FLcode-lab/DADPFed-Code: DADPFed v1.0.0: Code for "Drift-Aware Dynamic Pruning: A Stabilising Heuristic for Heterogeneous Federated Action Recognition"

Fuente: Zenodo
Saved in:
Bibliographic Details
Main Author: FLcode-lab
Format: Recurso digital
Published: Zenodo 2026
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901078494150656
author FLcode-lab
author_facet FLcode-lab
contents <p>This is the official code release accompanying the manuscript submitted to <em>The Visual Computer</em>.</p> <h2>Repository Overview</h2> <ul> <li><strong>Paper Title</strong>: Drift-Aware Dynamic Pruning: A Stabilising Heuristic for Heterogeneous Federated Action Recognition</li> <li><strong>Journal</strong>: The Visual Computer</li> <li><strong>Authors</strong>: Zhihao Liu, Wei Guo, Jie Wu, Mengke Zhu, Jiamin Liang</li> </ul> <h2>Contents</h2> <ul> <li>Full implementation of DADPFed framework</li> <li>Training/evaluation scripts for federated action recognition</li> <li>Subset construction, split files, and preprocessing pipelines for martial-arts video benchmarks</li> <li>Detailed README with environment setup and reproduction commands</li> </ul> <h2>Citation</h2> <p>If you use this code in your research, please cite our manuscript: Zhihao Liu, Wei Guo, Jie Wu, Mengke Zhu, Jiamin Liang. Drift-Aware Dynamic Pruning: A Stabilising Heuristic for Heterogeneous Federated Action Recognition. <em>The Visual Computer</em>, 2025.</p> <h2>Data Note</h2> <p>Raw video data is derived from public benchmarks (Kinetics-MA, UCF101-MA). Due to copyright constraints, raw videos are not included; all subset construction and preprocessing scripts are provided for full reproducibility.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19325591
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle FLcode-lab/DADPFed-Code: DADPFed v1.0.0: Code for "Drift-Aware Dynamic Pruning: A Stabilising Heuristic for Heterogeneous Federated Action Recognition"
FLcode-lab
<p>This is the official code release accompanying the manuscript submitted to <em>The Visual Computer</em>.</p> <h2>Repository Overview</h2> <ul> <li><strong>Paper Title</strong>: Drift-Aware Dynamic Pruning: A Stabilising Heuristic for Heterogeneous Federated Action Recognition</li> <li><strong>Journal</strong>: The Visual Computer</li> <li><strong>Authors</strong>: Zhihao Liu, Wei Guo, Jie Wu, Mengke Zhu, Jiamin Liang</li> </ul> <h2>Contents</h2> <ul> <li>Full implementation of DADPFed framework</li> <li>Training/evaluation scripts for federated action recognition</li> <li>Subset construction, split files, and preprocessing pipelines for martial-arts video benchmarks</li> <li>Detailed README with environment setup and reproduction commands</li> </ul> <h2>Citation</h2> <p>If you use this code in your research, please cite our manuscript: Zhihao Liu, Wei Guo, Jie Wu, Mengke Zhu, Jiamin Liang. Drift-Aware Dynamic Pruning: A Stabilising Heuristic for Heterogeneous Federated Action Recognition. <em>The Visual Computer</em>, 2025.</p> <h2>Data Note</h2> <p>Raw video data is derived from public benchmarks (Kinetics-MA, UCF101-MA). Due to copyright constraints, raw videos are not included; all subset construction and preprocessing scripts are provided for full reproducibility.</p>
title FLcode-lab/DADPFed-Code: DADPFed v1.0.0: Code for "Drift-Aware Dynamic Pruning: A Stabilising Heuristic for Heterogeneous Federated Action Recognition"
url https://doi.org/10.5281/zenodo.19325591