# Pose Flow: Efficient Online Pose Tracking

arXiv: https://arxiv.org/abs/1802.00977 · HTML: https://mlsanity.com/paper/1802.00977/

## Key facts

- Cited by 80 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Feb 2018.

## Built on by (most cited first, 30 of 80)

- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking](https://mlsanity.com/paper/2203.14360/) (2022)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [Capturing and Inferring Dense Full-Body Human-Scene Contact](https://mlsanity.com/paper/2206.09553/) (2022)
- [TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments](https://mlsanity.com/paper/2306.02850/) (2023)
- [Normalizing Flows for Human Pose Anomaly Detection](https://mlsanity.com/paper/2211.10946/) (2022)
- [Deep Dual Consecutive Network for Human Pose Estimation](https://mlsanity.com/paper/2103.07254/) (2021)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild](https://mlsanity.com/paper/2108.02452/) (2021)
- [Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking](https://mlsanity.com/paper/2106.03772/) (2021)
- [DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2307.16687/) (2023)
- [On the Benefits of 3D Pose and Tracking for Human Action Recognition](https://mlsanity.com/paper/2304.01199/) (2023)
- [FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection](https://mlsanity.com/paper/2301.04019/) (2023)
- [ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search](https://mlsanity.com/paper/2105.10154/) (2021)
- [Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2203.15227/) (2022)
- [Tracking People with 3D Representations](https://mlsanity.com/paper/2111.07868/) (2021)
- [Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection](https://mlsanity.com/paper/2112.03649/) (2021)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Network](https://mlsanity.com/paper/2107.00894/) (2021)
- [Simple Baseline for Single Human Motion Forecasting](https://mlsanity.com/paper/2110.07495/) (2021)
- [Egocentric Human Trajectory Forecasting with a Wearable Camera and Multi-Modal Fusion](https://mlsanity.com/paper/2111.00993/) (2021)
- [Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos](https://mlsanity.com/paper/2207.09425/) (2022)
- [Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video](https://mlsanity.com/paper/2303.08475/) (2023)
- [Tracking People by Predicting 3D Appearance, Location & Pose](https://mlsanity.com/paper/2112.04477/) (2021)
- [Behavior-Driven Synthesis of Human Dynamics](https://mlsanity.com/paper/2103.04677/) (2021)
- [Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generation](https://mlsanity.com/paper/2207.03714/) (2022)
- [Contracting Skeletal Kinematics for Human-Related Video Anomaly Detection](https://mlsanity.com/paper/2301.09489/) (2023)
- [Human MotionFormer: Transferring Human Motions with Vision Transformers](https://mlsanity.com/paper/2302.11306/) (2023)
- [TrouSPI-Net: Spatio-temporal attention on parallel atrous convolutions and U-GRUs for skeletal pedestrian crossing prediction](https://mlsanity.com/paper/2109.00953/) (2021)
- [Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions](https://mlsanity.com/paper/2202.11423/) (2022)

## Abstract (arXiv)

Multi-person articulated pose tracking in unconstrained videos is an important while challenging problem. In this paper, going along the road of top-down approaches, we propose a decent and efficient pose tracker based on pose flows. First, we design an online optimization framework to build the association of cross-frame poses and form pose flows (PF-Builder). Second, a novel pose flow non-maximum suppression (PF-NMS) is designed to robustly reduce redundant pose flows and re-link temporal disjoint ones. Extensive experiments show that our method significantly outperforms best-reported results on two standard Pose Tracking datasets by 13 mAP 25 MOTA and 6 mAP 3 MOTA respectively. Moreover, in the case of working on detected poses in individual frames, the extra computation of pose tracker is very minor, guaranteeing online 10FPS tracking. Our source codes are made publicly available(https://github.com/YuliangXiu/PoseFlow).