mlsanityData to 14 Oct 2026

Shape Preserving Facial Landmarks with Graph Attention Networks

arXiv 2210.07233 ↗First posted 13 Oct 2022cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Top-performing landmark estimation algorithms are based on exploiting the excellent ability of large convolutional neural networks (CNNs) to represent local appearance. However, it is well known that they can only learn weak spatial relationships. To address this problem, we propose a model based on the combination of a CNN with a cascade of Graph Attention Network regressors. To this end, we introduce an encoding that jointly represents the appearance and location of facial landmarks and an attention mechanism to weigh the information according to its reliability. This is combined with a multi-task approach to initialize the location of graph nodes and a coarse-to-fine landmark description scheme. Our experiments confirm that the proposed model learns a global representation of the structure of the face, achieving top performance in popular benchmarks on head pose and landmark estimation. The improvement provided by our model is most significant in situations involving large changes in the local appearance of landmarks.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 27 of its 45 references that are in the map. First posted on arXiv 13 Oct 2022.

Builds on

27 of 45 references.

References · 27

  1. 2017Graph Attention Networkscited by 8,923
  2. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  3. 2015Spatial Transformer Networkscited by 1,429
  4. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  5. 2017A simple neural network module for relational reasoningcited by 346
  6. 2021Fake It Till You Make It: Face analysis in the wild using synthetic data alonecited by 200
  7. 2018Look at Boundary: A Boundary-Aware Face Alignment Algorithmcited by 138
  8. 2019Adaptive Wing Loss for Robust Face Alignment via Heatmap Regressioncited by 128
  9. 2017Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networkscited by 109
  10. 2020LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihoodcited by 87
  11. 2018Style Aggregated Network for Facial Landmark Detectioncited by 60
  12. 2020Structured Landmark Detection via Topology-Adapting Deep Graph Learningcited by 50
15 more
  1. 2022Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learningcited by 47
  2. 2019DeCaFA: Deep Convolutional Cascade for Face Alignment In The Wildcited by 46
  3. 2017Deep Alignment Network: A convolutional neural network for robust face alignmentcited by 44
  4. 2021ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignmentcited by 34
  5. 2019Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Translationcited by 33
  6. 2022Towards Accurate Facial Landmark Detection via Cascaded Transformerscited by 31
  7. 2022Multi-task head pose estimation in-the-wildcited by 23
  8. 2018Disentangling 3D Pose in A Dendritic CNN for Unconstrained 2D Face Alignmentcited by 18
  9. 2016Structured Feature Learning for Pose Estimationcited by 17
  10. 2020Keypoint-Aligned Embeddings for Image Retrieval and Re-identificationcited by 15
  11. 2015Recombinator Networks: Learning Coarse-to-Fine Feature Aggregationcited by 10
  12. 2020PropagationNet: Propagate Points to Curve to Learn Structure Informationcited by 10
  13. 2021ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimationcited by 10
  14. 2019Face Alignment using a 3D Deeply-initialized Ensemble of Regression Treescited by 8
  15. 2015Face Alignment Assisted by Head Pose Estimationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 8; 2025: 9; 2026: 3.

23 papers.

Sort:

By area:

  1. 2024Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Modelcited by 45
  2. 20243D Face Tracking from 2D Video through Iterative Dense UV to Image Flowcited by 20
  3. 2024Generalizable Face Landmarking Guided by Conditional Face Warpingcited by 6
  4. 2024Cascaded Dual Vision Transformer for Accurate Facial Landmark Detectioncited by 5
  5. 2025OpenFace 3.0: A Lightweight Multitask System for Comprehensive Facial Behavior Analysiscited by 5
  6. 2023Automated Detection of Cat Facial Landmarkscited by 3
  7. 2023Measuring Student Behavioral Engagement using Histogram of Actionscited by 2
  8. 2024Evaluating Driver Readiness in Conditionally Automated Vehicles from Eye-Tracking Data and Head Posecited by 2
  9. 2025Graph-Attention Network with Adversarial Domain Alignment for Robust Cross-Domain Facial Expression Recognitioncited by 2
  10. 2025BLANKET: Anonymizing Faces in Infant Video Recordingscited by 2
  11. 2024Authentic Emotion Mapping: Benchmarking Facial Expressions in Real Newscited by 1
  12. 2025Mitigating Knowledge Discrepancies among Multiple Datasets for Task-agnostic Unified Face Alignmentcited by 1
11 more
  1. 20233D Face Alignment Through Fusion of Head Pose Information and Featurescited by 0
  2. 2024Towards Geometric-Photometric Joint Alignment for Facial Mesh Registrationcited by 0
  3. 2024UP-FacE: User-predictable Fine-grained Face Shape Editingcited by 0
  4. 2025Kinship Verification through a Forest Neural Networkcited by 0
  5. 2025Assessing the Use of Face Swapping Methods as Face Anonymizers in Videoscited by 0
  6. 2025Bridging the gap in FER: addressing age bias in deep learningcited by 0
  7. 2025Beyond Flicker: Detecting Kinematic Inconsistencies for Generalizable Deepfake Video Detectioncited by 0
  8. 2025Detection of Intoxicated Individuals from Facial Video Sequences via a Recurrent Fusion Modelcited by 0
  9. 2026DFIC: Towards a balanced facial image dataset for automatic ICAO compliance verificationcited by 0
  10. 2026Generalized Disguise Makeup Presentation Attack Detection Using an Attention-Guided Patch-Based Frameworkcited by 0
  11. 2026NeoLoc-68: End-to-end 68-point neonatal facial landmark localisation in neonatal clinical environmentscited by 0