# Impact of facial landmark localization on facial expression recognition

arXiv: https://arxiv.org/abs/1905.10784 · HTML: https://mlsanity.com/paper/1905.10784/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2019.

## Built on by (most cited first, 7 of 7)

- [From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos](https://mlsanity.com/paper/2312.05447/) (2023)
- [FER-YOLO-Mamba: Facial Expression Detection and Classification Based on Selective State Space](https://mlsanity.com/paper/2405.01828/) (2024)
- [Are 3D Face Shapes Expressive Enough for Recognising Continuous Emotions and Action Unit Intensities?](https://mlsanity.com/paper/2207.01113/) (2022)
- [eMotion-GAN: A Motion-based GAN for Photorealistic and Facial Expression Preserving Frontal View Synthesis](https://mlsanity.com/paper/2404.09940/) (2024)
- [Emotion estimation from video footage with LSTM](https://mlsanity.com/paper/2501.13432/) (2025)
- [Edge-preserving Image Denoising via Multi-scale Adaptive Statistical Independence Testing](https://mlsanity.com/paper/2505.01032/) (2025)
- [Edge Detection based on Channel Attention and Inter-region Independence Test](https://mlsanity.com/paper/2505.01040/) (2025)

## Abstract (arXiv)

Although facial landmark localization (FLL) approaches are becoming increasingly accurate for characterizing facial regions, one question remains unanswered: what is the impact of these approaches on subsequent related tasks? In this paper, the focus is put on facial expression recognition (FER), where facial landmarks are used for face registration, which is a common usage. Since the most used datasets for facial landmark localization do not allow for a proper measurement of performance according to the different difficulties (e.g., pose, expression, illumination, occlusion, motion blur), we also quantify the performance of recent approaches in the presence of head pose variations and facial expressions. Finally, a study of the impact of these approaches on FER is conducted. We show that the landmark accuracy achieved so far optimizing the conventional Euclidean distance does not necessarily guarantee a gain in performance for FER. To deal with this issue, we propose a new evaluation metric for FLL adapted to FER.