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

arXiv: https://arxiv.org/abs/2608.08873 · HTML: https://mlsanity.com/paper/2608.08873/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 9 Aug 2026.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [LocalViT: Analyzing Locality in Vision Transformers](https://mlsanity.com/paper/2104.05707/) (2021)
- [Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer](https://mlsanity.com/paper/2108.01390/) (2021)
- [TransFER: Learning Relation-aware Facial Expression Representations with Transformers](https://mlsanity.com/paper/2108.11116/) (2021)
- [Scalable Vision Transformers with Hierarchical Pooling](https://mlsanity.com/paper/2103.10619/) (2021)
- [Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition](https://mlsanity.com/paper/2207.10299/) (2022)
- [Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition](https://mlsanity.com/paper/2109.07270/) (2021)
- [Facial Expression Recognition with Visual Transformers and Attentional Selective Fusion](https://mlsanity.com/paper/2103.16854/) (2021)
- [Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognition](https://mlsanity.com/paper/2104.05160/) (2021)
- [POSTER: A Pyramid Cross-Fusion Transformer Network for Facial Expression Recognition](https://mlsanity.com/paper/2204.04083/) (2022)
- [Facial expression and attributes recognition based on multi-task learning of lightweight neural networks](https://mlsanity.com/paper/2103.17107/) (2021)
- [From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos](https://mlsanity.com/paper/2312.05447/) (2023)
- [Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition](https://mlsanity.com/paper/2212.05463/) (2022)
- [ARBEx: Attentive Feature Extraction with Reliability Balancing for Robust Facial Expression Learning](https://mlsanity.com/paper/2305.01486/) (2023)
- [Batch Transformer: Look for Attention in Batch](https://mlsanity.com/paper/2407.04218/) (2024)

## Abstract (arXiv)

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 O(N2), 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%.