# Norface: Improving Facial Expression Analysis by Identity Normalization

arXiv: https://arxiv.org/abs/2407.15617 · HTML: https://mlsanity.com/paper/2407.15617/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 104 references that are in the map.
- First posted on arXiv 22 Jul 2024.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [Geometric GAN](https://mlsanity.com/paper/1705.02894/) (2017)
- [High-Resolution Representations for Labeling Pixels and Regions](https://mlsanity.com/paper/1904.04514/) (2019)
- [Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts](https://mlsanity.com/paper/2206.02770/) (2022)
- [Latent Image Animator: Learning to Animate Images via Latent Space Navigation](https://mlsanity.com/paper/2203.09043/) (2022)
- [Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Framework](https://mlsanity.com/paper/2103.15792/) (2021)
- [FastMoE: A Fast Mixture-of-Expert Training System](https://mlsanity.com/paper/2103.13262/) (2021)
- [Implicit Warping for Animation with Image Sets](https://mlsanity.com/paper/2210.01794/) (2022)
- [Prior Aided Streaming Network for Multi-task Affective Recognitionat the 2nd ABAW2 Competition](https://mlsanity.com/paper/2107.03708/) (2021)
- [Optimal Transport-based Identity Matching for Identity-invariant Facial Expression Recognition](https://mlsanity.com/paper/2209.12172/) (2022)
- [GaFET: Learning Geometry-aware Facial Expression Translation from In-The-Wild Images](https://mlsanity.com/paper/2308.03413/) (2023)

## Built on by (most cited first, 10 of 10)

- [BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Digital Behavioural Change](https://mlsanity.com/paper/2505.19328/) (2025)
- [OpenFace 3.0: A Lightweight Multitask System for Comprehensive Facial Behavior Analysis](https://mlsanity.com/paper/2506.02891/) (2025)
- [Multimodal Prompt Alignment for Facial Expression Recognition](https://mlsanity.com/paper/2506.21017/) (2025)
- [Complementarity-Supervised Spectral-Band Routing for Multimodal Emotion Recognition](https://mlsanity.com/paper/2603.13340/) (2026)
- [Nuanced Emotion Recognition Based on a Segment-based MLLM Framework Leveraging Qwen3-Omni for AH Detection](https://mlsanity.com/paper/2603.13406/) (2026)
- [Multimodal Ambivalence/Hesitancy Recognition in Videos for Personalized Digital Health Interventions](https://mlsanity.com/paper/2604.11730/) (2026)
- [X2C: A Large-Scale Benchmark for Nuanced Humanoid Facial Expression Imitation](https://mlsanity.com/paper/2505.11146/) (2025)
- [Discrete Facial Encoding: : A Framework for Data-driven Facial Display Discovery](https://mlsanity.com/paper/2510.01662/) (2025)
- [ExpressNet-MoE: A Hybrid Deep Neural Network for Emotion Recognition](https://mlsanity.com/paper/2510.13493/) (2025)
- [On Applicability of Synthetic Datasets for Facial Expression Recognition](https://mlsanity.com/paper/2605.17483/) (2026)

## Abstract (arXiv)

Facial Expression Analysis remains a challenging task due to unexpected task-irrelevant noise, such as identity, head pose, and background. To address this issue, this paper proposes a novel framework, called Norface, that is unified for both Action Unit (AU) analysis and Facial Emotion Recognition (FER) tasks. Norface consists of a normalization network and a classification network. First, the carefully designed normalization network struggles to directly remove the above task-irrelevant noise, by maintaining facial expression consistency but normalizing all original images to a common identity with consistent pose, and background. Then, these additional normalized images are fed into the classification network. Due to consistent identity and other factors (e.g. head pose, background, etc.), the normalized images enable the classification network to extract useful expression information more effectively. Additionally, the classification network incorporates a Mixture of Experts to refine the latent representation, including handling the input of facial representations and the output of multiple (AU or emotion) labels. Extensive experiments validate the carefully designed framework with the insight of identity normalization. The proposed method outperforms existing SOTA methods in multiple facial expression analysis tasks, including AU detection, AU intensity estimation, and FER tasks, as well as their cross-dataset tasks. For the normalized datasets and code please visit {https://norface-fea.github.io/}.