mlsanityData to 7 Oct 2026

Meta-Point Learning and Refining for Category-Agnostic Pose Estimation

arXiv 2403.13647 ↗First posted 20 Mar 2024cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Category-agnostic pose estimation (CAPE) aims to predict keypoints for arbitrary classes given a few support images annotated with keypoints. Existing methods only rely on the features extracted at support keypoints to predict or refine the keypoints on query image, but a few support feature vectors are local and inadequate for CAPE. Considering that human can quickly perceive potential keypoints of arbitrary objects, we propose a novel framework for CAPE based on such potential keypoints (named as meta-points). Specifically, we maintain learnable embeddings to capture inherent information of various keypoints, which interact with image feature maps to produce meta-points without any support. The produced meta-points could serve as meaningful potential keypoints for CAPE. Due to the inevitable gap between inherency and annotation, we finally utilize the identities and details offered by support keypoints to assign and refine meta-points to desired keypoints in query image. In addition, we propose a progressive deformable point decoder and a slacked regression loss for better prediction and supervision. Our novel framework not only reveals the inherency of keypoints but also outperforms existing methods of CAPE. Comprehensive experiments and in-depth studies on large-scale MP-100 dataset demonstrate the effectiveness of our framework.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 41 of its 57 references that are in the map. First posted on arXiv 20 Mar 2024.

Builds on

41 of 57 references.

References · 41

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  8. 2017Non-local Neural Networkscited by 2,290
  9. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  10. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
  11. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  12. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
29 more
  1. 2021A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Modelcited by 223
  2. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  3. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  4. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  5. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  6. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  7. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  8. 2020CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinementcited by 113
  9. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  10. 2019Cross-Domain Adaptation for Animal Pose Estimationcited by 108
  11. 2019Single-Stage Multi-Person Pose Machinescited by 95
  12. 2020Rethinking the Heatmap Regression for Bottom-up Human Pose Estimationcited by 69
  13. 2018ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Drivingcited by 59
  14. 2021Hallucination Improves Few-Shot Object Detectioncited by 50
  15. 2022Poseur: Direct Human Pose Regression with Transformerscited by 43
  16. 2015What makes for effective detection proposals?cited by 38
  17. 2022Pose for Everything: Towards Category-Agnostic Pose Estimationcited by 36
  18. 20193FabRec: Fast Few-shot Face alignment by Reconstructioncited by 33
  19. 2019Revisiting Fine-tuning for Few-shot Learningcited by 29
  20. 2021Few-shot Keypoint Detection with Uncertainty Learning for Unseen Speciescited by 27
  21. 2020Weak-shot Fine-grained Classification via Similarity Transfercited by 18
  22. 2020Class-agnostic Object Detectioncited by 17
  23. 2021Semi-supervised Anatomical Landmark Detection via Shape-regulated Self-trainingcited by 11
  24. 2022Weak-shot Semantic Segmentation via Dual Similarity Transfercited by 10
  25. 2022One-Shot Medical Landmark Localization by Edge-Guided Transform and Noisy Landmark Refinementcited by 8
  26. 2023From Saliency to DINO: Saliency-guided Vision Transformer for Few-shot Keypoint Detectioncited by 8
  27. 2021MetaCloth: Learning Unseen Tasks of Dense Fashion Landmark Detection from a Few Samplescited by 6
  28. 2023Few-shot Geometry-Aware Keypoint Localizationcited by 6
  29. 2021Few-Shot Model Adaptation for Customized Facial Landmark Detection, Segmentation, Stylization and Shadow Removalcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 2.

7 papers.

  1. 2024CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Modelscited by 2
  2. 2025Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimationcited by 2
  3. 2026Adaptive Image Zoom-in with Bounding Box Transformation for UAV Object Detectioncited by 2
  4. 2024Edge Weight Prediction For Category-Agnostic Pose Estimationcited by 0
  5. 2025Incremental Object Keypoint Learningcited by 0
  6. 2025CapeNext: Rethinking and Refining Dynamic Support Information for Category-Agnostic Pose Estimationcited by 0
  7. 2026GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose Estimationcited by 0