mlsanityData to 7 Oct 2026

LwPosr: Lightweight Efficient Fine-Grained Head Pose Estimation

arXiv 2202.03544 ↗First posted 7 Feb 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

This paper presents a lightweight network for head pose estimation (HPE) task. While previous approaches rely on convolutional neural networks, the proposed network textitLwPosr uses mixture of depthwise separable convolutional (DSC) and transformer encoder layers which are structured in two streams and three stages to provide fine-grained regression for predicting head poses. The quantitative and qualitative demonstration is provided to show that the proposed network is able to learn head poses efficiently while using less parameter space. Extensive ablations are conducted using three open-source datasets namely 300W-LP, AFLW2000, and BIWI datasets. To our knowledge, (1) textitLwPosr is the lightest network proposed for estimating head poses compared to both keypoints-based and keypoints-free approaches; (2) it sets a benchmark for both overperforming the previous lightweight network on mean absolute error and on reducing number of parameters; (3) it is first of its kind to use mixture of DSCs and transformer encoders for HPE. This approach is suitable for mobile devices which require lightweight networks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 33 of its 59 references that are in the map. First posted on arXiv 7 Feb 2022.

Builds on

33 of 59 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2016Layer Normalizationcited by 5,579
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  7. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  8. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  9. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  10. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  11. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  12. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
21 more
  1. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
  2. 2020Pre-Trained Image Processing Transformercited by 891
  3. 2018Image Transformercited by 770
  4. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 524
  5. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  6. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  7. 2020MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformerscited by 355
  8. 2020Learning Texture Transformer Network for Image Super-Resolutioncited by 346
  9. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  10. 2017Fine-Grained Head Pose Estimation Without Keypointscited by 163
  11. 2018Face Alignment in Full Pose Range: A 3D Total Solutioncited by 147
  12. 2020HOPE-Net: A Graph-based Model for Hand-Object Pose Estimationcited by 112
  13. 2016HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognitioncited by 103
  14. 2020WHENet: Real-time Fine-Grained Estimation for Wide Range Head Posecited by 47
  15. 2016An All-In-One Convolutional Neural Network for Face Analysiscited by 45
  16. 2020A Vector-based Representation to Enhance Head Pose Estimationcited by 34
  17. 2021End-to-End Trainable Multi-Instance Pose Estimation with Transformerscited by 30
  18. 2017FacePoseNet: Making a Case for Landmark-Free Face Alignmentcited by 21
  19. 2021Centroid Transformers: Learning to Abstract with Attentioncited by 20
  20. 2017KEPLER: Keypoint and Pose Estimation of Unconstrained Faces by Learning Efficient H-CNN Regressorscited by 10
  21. 2019Improving Head Pose Estimation with a Combined Loss and Bounding Box Margin Adjustmentcited by 8

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 2.

4 papers.

  1. 2023DirectMHP: Direct 2D Multi-Person Head Pose Estimation with Full-range Anglescited by 6
  2. 2022Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priorscited by 1
  3. 2024Latent Embedding Clustering for Occlusion Robust Head Pose Estimationcited by 0
  4. 2024CLERF: Contrastive LEaRning for Full Range Head Pose Estimationcited by 0