MétaCan
Menu
Back to cohort
Record W7106608427 · doi:10.1016/j.procs.2025.10.265

Transformer-based Human Action Recognition using Skeleton Heatmap

2025· article· en· W7106608427 on OpenAlexafffund

Bibliographic record

VenueProcedia Computer Science · 2025
Typearticle
Languageen
FieldComputer Science
TopicHuman Pose and Action Recognition
Canadian institutionsQueen's University
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsHuman skeletonSkeleton (computer programming)Pipeline (software)Benchmark (surveying)Activity recognitionGeneralizationPattern recognition (psychology)BiometricsGaussian

Abstract

fetched live from OpenAlex

Human activity recognition (HAR) can alert clinicians when a frail patient falls, track rehabilitation exercises, and ease the workload of healthcare staff. Yet continuous video recording in wards or homes raises serious privacy concerns. Converting each frame to an anonymous 3D skeleton keeps only the motion cues needed for HAR while removing faces, clothing, and scene details. We extend SwinPoseFormer, a transformer that operates on skeleton heatmaps beyond its original FineGym benchmark to two larger and more varied datasets: Kinetics-400 and NTU-RGB+D 120. Using the same lightweight pipeline (incorporating uniform temporal sampling, subject-centred cropping, Gaussian joint and limb heatmaps generation, and a single-channel input strategy), the model achieves 78.3% / 98.7% top-1 / top-5 accuracy on Kinetics-400 and 74.0% / 98.0% on NTU-120, compared to 84.3% / 98.5% on FineGym. The stable top-5 scores demonstrate strong cross-dataset generalization without leaking visual identity. These results show that privacy-preserving skeleton streams captured by inexpensive IoT cameras can support reliable, real-time HAR across a broad range of daily activities.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.007
Threshold uncertainty score0.016

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0050.003

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.059
GPT teacher head0.330
Teacher spread0.271 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2025
Admission routes2
Has abstractyes

Explore more

Same venueProcedia Computer ScienceSame topicHuman Pose and Action RecognitionFrench-language works237,207