PoseTrack: A Benchmark for Human Pose Estimation and Tracking

TL;DR

PoseTrack introduces a comprehensive benchmark dataset and evaluation platform for advancing research in video-based human pose estimation and tracking, fostering progress through standardized testing and community engagement.

Contribution

It establishes the PoseTrack benchmark with a large-scale annotated dataset and evaluation server, unifying research efforts in human pose estimation and tracking in videos.

Findings

New large-scale annotated dataset released

Benchmark includes three competition tracks

Evaluation server enables standardized comparison

Abstract

Human poses and motions are important cues for analysis of videos with people and there is strong evidence that representations based on body pose are highly effective for a variety of tasks such as activity recognition, content retrieval and social signal processing. In this work, we aim to further advance the state of the art by establishing "PoseTrack", a new large-scale benchmark for video-based human pose estimation and articulated tracking, and bringing together the community of researchers working on visual human analysis. The benchmark encompasses three competition tracks focusing on i) single-frame multi-person pose estimation, ii) multi-person pose estimation in videos, and iii) multi-person articulated tracking. To facilitate the benchmark and challenge we collect, annotate and release a new %large-scale benchmark dataset that features videos with multiple people labeled with person tracks and articulated pose. A centralized evaluation server is provided to allow participants to evaluate on a held-out test set. We envision that the proposed benchmark will stimulate productive research both by providing a large and representative training dataset as well as providing a platform to objectively evaluate and compare the proposed methods. The benchmark is freely accessible at https://posetrack.net.