Data

Tools

Indexes

Applications

Experiments

Open Source Science

dynamically-gated-similarities

Code for Thesis: "Multi-Person Pose Tracking using Dynamically Gated Similarities"

https://github.com/bmmtstb/dynamically-gated-similarities

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 7 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.7%) to scientific vocabulary

Keywords

human-pose-tracking tracking
Last synced: 6 months ago · JSON representation ·

Repository

Code for Thesis: "Multi-Person Pose Tracking using Dynamically Gated Similarities"

Basic Info
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 1
  • Releases: 10
Topics
human-pose-tracking tracking
Created over 2 years ago · Last pushed 6 months ago
Metadata Files
Readme License Citation

README.md

Coverage Run CI Deploy Docs DOI

Dynamically Gated Similarities

This is the code for the Thesis "Multi-Person Pose Tracking using Dynamically Gated Similarities", available here (or see: ./thesis.pdf).

Documentation

You can find the extended Documentation over at https://bmmtstb.github.io/dynamically-gated-similarities/.

Pipeline

You can find a visual Pipeline on LucidChart or downloadable as PDF (or see: ./docs/figures/Pipeline-DGS-Overview.pdf). The visual pipeline of the training module is also available as PDF (or see: ./docs/figures/Pipeline-DGS-Training.pdf).

Examples

| pt21__val__012968_mpii_test__prediction | |:--:| | pt21val012968mpiitest__prediction |

| dance__test__dancetrack0017__prediction | |:--:| | dancetestdancetrack0017__prediction |

Citing

To cite this thesis, you can use the following BibTeX entry:

bibtex @mastersthesis{tuprints29468, title = {Multi-Person Pose Tracking Using Dynamically Gated Similarities}, author = {Martin Steinborn}, school = {Technische Universit{\"a}t Darmstadt}, language = {en}, address = {Darmstadt}, year = {2025}, pages = {VII, 56 Seiten}, month = {M{\"a}rz}, url = {http://tuprints.ulb.tu-darmstadt.de/29468/}, doi = {https://doi.org/10.26083/tuprints-00029468}, keywords = {tracking, pose-tracking, mppt} }

To cite the code, you can use the following BibTeX entry:

bibtex @software{brizar_2025_14910547, author = {Brizar}, title = {bmmtstb/dynamically-gated-similarities}, month = feb, year = 2025, publisher = {Zenodo}, version = {v0.3.0}, doi = {10.5281/zenodo.14910547}, url = {https://doi.org/10.5281/zenodo.14910547}, }

This code is based on works of other people as well. Please refer to the respective repositories for citing.

Owner

  • Name: Brizar
  • Login: bmmtstb
  • Kind: user

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: dynamically-gated-similarities
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Martin
    family-names: Steinborn
    email: bmmartint.stb+cffinit@gmail.com
    orcid: 'https://orcid.org/0009-0000-5694-6231'
identifiers:
  - type: doi
    value: 10.26083/tuprints-00029468
    description: Master Thesis
repository-code: 'https://github.com/bmmtstb/dynamically-gated-similarities'
url: 'https://bmmtstb.github.io/dynamically-gated-similarities/'
abstract: >-
  This is the code for the Thesis “Multi-Person Pose
  Tracking using Dynamically Gated Similarities”.


  We proposed a new model that uses dynamically learned
  weights to combine the pose, appearance, and or other
  information. The so-called Dynamically-Gated Similarities
  (DGS) model is highly modular and customizable. Weights
  can be used and trained mostly dataset independent.
  Additionally, the weights are computed individually for
  every detection, allowing the model to adapt more freely
  to the current situation.
keywords:
  - human pose tracking
  - tracking
license: MIT
commit: d04eb1b
version: ' v0.3.0'

GitHub Events

Total
  • Release event: 2
  • Delete event: 1
  • Push event: 37
  • Pull request event: 2
  • Create event: 1
Last Year
  • Release event: 2
  • Delete event: 1
  • Push event: 37
  • Pull request event: 2
  • Create event: 1

Issues and Pull Requests

Last synced: almost 2 years ago

All Time
  • Total issues: 2
  • Total pull requests: 2
  • Average time to close issues: N/A
  • Average time to close pull requests: about 13 hours
  • Total issue authors: 1
  • Total pull request authors: 1
  • Average comments per issue: 0.0
  • Average comments per pull request: 2.0
  • Merged pull requests: 2
  • Bot issues: 0
  • Bot pull requests: 2
Past Year
  • Issues: 2
  • Pull requests: 2
  • Average time to close issues: N/A
  • Average time to close pull requests: about 13 hours
  • Issue authors: 1
  • Pull request authors: 1
  • Average comments per issue: 0.0
  • Average comments per pull request: 2.0
  • Merged pull requests: 2
  • Bot issues: 0
  • Bot pull requests: 2
View more stats
Top Authors
Issue Authors
  • bmmtstb (1)
Pull Request Authors
  • dependabot[bot] (4)
Top Labels
Issue Labels
enhancement (1)
Pull Request Labels
dependencies (4) github_actions (4)

Dependencies

requirements.txt pypi
  • Pillow *
  • av *
  • black *
  • coverage *
  • cython ==3.0.
  • easydict *
  • future *
  • gdown *
  • h5py *
  • imageio *
  • imagesize *
  • jinja2 *
  • matplotlib *
  • munkres *
  • natsort *
  • ninja *
  • numpy *
  • opencv-python *
  • pycocotools ==2.0.
  • pylint *
  • pyyaml ==6.0.
  • scipy *
  • sphinx *
  • tb-nightly *
  • torcheval *
  • tqdm *
  • visdom *
.github/workflows/coverage.yaml actions
  • orgoro/coverage v3.1 composite
pyproject.toml pypi
.github/workflows/ci.yaml actions
  • actions/checkout v4 composite
  • actions/setup-python v4 composite
.github/workflows/wiki.yaml actions
  • sphinx-notes/pages v3 composite
docs/requirements_docs.txt pypi
  • easydict *
  • numpy *
  • pyyaml *
  • scipy *
  • sphinx *
  • terminaltables *
  • torch *
tests/requirements_test.txt pypi
  • black * test
  • easydict * test
  • munkres * test
  • natsort * test
  • numpy * test
  • opencv-python * test
  • pylint * test
  • pyyaml * test
  • scipy * test
  • terminaltables * test
  • torch * test
  • tqdm * test
  • visdom * test