mlsanityData to 7 Oct 2026

ActionPrompt: Action-Guided 3D Human Pose Estimation With Text and Pose Prompting

arXiv 2307.09026 ↗First posted 18 Jul 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Recent 2D-to-3D human pose estimation (HPE) utilizes temporal consistency across sequences to alleviate the depth ambiguity problem but ignore the action related prior knowledge hidden in the pose sequence. In this paper, we propose a plug-and-play module named Action Prompt Module (APM) that effectively mines different kinds of action clues for 3D HPE. The highlight is that, the mining scheme of APM can be widely adapted to different frameworks and bring consistent benefits. Specifically, we first present a novel Action-related Text Prompt module (ATP) that directly embeds action labels and transfers the rich language information in the label to the pose sequence. Besides, we further introduce Action-specific Pose Prompt module (APP) to mine the position-aware pose pattern of each action, and exploit the correlation between the mined patterns and input pose sequence for further pose refinement. Experiments show that APM can improve the performance of most video-based 2D-to-3D HPE frameworks by a large margin.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 15 of its 21 references that are in the map. First posted on arXiv 18 Jul 2023.

Builds on

15 of 21 references.

References · 15

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  4. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  5. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 530
  6. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 504
  7. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  8. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  9. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  10. 20182D/3D Pose Estimation and Action Recognition using Multitask Deep Learningcited by 103
  11. 2021SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videoscited by 64
  12. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
3 more
  1. 2019Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognitioncited by 35
  2. 2023Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimationcited by 19
  3. 2021Hierarchical Graph Networks for 3D Human Pose Estimationcited by 11

Built on by

Cited by year

Citing papers per year: 2024: 5; 2025: 3.

8 papers.

  1. 2024Image Compression for Machine and Human Vision with Spatial-Frequency Adaptationcited by 26
  2. 2024FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Modelscited by 23
  3. 2024Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learningcited by 11
  4. 2025HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimationcited by 8
  5. 2024BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learningcited by 6
  6. 2025DreamPose3D: Hallucinative Diffusion with Prompt Learning for 3D Human Pose Estimationcited by 2
  7. 2025Talk is Not Always Cheap: Promoting Wireless Sensing Models with Text Promptscited by 1
  8. 2024LangPose: Language-Aligned Motion for Robust 3D Human Pose Estimationcited by 0