# Joint Flow: Temporal Flow Fields for Multi Person Tracking

arXiv: https://arxiv.org/abs/1805.04596 · HTML: https://mlsanity.com/paper/1805.04596/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 May 2018.

## Built on by (most cited first, 5 of 5)

- [Deep Dual Consecutive Network for Human Pose Estimation](https://mlsanity.com/paper/2103.07254/) (2021)
- [Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2203.15227/) (2022)
- [OTPose: Occlusion-Aware Transformer for Pose Estimation in Sparsely-Labeled Videos](https://mlsanity.com/paper/2207.09725/) (2022)
- [SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation](https://mlsanity.com/paper/2104.02486/) (2021)
- [Human Modelling and Pose Estimation Overview](https://mlsanity.com/paper/2406.19290/) (2024)

## Abstract (arXiv)

In this work we propose an online multi person pose tracking approach which works on two consecutive frames It-1 and It. The general formulation of our temporal network allows to rely on any multi person pose estimation approach as spatial network. From the spatial network we extract image features and pose features for both frames. These features serve as input for our temporal model that predicts Temporal Flow Fields (TFF). These TFF are vector fields which indicate the direction in which each body joint is going to move from frame It-1 to frame It. This novel representation allows to formulate a similarity measure of detected joints. These similarities are used as binary potentials in a bipartite graph optimization problem in order to perform tracking of multiple poses. We show that these TFF can be learned by a relative small CNN network whilst achieving state-of-the-art multi person pose tracking results.