Sparse Attention to Emotion: Efficient Facial Emotion Recognition via Token Reduction

• URL: http://arxiv.org/abs/2608.08873v1
• Date: Sun, 09 Aug 2026 19:28:27 GMT
• Title: Sparse Attention to Emotion: Efficient Facial Emotion Recognition via Token Reduction
• Abstract summary: Facial Emotion Recognition (FER) is an important task that has significant implications across various fields such as biometrics, health, and human-computer interaction.<n>Current Vision Transformer-based approaches display quadratic complexity $mathcalO(N2)$, with N being the input sequence length.<n>We propose Sparse Attention to Emotion (SAE), a model that discards image tokens that have no added value to the emotional context.
• Score: 1.0266286487433587
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Facial Emotion Recognition (FER) is an important task that has significant implications across various fields such as biometrics, health, and human-computer interaction. Current Vision Transformer-based approaches display quadratic complexity $\mathcal{O}(N^2)$, with N being the input sequence length, making them cumbersome to deploy at the edge. In this paper, we hypothesize that the FER task does not necessarily require all facial information to correctly interpret emotional states, as specific regions such as the eyes, the mouth, and parts of the cheeks carry discriminative information that can be sufficient to recognize emotions. Based on this, we propose Sparse Attention to Emotion (SAE), a model that discards image tokens that have no added value to the emotional context, while preserving good accuracy and achieving a significant gain in computational cost. Surprisingly, even after suppressing 90\% of the image tokens, our model achieves competitive accuracy to state of the art methods at much lower cost, providing a lightweight Facial Emotion Recognition approach. Experimental results demonstrate that SAE achieves new state of the art results on the RAF-DB dataset while reducing the computational complexity by up to 90\%.

Related papers

• Smile on the Face, Sadness in the Eyes: Bridging the Emotion Gap with a Multimodal Dataset of Eye and Facial Behaviors [49.833812625518554]
  We introduce eye behaviors as an important emotional cue and construct an Eye-behavior-aided Multimodal Emotion Recognition dataset.<n>In the experiment, we introduce seven multimodal benchmark protocols for a variety of comprehensive evaluations of the EMER dataset.<n>The results show that the EMERT outperforms other state-of-the-art multimodal methods by a great margin, revealing the importance of modeling eye behaviors for robust ER.
  arXiv  Detail & Related papers  (2025-12-18T12:52:55Z)
• Smile upon the Face but Sadness in the Eyes: Emotion Recognition based on Facial Expressions and Eye Behaviors [63.194053817609024]
  We introduce eye behaviors as an important emotional cues for the creation of a new Eye-behavior-aided Multimodal Emotion Recognition dataset. For the first time, we provide annotations for both Emotion Recognition (ER) and Facial Expression Recognition (FER) in the EMER dataset. We specifically design a new EMERT architecture to concurrently enhance performance in both ER and FER.
  arXiv  Detail & Related papers  (2024-11-08T04:53:55Z)
• Facial Expression Recognition using Squeeze and Excitation-powered Swin Transformers [0.0]
  We propose a framework that employs Swin Vision Transformers (SwinT) and squeeze and excitation block (SE) to address vision tasks. Our focus was to create an efficient FER model based on SwinT architecture that can recognize facial emotions using minimal data. We trained our model on a hybrid dataset and evaluated its performance on the AffectNet dataset, achieving an F1-score of 0.5420.
  arXiv  Detail & Related papers  (2023-01-26T02:29:17Z)
• Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers [57.1091606948826]
  We propose a novel FER model, named Poker Face Vision Transformer or PF-ViT, to address these challenges. PF-ViT aims to separate and recognize the disturbance-agnostic emotion from a static facial image via generating its corresponding poker face. PF-ViT utilizes vanilla Vision Transformers, and its components are pre-trained as Masked Autoencoders on a large facial expression dataset.
  arXiv  Detail & Related papers  (2022-07-22T13:39:06Z)
• Facial Emotion Recognition: A multi-task approach using deep learning [0.0]
  We propose a multi-task learning algorithm, in which a single CNN detects gender, age and race of the subject along with their emotion. Results show that this approach is significantly better than the current State of the art algorithms for this task.
  arXiv  Detail & Related papers  (2021-10-28T11:23:00Z)
• Interpretable Image Emotion Recognition: A Domain Adaptation Approach Using Facial Expressions [11.808447247077902]
  This paper proposes a feature-based domain adaptation technique for identifying emotions in generic images.<n>It addresses the challenge of the limited availability of pre-trained models and well-annotated datasets for Image Emotion Recognition (IER)<n>The proposed IER system demonstrated emotion classification accuracies of 61.86% for the IAPSa dataset, 62.47 for the ArtPhoto dataset, 70.78% for the FI dataset, and 59.72% for the EMOTIC dataset.
  arXiv  Detail & Related papers  (2020-11-17T02:55:16Z)
• Learning Emotional-Blinded Face Representations [77.7653702071127]
  We propose two face representations that are blind to facial expressions associated to emotional responses. This work is motivated by new international regulations for personal data protection.
  arXiv  Detail & Related papers  (2020-09-18T09:24:10Z)
• Continuous Emotion Recognition via Deep Convolutional Autoencoder and Support Vector Regressor [70.2226417364135]
  It is crucial that the machine should be able to recognize the emotional state of the user with high accuracy. Deep neural networks have been used with great success in recognizing emotions. We present a new model for continuous emotion recognition based on facial expression recognition.
  arXiv  Detail & Related papers  (2020-01-31T17:47:16Z)
• Learning to Augment Expressions for Few-shot Fine-grained Facial Expression Recognition [98.83578105374535]
  We present a novel Fine-grained Facial Expression Database - F2ED. It includes more than 200k images with 54 facial expressions from 119 persons. Considering the phenomenon of uneven data distribution and lack of samples is common in real-world scenarios, we evaluate several tasks of few-shot expression learning. We propose a unified task-driven framework - Compositional Generative Adversarial Network (Comp-GAN) learning to synthesize facial images.
  arXiv  Detail & Related papers  (2020-01-17T03:26:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.