patch tokenization, Integration and Representation framework (EPIR), which can balance high recognition performance and low computational complexity. Specifically, we first propose a dual norm shifted tokenization (DNSPT) module to learn the spatial relationship between neighboring pixels in the face region, which is implemented by a refined spatial transformation and dual norm projection. Then, we propose a token integration module to integrate partial tokens among multiple cascaded Transformer blocks, thereby reducing the number of tokens without information loss. Furthermore, we design a discriminative token extractor, which first improves the attention in the Transformer block to reduce the unnecessary focus of the attention calculation on self-tokens, and uses the dynamic token selection module (DTSM) to select key tokens, thereby capturing more discriminative micro-expression representations. We conduct extensive experiments on four popular public datasets (i.e., CASME II, SAMM, SMIC, and CAS(ME)3. The experimental results show that our method achieves significant performance gains over the state-of-the-art methods, such as 9.6% improvement on the CAS(ME)$^3$ dataset in terms of UF1 and 4.58% improvement on the SMIC dataset in terms of UAR metric.