# A Top-down Approach to Articulated Human Pose Estimation and Tracking

## TL;DR

This paper presents a top-down system for multi-person human pose estimation and tracking in videos, combining human detection, pose estimation, and flow-based tracking to improve accuracy and consistency.

## Contribution

It introduces a strong baseline system with a modular pipeline for pose estimation and tracking, validated through extensive experiments and participation in ECCV 18 challenges.

## Key findings

- Effective human candidate detection using state-of-the-art methods
- Accurate single-person pose estimation with cascaded pyramid networks
- Robust pose tracking via flow-based keypoint association

## Abstract

Both the tasks of multi-person human pose estimation and pose tracking in videos are quite challenging. Existing methods can be categorized into two groups: top-down and bottom-up approaches. In this paper, following the top-down approach, we aim to build a strong baseline system with three modules: human candidate detector, single-person pose estimator and human pose tracker. Firstly, we choose a generic object detector among state-of-the-art methods to detect human candidates. Then, the cascaded pyramid network is used to estimate the corresponding human pose. Finally, we use a flow-based pose tracker to render keypoint-association across frames, i.e., assigning each human candidate a unique and temporally-consistent id, for the multi-target pose tracking purpose. We conduct extensive ablative experiments to validate various choices of models and configurations. We take part in two ECCV 18 PoseTrack challenges: pose estimation and pose tracking.