Spatially Time-Based Robust Tracking and Re-Identification of Kindergarten Students: A Hybrid Deep Learning Framework Combining YOLOv8n and Vision Transformer (ViT)

Md. Rahatul Islam, Yui Kataoka, Keisuke Teramoto, Keiichi Horio

Open source

DOI
10.3390/jimaging12040150
Published
2026-03-30
Container
Journal of Imaging
Publisher
MDPI AG
Open access
unknown

Credibility signals

uncertain Score 64/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.3390/jimaging12040150,
  title = {Spatially Time-Based Robust Tracking and Re-Identification of Kindergarten Students: A Hybrid Deep Learning Framework Combining YOLOv8n and Vision Transformer (ViT)},
  author = {Md. Rahatul Islam and Yui Kataoka and Keisuke Teramoto and Keiichi Horio},
  year = {2026},
  journal = {Journal of Imaging},
  doi = {10.3390/jimaging12040150},
  url = {https://doi.org/10.3390/jimaging12040150}
}

RIS

TY  - JOUR
TI  - Spatially Time-Based Robust Tracking and Re-Identification of Kindergarten Students: A Hybrid Deep Learning Framework Combining YOLOv8n and Vision Transformer (ViT)
AU  - Md. Rahatul Islam
AU  - Yui Kataoka
AU  - Keisuke Teramoto
AU  - Keiichi Horio
PY  - 2026
JO  - Journal of Imaging
DO  - 10.3390/jimaging12040150
UR  - https://doi.org/10.3390/jimaging12040150
ER  - 

APA

Islam, M. R., Kataoka, Y., Teramoto, K., & Horio, K. (2026). Spatially Time-Based Robust Tracking and Re-Identification of Kindergarten Students: A Hybrid Deep Learning Framework Combining YOLOv8n and Vision Transformer (ViT). Journal of Imaging. https://doi.org/10.3390/jimaging12040150

Source records