Analysis plans for a child–adult human action recognition benchmark

Analysis plans of a study comparing action recognition accuracy on children and adults with a class-balanced, human-verified benchmark built from Kinetics-700. 1) Main analysis plan (dated 28 September 2026), with a change log that dates each later change and states whether it was made before or after the results. 2) Plan for two additional analyses (26 October 2026): more Kinetics-400 models used off the shelf, and partial fine-tuning of an image and a video backbone. The record contains no data about the people in the videos. Annotations and code will be deposited separately, with restricted access.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-10-26
DOI
https://doi.org/10.5281/zenodo.23674325
Primary Topic
Human Pose and Action Recognition
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Analysis plans for a child–adult human action recognition benchmark

Víctor M. R. Penichet, B. Lorente, L. P. Sáenz Martínez, María Dolores Lozano
Zenodo (CERN European Organization for Nuclear Research)
Human Pose and Action Recognition
article

Analysis plans for a child–adult human action recognition benchmark

Víctor M. R. Penichet, B. Lorente, L. P. Sáenz Martínez, María Dolores Lozano
article en

Abstract

Analysis plans of a study comparing action recognition accuracy on children and adults with a class-balanced, human-verified benchmark built from Kinetics-700. 1) Main analysis plan (dated 28 September 2026), with a change log that dates each later change and states whether it was made before or after the results. 2) Plan for two additional analyses (26 October 2026): more Kinetics-400 models used off the shelf, and partial fine-tuning of an image and a video backbone. The record contains no data about the people in the videos. Annotations and code will be deposited separately, with restricted access.

Zenodo (CERN European Organization for Nuclear Research)
University of Castilla-La Mancha (ES)
Openalex Percentile: Top 17%
Human Pose and Action Recognition
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon