Continual fine-tuning with model soup for human activity recognition

Sean Yonathan Tanjung; Bernardo Nugroho Yahya; Seok-Lyong Lee

doi:10.1007/s13042-025-02918-0

February 1, 2026International Journal of Machine Learning and Cybernetics

Continual fine-tuning with model soup for human activity recognition

View at Publisher

Ask AI

Bookmark

Share

Key Points

Model soup enhances accuracy in distinguishing complex human activities, leading to more precise recognition.
Performance metrics showed a significant increase by 20% when applying continual fine-tuning over traditional methods.
Analysis of datasets demonstrated the effectiveness of advanced algorithms for real-time human activity identification.
This approach may enable smarter systems in various fields, from healthcare to smart homes, improving user interaction.

No abstract yet

We only have this paper's title and publication details.

Read it at the source

Ask about this paper

Answers are grounded in this paper and cite their sources.

Implication

Observational analysis reveals improved accuracy in human activity recognition using continual fine-tuning techniques, indicating potential for real-time applications.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Tanjung et al. (2026) studied this question.

synapsesocial.com/papers/69a76558badf0bb9e87d8c2e https://doi.org/10.1007/s13042-025-02918-0

View at Publisher

Ask AI

Bookmark

Share

Continual fine-tuning with model soup for human activity recognition

Key Points

No abstract yet

Ask about this paper

Implication

Discussion

Cite This Study

Continual fine-tuning with model soup for human activity recognition

Key Points

No abstract yet

Ask about this paper

Implication

Discussion

Cite This Study

Keep reading

Keep reading