About

Pose Tracking is the task of estimating multi-person human poses in videos and assigning unique instance IDs for each keypoint across frames. Accurate estimation of human keypoint-trajectories is useful for human action recognition, human interaction understanding, motion capture and animation.

Source: LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Datasets

Greatest papers with code

Deep High-Resolution Representation Learning for Human Pose Estimation

CVPR 2019 leoxiaobin/deep-high-resolution-net.pytorch

We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel.

INSTANCE SEGMENTATION KEYPOINT DETECTION MULTI-PERSON POSE ESTIMATION OBJECT DETECTION POSE TRACKING REPRESENTATION LEARNING

Simple Baselines for Human Pose Estimation and Tracking

ECCV 2018 Microsoft/human-pose-estimation.pytorch

There has been significant progress on pose estimation and increasing interests on pose tracking in recent years.

KEYPOINT DETECTION POSE TRACKING

Detect-and-Track: Efficient Pose Estimation in Videos

CVPR 2018 facebookresearch/DetectAndTrack

This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video.

Ranked #5 on Pose Tracking on PoseTrack2017 (using extra training data)

HUMAN DETECTION MULTI-OBJECT TRACKING POSE ESTIMATION POSE TRACKING VIDEO UNDERSTANDING

LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking

7 May 2019Guanghan/lighttrack

To the best of our knowledge, this is the first paper to propose an online human pose tracking framework in a top-down fashion.

 Ranked #1 on Pose Tracking on PoseTrack2017 (MAP metric)

POSE ESTIMATION POSE TRACKING VISUAL OBJECT TRACKING

Pose Flow: Efficient Online Pose Tracking

3 Feb 2018YuliangXiu/PoseFlow

Multi-person articulated pose tracking in unconstrained videos is an important while challenging problem.

Ranked #6 on Pose Tracking on PoseTrack2017 (using extra training data)

POSE TRACKING

6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints

23 Oct 2019j96w/6-PACK

We present 6-PACK, a deep learning approach to category-level 6D object pose tracking on RGB-D data.

6D POSE ESTIMATION 6D POSE ESTIMATION USING RGBD POSE TRACKING

PoseTrack: Joint Multi-Person Pose Estimation and Tracking

CVPR 2017 iqbalu/PoseTrack-CVPR2017

In this work, we introduce the challenging problem of joint multi-person pose estimation and tracking of an unknown number of persons in unconstrained videos.

MULTI-PERSON POSE ESTIMATION MULTI-PERSON POSE ESTIMATION AND TRACKING POSE TRACKING

A Region-based Gauss-Newton Approach to Real-Time Monocular Multiple Object Tracking

5 Jul 2018henningtjaden/RBOT

We propose an algorithm for real-time 6DOF pose tracking of rigid 3D objects using a monocular RGB camera.

MULTIPLE OBJECT TRACKING POSE TRACKING