Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-7

Pose Tracking

3260 papers • 126 benchmarks • 313 datasets

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

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in pose-tracking-7

Trend

Dataset

Best Model

Actions

PoseTrack2017

PoseTrack2017

PoseTrack2018

PoseTrack2018

Multi-Person PoseTrack

Libraries

i

Use these libraries to find pose-tracking-7 models and implementations

open-mmlab/mmpose

3 papers 4,932

Datasets

PoseTrack

10,000 People - Human Pose Recognition Data

10,000 People - Human Pose Recognition Data

HOI4D

YCBInEOAT Dataset

YCBInEOAT Dataset

VR Mocap Dataset for Pose/Orientation Prediction

VR Mocap Dataset for Pose/Orientation Prediction

Subtasks

3D Human Pose Tracking

Most implemented papers

Deep High-Resolution Representation Learning for Human Pose Estimation

Ke Sun, Bin Xiao, Dong Liu, Jingdong Wang•Sun Feb 24 2019

This paper proposes a network that maintains high-resolution representations through the whole process of human pose estimation and empirically demonstrates the effectiveness of the network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset.

4672

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Multi-Person PoseTrack

dlr-rm/3dobjecttracking

3 papers 591

PaddlePaddle/PaddleDetection

2 papers 11,993

2 papers 2,915

wenbowen123/BundleTrack

2 papers 569

mindspore-lab/mindpose

2 papers 15

VRMocap: VR Mocap Dataset for Pose Reconstruction

VRMocap: VR Mocap Dataset for Pose Reconstruction

VR-Folding

Drunkard's Dataset

Drunkard's Dataset

InfiniteRep

0

Simple Baselines for Human Pose Estimation and Tracking

Bin Xiao, Yichen Wei, Haiping Wu•Mon Apr 16 2018

This work provides simple and effective baseline methods for pose estimation that are helpful for inspiring and evaluating new ideas for the field and achieved on challenging benchmarks.

1995 0

BlazePose: On-device Real-time Body Pose tracking

Valentin Bazarevsky, Ivan Grishchenko, Karthik Raveendran, Tyler Lixuan Zhu, Fan Zhang, Matthias Grundmann•Tue Jun 16 2020

BlazePose is presented, a lightweight convolutional neural network architecture for human pose estimation that is tailored for real-time inference on mobile devices that uses both heatmaps and regression to keypoint coordinates.

735 0

Event-based Camera Pose Tracking using a Generative Event Model

D. Scaramuzza, Guillermo Gallego, Elias Mueggler, Christian Forster•Tue Oct 06 2015

This work tackles the problem of event-based camera localization in a known environment, without additional sensing, using a probabilistic generative event model in a Bayesian filtering framework and proposes to use the contrast residual as a measure of how well the estimated pose of the event- based camera and the environment explain the observed events.

62 0

PoseTrack: Joint Multi-person Pose Estimation and Tracking

Anton Milan, Juergen Gall•Tue Nov 22 2016

This work proposes a novel method that jointly models multi-person pose estimation and tracking in a single formulation and introduces a challenging Multi-Person PoseTrack dataset, and proposes a completely unconstrained evaluation protocol that does not make any assumptions about the scale, size, location or the number of persons.

233 0

PoseTrack: A Benchmark for Human Pose Estimation and Tracking

Mykhaylo Andriluka, B. Schiele, Anton Milan, Juergen Gall, Eldar Insafutdinov, L. Pishchulin•Thu Oct 26 2017

PoseTrack is a new large-scale benchmark for video-based human pose estimation and articulated tracking that conducts an extensive experimental study on recent approaches to articulated pose tracking and provides analysis of the strengths and weaknesses of the state of the art.

501 0

Capturing Hand Motion with an RGB-D Sensor, Fusing a Generative Model with Salient Points

Juergen Gall, Dimitrios Tzionas, A. Srikantha, Pablo Aponte•Mon Sep 01 2014

This work proposes a framework for hand tracking that can capture the motion of two interacting hands using only a single, inexpensive RGB-D camera, and combines a generative model with collision detection and discriminatively learned salient points.

33 0

Multigrid Predictive Filter Flow for Unsupervised Learning on Videos

Charless C. Fowlkes, Shu Kong•Mon Apr 01 2019

It is shown that mgPFF is able to not only estimate long-range flow for frame reconstruction and detect video shot transitions, but also readily amendable for video object segmentation and pose tracking, where it substantially outperforms the published state-of-the-art without bells and whistles.

16 0

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

G. Ning, Heng Huang•Mon May 06 2019

A Siamese Graph Convolution Network is proposed for human pose matching as a Re-ID module, which uses a graphical representation of human joints for matching and is robust to sudden camera shifts that introduce human drifting.

75 0

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

S. Savarese, Li Fei-Fei, Yuke Zhu, Roberto Mart'in-Mart'in, Chen Wang, Danfei Xu, Jun Lv, Cewu Lu•Tue Oct 22 2019

6-PACK learns to compactly represent an object by a handful of 3D keypoints, based on which the interframe motion of an object instance can be estimated through keypoint matching, and substantially outperforms existing methods on the NOCS category-level 6D pose estimation benchmark.

167 0

Adding a benchmark result helps the community track progress.

Pose Tracking | State-of-the-Art