mlsanityData to 7 Oct 2026

LAMP: Leveraging Language Prompts for Multi-person Pose Estimation

arXiv 2307.11934 ↗First posted 21 Jul 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Human-centric visual understanding is an important desideratum for effective human-robot interaction. In order to navigate crowded public places, social robots must be able to interpret the activity of the surrounding humans. This paper addresses one key aspect of human-centric visual understanding, multi-person pose estimation. Achieving good performance on multi-person pose estimation in crowded scenes is difficult due to the challenges of occluded joints and instance separation. In order to tackle these challenges and overcome the limitations of image features in representing invisible body parts, we propose a novel prompt-based pose inference strategy called LAMP (Language Assisted Multi-person Pose estimation). By utilizing the text representations generated by a well-trained language model (CLIP), LAMP can facilitate the understanding of poses on the instance and joint levels, and learn more robust visual representations that are less susceptible to occlusion. This paper demonstrates that language-supervised training boosts the performance of single-stage multi-person pose estimation, and both instance-level and joint-level prompts are valuable for training. The code is available at https://github.com/shengnanh20/LAMP.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 43 of its 52 references that are in the map. First posted on arXiv 21 Jul 2023.

Builds on

43 of 52 references.

References · 43

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2017Mask R-CNNcited by 7,259
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  6. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  7. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  8. 2019Objects as Pointscited by 1,172
  9. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  10. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  11. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 529
  12. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
31 more
  1. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  2. 2021Prompting Visual-Language Models for Efficient Video Understandingcited by 309
  3. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  4. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  5. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  6. 2020Deep Learning-Based Human Pose Estimation: A Surveycited by 205
  7. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  8. 2015DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimationcited by 117
  9. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  10. 2023Synthesizing Diverse Human Motions in 3D Indoor Scenescited by 109
  11. 2018Pose2Seg: Detection Free Human Instance Segmentationcited by 107
  12. 2021Pose Recognition with Cascade Transformerscited by 99
  13. 2016DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Modelcited by 96
  14. 2019Single-Stage Multi-Person Pose Machinescited by 95
  15. 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimationcited by 91
  16. 2022K-LITE: Learning Transferable Visual Models with External Knowledgecited by 79
  17. 2020Rethinking the Heatmap Regression for Bottom-up Human Pose Estimationcited by 69
  18. 2022Can Language Understand Depth?cited by 66
  19. 2022Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Studycited by 66
  20. 2020Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimationcited by 57
  21. 2020Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimationcited by 52
  22. 2021FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutionscited by 34
  23. 2023POTTER: Pooling Attention Transformer for Efficient Human Mesh Recoverycited by 31
  24. 2020Peeking into occluded joints: A novel framework for crowd pose estimationcited by 25
  25. 2023Part Aware Contrastive Learning for Self-Supervised Action Recognitioncited by 21
  26. 2021The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimationcited by 18
  27. 2021Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimationcited by 14
  28. 2021InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose Estimationcited by 13
  29. 2022FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformERcited by 9
  30. 2022I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimationcited by 6
  31. 2020Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint Estimatescited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 2.

4 papers.

  1. 2023Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matchingcited by 10
  2. 2025DreamPose3D: Hallucinative Diffusion with Prompt Learning for 3D Human Pose Estimationcited by 2
  3. 2024MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint Detectioncited by 1
  4. 2025Parse Graph-Based Visual-Language Interaction for Human Pose Estimationcited by 0