Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.14948595 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p>This dataset accompanies the research paper <em>"Hybrid Approaches to Dynamic Image Style Transfer for Aesthetic Innovation"</em>. It includes content images, style images, and experimental results related to neural style transfer. The dataset is structured as follows:</p> <ul> <li><strong>Content_Images/</strong> – Contains 17 images used as content inputs for style transfer.</li> <li><strong>Style_Images/</strong> – Contains 16 images representing artistic styles applied to the content images.</li> <li><strong>Results_and_Discussions/</strong> – Includes: <ul> <li><em>Fig. 8 – Total Loss on Iterations:</em> A graphical representation of the loss values over multiple iterations.</li> <li><em>Table 2 – Total Loss Values for Foreground and Background:</em> Numerical loss data for both foreground and background across multiple iterations.</li> <li><em>Google Colab Output of Table 2:</em> Execution logs and loss data from the experiment.</li> </ul> </li> </ul> <h3><strong>Usage Notes</strong></h3> <p>This dataset can be used for research and development in neural style transfer, deep learning-based image transformation, and aesthetic enhancement techniques. It provides insights into loss progression over iterations, helping researchers analyze the effectiveness of different style transfer approaches.</p>