# YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss

arXiv: https://arxiv.org/abs/2204.06806 · HTML: https://mlsanity.com/paper/2204.06806/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 33 references that are in the map.
- First posted on arXiv 14 Apr 2022.

## Builds on (most cited first, 29 of 29)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [CSPNet: A New Backbone that can Enhance Learning Capability of CNN](https://mlsanity.com/paper/1911.11929/) (2019)
- [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017)
- [HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/1908.10357/) (2019)
- [Associative Embedding: End-to-End Learning for Joint Detection and Grouping](https://mlsanity.com/paper/1611.05424/) (2016)
- [PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model](https://mlsanity.com/paper/1803.08225/) (2018)
- [Towards Accurate Multi-person Pose Estimation in the Wild](https://mlsanity.com/paper/1701.01779/) (2017)
- [PifPaf: Composite Fields for Human Pose Estimation](https://mlsanity.com/paper/1903.06593/) (2019)
- [DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation](https://mlsanity.com/paper/1511.06645/) (2015)
- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [Single-Stage Multi-Person Pose Machines](https://mlsanity.com/paper/1908.09220/) (2019)
- [EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation](https://mlsanity.com/paper/2007.08090/) (2020)

## Built on by (most cited first, 30 of 68)

- [Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models](https://mlsanity.com/paper/2606.03748/) (2026)
- [RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation](https://mlsanity.com/paper/2312.07526/) (2023)
- [JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Tracking](https://mlsanity.com/paper/2210.11940/) (2022)
- [Robots That Can See: Leveraging Human Pose for Trajectory Prediction](https://mlsanity.com/paper/2309.17209/) (2023)
- [The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences](https://mlsanity.com/paper/2406.10447/) (2024)
- [Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks](https://mlsanity.com/paper/2209.13948/) (2022)
- [Towards Online Multi-Modal Social Interaction Understanding](https://mlsanity.com/paper/2503.19851/) (2025)
- [PIP-Net: Pedestrian Intention Prediction in the Wild](https://mlsanity.com/paper/2402.12810/) (2024)
- [HandOS: 3D Hand Reconstruction in One Stage](https://mlsanity.com/paper/2412.01537/) (2024)
- [ProbPose: A Probabilistic Approach to 2D Human Pose Estimation](https://mlsanity.com/paper/2412.02254/) (2024)
- [YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems](https://mlsanity.com/paper/2408.09332/) (2024)
- [Hierarchical Windowed Graph Attention Network and a Large Scale Dataset for Isolated Indian Sign Language Recognition](https://mlsanity.com/paper/2407.14224/) (2024)
- [WheelPoser: Sparse-IMU Based Body Pose Estimation for Wheelchair Users](https://mlsanity.com/paper/2409.08494/) (2024)
- [KGNv2: Separating Scale and Pose Prediction for Keypoint-based 6-DoF Grasp Synthesis on RGB-D input](https://mlsanity.com/paper/2303.05617/) (2023)
- [HGMamba: Enhancing 3D Human Pose Estimation with a HyperGCN-Mamba Network](https://mlsanity.com/paper/2504.06638/) (2025)
- [MultiCrafter: High-Fidelity Multi-Subject Generation via Disentangled Attention and Identity-Aware Preference Alignment](https://mlsanity.com/paper/2509.21953/) (2025)
- [Improving the Reproducibility of Deep Learning Software: An Initial Investigation through a Case Study Analysis](https://mlsanity.com/paper/2505.03165/) (2025)
- [From Orthomosaics to Raw UAV Imagery: Enhancing Palm Detection and Crown-Center Localization](https://mlsanity.com/paper/2509.12400/) (2025)
- [EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation](https://mlsanity.com/paper/2603.18739/) (2026)
- [BPJDet: Extended Object Representation for Generic Body-Part Joint Detection](https://mlsanity.com/paper/2304.10765/) (2023)
- [Model Compression Methods for YOLOv5: A Review](https://mlsanity.com/paper/2307.11904/) (2023)
- [Riverbed litter monitoring using consumer-grade aerial-aquatic speedy scanner (AASS) and deep learning based super-resolution reconstruction and detection network](https://mlsanity.com/paper/2408.03564/) (2024)
- [EasyVis2: A Real Time Multi-view 3D Visualization System for Laparoscopic Surgery Training Enhanced by a Deep Neural Network YOLOv8-Pose](https://mlsanity.com/paper/2412.16742/) (2024)
- [Marginalized Generalized IoU (MGIoU): A Unified Objective Function for Optimizing Any Convex Parametric Shapes](https://mlsanity.com/paper/2504.16443/) (2025)
- [Pointing-Guided Target Estimation via Transformer-Based Attention](https://mlsanity.com/paper/2509.05031/) (2025)
- [A Real-Time Multi-Task Learning System for Joint Detection of Face, Facial Landmark and Head Pose](https://mlsanity.com/paper/2309.11773/) (2023)
- [YOLOv7 for Mosquito Breeding Grounds Detection and Tracking](https://mlsanity.com/paper/2310.10423/) (2023)
- [PBADet: A One-Stage Anchor-Free Approach for Part-Body Association](https://mlsanity.com/paper/2402.07814/) (2024)
- [PoseAdapt: Sustainable Human Pose Estimation via Continual Learning Benchmarks and Toolkit](https://mlsanity.com/paper/2409.20469/) (2024)
- [DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypoints](https://mlsanity.com/paper/2506.13027/) (2025)

## Abstract (arXiv)

We introduce YOLO-pose, a novel heatmap-free approach for joint detection, and 2D multi-person pose estimation in an image based on the popular YOLO object detection framework. Existing heatmap based two-stage approaches are sub-optimal as they are not end-to-end trainable and training relies on a surrogate L1 loss that is not equivalent to maximizing the evaluation metric, i.e. Object Keypoint Similarity (OKS). Our framework allows us to train the model end-to-end and optimize the OKS metric itself. The proposed model learns to jointly detect bounding boxes for multiple persons and their corresponding 2D poses in a single forward pass and thus bringing in the best of both top-down and bottom-up approaches. Proposed approach doesn't require the postprocessing of bottom-up approaches to group detected keypoints into a skeleton as each bounding box has an associated pose, resulting in an inherent grouping of the keypoints. Unlike top-down approaches, multiple forward passes are done away with since all persons are localized along with their pose in a single inference. YOLO-pose achieves new state-of-the-art results on COCO validation (90.2% AP50) and test-dev set (90.3% AP50), surpassing all existing bottom-up approaches in a single forward pass without flip test, multi-scale testing, or any other test time augmentation. All experiments and results reported in this paper are without any test time augmentation, unlike traditional approaches that use flip-test and multi-scale testing to boost performance. Our training codes will be made publicly available at https://github.com/TexasInstruments/edgeai-yolov5 and https://github.com/TexasInstruments/edgeai-yolox