15 Keypoints Is All You Need

12/05/2019
by   Michael Snower, et al.
28

Pose tracking is an important problem that requires identifying unique human pose-instances and matching them temporally across different frames of a video. However, existing pose tracking methods are unable to accurately model temporal relationships and require significant computation, often computing the tracks offline. We present an efficient Multi-person Pose Tracking method, KeyTrack, that only relies on keypoint information without using any RGB or optical flow information to track human keypoints in real-time. Keypoints are tracked using our Pose Entailment method, in which, first, a pair of pose estimates is sampled from different frames in a video and tokenized. Then, a Transformer-based network makes a binary classification as to whether one pose temporally follows another. Furthermore, we improve our top-down pose estimation method with a novel, parameter-free, keypoint refinement technique that improves the keypoint estimates used during the Pose Entailment step. We achieve state-of-the-art results on the PoseTrack'17 and the PoseTrack'18 benchmarks while using only a fraction of the computation required by most other methods for computing the tracking information.

READ FULL TEXT

page 1

page 4

page 7

page 8

page 13

page 14

research
04/27/2020

Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos

Video annotation is expensive and time consuming. Consequently, datasets...
research
01/23/2019

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

Both the tasks of multi-person human pose estimation and pose tracking i...
research
04/30/2012

Parametric annealing: a stochastic search method for human pose tracking

Model based methods to marker-free motion capture have a very high compu...
research
01/04/2020

Grab: Fast and Accurate Sensor Processing for Cashier-Free Shopping

Cashier-free shopping systems like Amazon Go improve shopping experience...
research
12/26/2017

Detect-and-Track: Efficient Pose Estimation in Videos

This paper addresses the problem of estimating and tracking human body k...
research
11/20/2015

Personalizing Human Video Pose Estimation

We propose a personalized ConvNet pose estimator that automatically adap...
research
10/16/2020

A Simple Baseline for Pose Tracking in Videos of Crowded Scenes

This paper presents our solution to ACM MM challenge: Large-scale Human-...

Please sign up or login with your details

Forgot password? Click here to reset