mlsanityData to 7 Oct 2026

Test-Time Personalization with a Transformer for Human Pose Estimation

arXiv 2107.02133 ↗First posted 5 Jul 2021cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

We propose to personalize a human pose estimator given a set of test images of a person without using any manual annotations. While there is a significant advancement in human pose estimation, it is still very challenging for a model to generalize to different unknown environments and unseen persons. Instead of using a fixed model for every test case, we adapt our pose estimator during test time to exploit person-specific information. We first train our model on diverse data with both a supervised and a self-supervised pose estimation objectives jointly. We use a Transformer model to build a transformation between the self-supervised keypoints and the supervised keypoints. During test time, we personalize and adapt our model by fine-tuning with the self-supervised objective. The pose is then improved by transforming the updated self-supervised keypoints. We experiment with multiple datasets and show significant improvements on pose estimations with our self-supervised personalization.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 62 of its 74 references that are in the map. First posted on arXiv 5 Jul 2021.

Builds on

62 of 74 references.

References · 62

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2017Mask R-CNNcited by 7,259
  7. 2016Layer Normalizationcited by 5,579
  8. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  9. 2017Non-local Neural Networkscited by 2,290
  10. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  11. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  12. 2019Objects as Pointscited by 1,172
38 more
  1. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  2. 2016Colorful Image Colorizationcited by 1,113
  3. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  4. 2020Object-Centric Learning with Slot Attentioncited by 865
  5. 2018Image Transformercited by 770
  6. 2019VideoBERT: A Joint Model for Video and Language Representation Learningcited by 702
  7. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  8. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  9. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  10. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  11. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  12. 2016Convolutional Pose Machinescited by 325
  13. 2020Exploring Self-attention for Image Recognitioncited by 313
  14. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  15. 2017Relation Networks for Object Detectioncited by 305
  16. 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 285
  17. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  18. 2020Semantic Photo Manipulation with a Generative Image Priorcited by 178
  19. 2021Hand-Object Contact Consistency Reasoning for Human Grasps Generationcited by 160
  20. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  21. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  22. 2020Self-Supervised Policy Adaptation during Deploymentcited by 121
  23. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  24. 2018Unsupervised Learning of Object Landmarks through Conditional Image Generationcited by 113
  25. 2020Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimationcited by 113
  26. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 113
  27. 2019Unsupervised Learning of Object Keypoints for Perception and Controlcited by 109
  28. 2021Pose Recognition with Cascade Transformerscited by 99
  29. 2019Single-Stage Multi-Person Pose Machinescited by 95
  30. 2020Causal Discovery in Physical Systems from Videoscited by 77
  31. 2018Unsupervised Discovery of Object Landmarks as Structural Representationscited by 73
  32. 2020Keypoints into the Future: Self-Supervised Correspondence in Model-Based Reinforcement Learningcited by 69
  33. 2019Unsupervised Part-Based Disentangling of Object Shape and Appearancecited by 67
  34. 2020Tent: Fully Test-time Adaptation by Entropy Minimizationcited by 59
  35. 2017Learning Feature Pyramids for Human Pose Estimationcited by 57
  36. 2015Flowing ConvNets for Human Pose Estimation in Videoscited by 55
  37. 2017Detect-and-Track: Efficient Pose Estimation in Videoscited by 51
  38. 2020Online Adaptation for Consistent Mesh Reconstruction in the Wildcited by 51

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 9; 2023: 13; 2024: 4; 2025: 5; 2026: 1.

33 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2022MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentationcited by 76
  3. 2022MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstructioncited by 72
  4. 2022Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstructioncited by 67
  5. 2022Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imagingcited by 66
  6. 2023On Pitfalls of Test-Time Adaptationcited by 63
  7. 2022Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Expertscited by 50
  8. 2023Improved Test-Time Adaptation for Domain Generalizationcited by 45
  9. 2021Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspectivecited by 40
  10. 2024Dual Prototype Evolving for Test-Time Generalization of Vision-Language Modelscited by 36
  11. 2023Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Modelscited by 26
  12. 2023Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptationcited by 23
21 more
  1. 2023AUTO: Adaptive Outlier Optimization for Test-Time OOD Detectioncited by 12
  2. 2024ForgeryTTT: Zero-Shot Image Manipulation Localization with Test-Time Trainingcited by 8
  3. 2023Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimationcited by 7
  4. 2022Boost Test-Time Performance with Closed-Loop Inferencecited by 6
  5. 2022Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022cited by 5
  6. 2023From Question to Exploration: Test-Time Adaptation in Semantic Segmentation?cited by 5
  7. 2022Skeleton2Humanoid: Animating Simulated Characters for Physically-plausible Motion In-betweeningcited by 4
  8. 2023Active Transfer Learning for Efficient Video-Specific Human Pose Estimationcited by 4
  9. 2025Align the GAP: Prior-based Unified Multi-Task Remote Physiological Measurement Framework For Domain Generalization and Personalizationcited by 4
  10. 2025PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completioncited by 4
  11. 2023Generalized Robust Test-Time Adaptation in Continuous Dynamic Scenarioscited by 3
  12. 2023Meta-Auxiliary Learning for Adaptive Human Pose Predictioncited by 2
  13. 2023Boost Video Frame Interpolation via Motion Adaptationcited by 2
  14. 2025Not Only Consistency: Enhance Test-Time Adaptation with Spatio-temporal Inconsistency for Remote Physiological Measurementcited by 2
  15. 2026Towards Egocentric 3D Hand Pose Estimation in Unseen Domainscited by 2
  16. 2023H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulationcited by 1
  17. 2024Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesiscited by 1
  18. 2022A new benchmark for group distribution shifts in hand grasp regression for object manipulation. Can meta-learning raise the bar?cited by 0
  19. 2024FlexPose: Pose Distribution Adaptation with Limited Guidancecited by 0
  20. 2025Differentially Private 2D Human Pose Estimationcited by 0
  21. 2025POEM: Explore Unexplored Reliable Samples to Enhance Test-Time Adaptationcited by 0