TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

research

Forty-Four Runners Became a Markerless Benchmark

VideoRun2D compared pose trackers against expert annotations across 314 sprints and reduced its best joint-angle errors with post-processing.

Published Updated Story ID: mp-2026-08-21-011
Read the complete editionStory JSON

Summary

VideoRun2D compared pose trackers against expert annotations across 314 sprints and reduced its best joint-angle errors with post-processing.

VideoRun2D evaluates hip and knee angle estimates from multiple human-pose trackers on 314 sprints by 44 professional runners. Expert manual annotations supply the comparison, and an outlier-processing module reduced the best reported root-mean-square errors from 11.46 to 9.87 degrees and from 5.83 to 5.30 degrees for the two target angles. The study supports biomechanical analysis from video, not medical diagnosis or replacement of laboratory measurement.

Why it matters

VideoRun2D compared pose trackers against expert annotations across 314 sprints and reduced its best joint-angle errors with post-processing.

Limits and context

  • The study supports biomechanical analysis from video, not medical diagnosis or replacement of laboratory measurement.

Key claims

  1. VideoRun2D compared pose trackers against expert annotations across 314 sprints and reduced its best joint-angle errors with post-processing.

    Qualification: The study supports biomechanical analysis from video, not medical diagnosis or replacement of laboratory measurement.

    Evidence: source-2026-08-21-011

Sources

  1. arXiv preprint 2608.19480arXiv · primary research

Corrections

No corrections have been recorded for this story.