mlsanityData to 14 Oct 2026

Pose for Everything: Towards Category-Agnostic Pose Estimation

arXiv 2207.10387 ↗First posted 21 Jul 2022cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

Existing works on 2D pose estimation mainly focus on a certain category, e.g. human, animal, and vehicle. However, there are lots of application scenarios that require detecting the poses/keypoints of the unseen class of objects. In this paper, we introduce the task of Category-Agnostic Pose Estimation (CAPE), which aims to create a pose estimation model capable of detecting the pose of any class of object given only a few samples with keypoint definition. To achieve this goal, we formulate the pose estimation problem as a keypoint matching problem and design a novel CAPE framework, termed POse Matching Network (POMNet). A transformer-based Keypoint Interaction Module (KIM) is proposed to capture both the interactions among different keypoints and the relationship between the support and query images. We also introduce Multi-category Pose (MP-100) dataset, which is a 2D pose dataset of 100 object categories containing over 20K instances and is well-designed for developing CAPE algorithms. Experiments show that our method outperforms other baseline approaches by a large margin. Codes and data are available at https://github.com/luminxu/Pose-for-Everything.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Builds on 55 of its 76 references that are in the map. First posted on arXiv 21 Jul 2022.

Builds on

55 of 76 references.

References · 55

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2020End-to-End Object Detection with Transformerscited by 7,414
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  8. 2016Matching Networks for One Shot Learningcited by 2,255
  9. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  10. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  11. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  12. 2018Image Transformercited by 772
38 more
  1. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 525
  2. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  3. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  4. 2016Convolutional Pose Machinescited by 325
  5. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  6. 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
  7. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  8. 2020InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Imagecited by 245
  9. 2017Learning to Estimate 3D Hand Pose from Single RGB Imagescited by 234
  10. 2017Hand Keypoint Detection in Single Images using Multiview Bootstrappingcited by 231
  11. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  12. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  13. 2018Low-Shot Learning from Imaginary Datacited by 181
  14. 2020Whole-Body Human Pose Estimation in the Wildcited by 178
  15. 2017PoseTrack: A Benchmark for Human Pose Estimation and Trackingcited by 173
  16. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  17. 2017GANerated Hands for Real-time 3D Hand Tracking from Monocular RGBcited by 147
  18. 2018Look at Boundary: A Boundary-Aware Face Alignment Algorithmcited by 138
  19. 2019DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Imagescited by 134
  20. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  21. 2017Compositional Human Pose Regressioncited by 124
  22. 2021AP-10K: A Benchmark for Animal Pose Estimation in the Wildcited by 123
  23. 2019Cross-Domain Adaptation for Animal Pose Estimationcited by 108
  24. 2018Pose2Seg: Detection Free Human Instance Segmentationcited by 107
  25. 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 107
  26. 2022Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformercited by 101
  27. 2019Single-Stage Multi-Person Pose Machinescited by 95
  28. 2018Class-Agnostic Countingcited by 85
  29. 2017Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensorcited by 84
  30. 2017AI Challenger : A Large-scale Dataset for Going Deeper in Image Understandingcited by 73
  31. 2017Multi-Context Attention for Human Pose Estimationcited by 66
  32. 2018Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsingcited by 60
  33. 2018ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Drivingcited by 59
  34. 2020Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimationcited by 52
  35. 2019Pretraining boosts out-of-domain robustness for pose estimationcited by 47
  36. 2018StarMap for Category-Agnostic Keypoint and Viewpoint Estimationcited by 42
  37. 2021TFPose: Direct Human Pose Estimation with Transformerscited by 42
  38. 2019Multi-person Articulated Tracking with Spatial and Temporal Embeddingscited by 38

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 9; 2024: 10; 2025: 12; 2026: 5.

36 papers.

Sort:

By area:

  1. 2023AutoDecoding Latent 3D Diffusion Modelscited by 50
  2. 2023X-Pose: Detecting Any Keypointscited by 21
  3. 2023A Graph-Based Approach for Category-Agnostic Pose Estimationcited by 17
  4. 2023Segment Anything in Non-Euclidean Domains: Challenges and Opportunitiescited by 16
  5. 2025FaceShot: Bring Any Character into Lifecited by 13
  6. 2023Neural Interactive Keypoint Detectioncited by 12
  7. 2023Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matchingcited by 11
  8. 2025MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videoscited by 10
  9. 2023You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perceptioncited by 9
  10. 2024CapeX: Category-Agnostic Pose Estimation from Textual Point Explanationcited by 9
  11. 2024OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detectioncited by 8
  12. 2023UniAP: Towards Universal Animal Perception in Vision via Few-shot Learningcited by 7
24 more
  1. 2024Meta-Point Learning and Refining for Category-Agnostic Pose Estimationcited by 7
  2. 2024KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehensioncited by 5
  3. 2023Meta Omnium: A Benchmark for General-Purpose Learning-to-Learncited by 4
  4. 2025AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Modelscited by 4
  5. 2024VoxelKeypointFusion: Generalizable Multi-View Multi-Person Pose Estimationcited by 3
  6. 2025Learning Structure-Supporting Dependencies via Keypoint Interactive Transformer for General Mammal Pose Estimationcited by 3
  7. 2025Probabilistic Prompt Distribution Learning for Animal Pose Estimationcited by 3
  8. 2026MARCO: Navigating the Unseen Space of Semantic Correspondencecited by 3
  9. 2024UniFS: Universal Few-shot Instance Perception with Point Representationscited by 2
  10. 2024CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Modelscited by 2
  11. 2025Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimationcited by 2
  12. 2026MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletonscited by 2
  13. 2024FAFA: Frequency-Aware Flow-Aided Self-Supervision for Underwater Object Pose Estimationcited by 1
  14. 2025PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimationcited by 1
  15. 2024Edge Weight Prediction For Category-Agnostic Pose Estimationcited by 0
  16. 2024Skel3D: Skeleton Guided Novel View Synthesiscited by 0
  17. 2025Incremental Object Keypoint Learningcited by 0
  18. 2025KptLLM++: Towards Generic Keypoint Comprehension with Large Language Modelcited by 0
  19. 2025Talking Points: Describing and Localizing Pixelscited by 0
  20. 2025CapeNext: Rethinking and Refining Dynamic Support Information for Category-Agnostic Pose Estimationcited by 0
  21. 2025Point-to-Point: Sparse Motion Guidance for Controllable Video Editingcited by 0
  22. 2026PoseDriver: A Unified Approach to Multi-Category Skeleton Detection for Autonomous Drivingcited by 0
  23. 2026GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose Estimationcited by 0
  24. 2026GKDT: General Keypoint Detection Transformercited by 0