mlsanityData to 7 Oct 2026

Multi-task head pose estimation in-the-wild

arXiv 2202.02299 ↗First posted 4 Feb 2022cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

We present a deep learning-based multi-task approach for head pose estimation in images. We contribute with a network architecture and training strategy that harness the strong dependencies among face pose, alignment and visibility, to produce a top performing model for all three tasks. Our architecture is an encoder-decoder CNN with residual blocks and lateral skip connections. We show that the combination of head pose estimation and landmark-based face alignment significantly improve the performance of the former task. Further, the location of the pose task at the bottleneck layer, at the end of the encoder, and that of tasks depending on spatial information, such as visibility and alignment, in the final decoder layer, also contribute to increase the final performance. In the experiments conducted the proposed model outperforms the state-of-the-art in the face pose and visibility tasks. By including a final landmark regression step it also produces face alignment results on par with the state-of-the-art.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 36 of its 64 references that are in the map. First posted on arXiv 4 Feb 2022.

Builds on

36 of 64 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  4. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
  5. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 524
  6. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 367
  7. 2014CNN Features off-the-shelf: an Astounding Baseline for Recognitioncited by 316
  8. 2018Characterizing and Avoiding Negative Transfercited by 226
  9. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
  10. 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
  11. 2017Fine-Grained Head Pose Estimation Without Keypointscited by 163
  12. 2018Face Alignment in Full Pose Range: A 3D Total Solutioncited by 147
24 more
  1. 2018Look at Boundary: A Boundary-Aware Face Alignment Algorithmcited by 137
  2. 2019Transferability and Hardness of Supervised Classification Taskscited by 125
  3. 2017Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networkscited by 108
  4. 2016HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognitioncited by 103
  5. 2018Unsupervised Discovery of Object Landmarks as Structural Representationscited by 73
  6. 2018Facial Landmark Detection: a Literature Surveycited by 63
  7. 2016An All-In-One Convolutional Neural Network for Face Analysiscited by 45
  8. 2018Self-supervised learning of a facial attribute embedding from videocited by 44
  9. 2017Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approachcited by 43
  10. 2019Unsupervised Learning of Landmarks by Descriptor Vector Exchangecited by 39
  11. 2014Learning Deep Representation for Face Alignment with Auxiliary Attributescited by 32
  12. 2017Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resourcescited by 23
  13. 2017FacePoseNet: Making a Case for Landmark-Free Face Alignmentcited by 21
  14. 2017Faster Than Real-time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Posescited by 19
  15. 2018Disentangling 3D Pose in A Dendritic CNN for Unconstrained 2D Face Alignmentcited by 18
  16. 2017Robust Facial Landmark Detection under Significant Head Poses and Occlusioncited by 12
  17. 2017Simultaneous Facial Landmark Detection, Pose and Deformation Estimation under Facial Occlusioncited by 12
  18. 2015Recombinator Networks: Learning Coarse-to-Fine Feature Aggregationcited by 10
  19. 2016Face Attribute Prediction Using Off-the-Shelf CNN Featurescited by 10
  20. 2019Facial Pose Estimation by Deep Learning from Label Distributionscited by 10
  21. 2016Combining Data-driven and Model-driven Methods for Robust Facial Landmark Detectioncited by 8
  22. 2019Face Alignment using a 3D Deeply-initialized Ensemble of Regression Treescited by 8
  23. 2015Face Alignment Assisted by Head Pose Estimationcited by 6
  24. 2019Joint Learning of Semantic Alignment and Object Landmark Detectioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 5; 2024: 10; 2025: 1; 2026: 2.

22 papers.

Sort:

By area:

  1. 20223D GAN Inversion with Pose Optimizationcited by 44
  2. 2023SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimationcited by 38
  3. 2024FaceXFormer: A Unified Transformer for Facial Analysiscited by 34
  4. 2022Shape Preserving Facial Landmarks with Graph Attention Networkscited by 23
  5. 2023Towards Robust and Unconstrained Full Range of Rotation Head Pose Estimationcited by 20
  6. 2024Second FRCSyn-onGoing: Winning Solutions and Post-Challenge Analysis to Improve Face Recognition with Synthetic Datacited by 13
  7. 2024On the representation and methodology for wide and short range head pose estimationcited by 11
  8. 2024Face-MLLM: A Large Face Perception Modelcited by 11
  9. 2022Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussiancited by 7
  10. 2023DirectMHP: Direct 2D Multi-Person Head Pose Estimation with Full-range Anglescited by 6
  11. 2023DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignmentcited by 6
  12. 2025FaVChat: Hierarchical Prompt-Query Guided Facial Video Understanding with Data-Efficient GRPOcited by 6
10 more
  1. 2022PedRecNet: Multi-task deep neural network for full 3D human pose and orientation estimationcited by 4
  2. 2024VGGHeads: 3D Multi Head Alignment with a Large-Scale Synthetic Datasetcited by 4
  3. 2024Semi-Supervised Unconstrained Head Pose Estimation in the Wildcited by 2
  4. 2024Rank-based No-reference Quality Assessment for Face Swappingcited by 1
  5. 2024ORFormer: Occlusion-Robust Transformer for Accurate Facial Landmark Detectioncited by 1
  6. 20233D Face Alignment Through Fusion of Head Pose Information and Featurescited by 0
  7. 2024On the power of data augmentation for head pose estimationcited by 0
  8. 2024Bidirectional Regression for Monocular 6DoF Head Pose Estimation and Reference System Alignmentcited by 0
  9. 2026Auditing Demographic Bias in Facial Landmark Detection for Fair Human-Robot Interactioncited by 0
  10. 2026VGGT-HPE: Reframing Head Pose Estimation as Relative Pose Predictioncited by 0