app_config.py

ckpt_path = 'checkpoints/epoch_20'
CONTENT = '''
<h2 style="text-align: center;">Deep Exemplar-based Video Colorization using Vision Transformer</h3>
<p style="text-align: center;">
    <a href="https://github.com/Chronopt-Research/video_colorization">GitHub</a> | <a href="">Report</a> | <a href="https://2023.ictc.org/program_proceeding#:~:text=Vitexco%3A%20Exemplar%2Dbased%20Video%20Colorization%20using%20Vision%20Transformer">Paper</a>
</p>

# Demo
'''

APPENDIX = '''
---

# Appendix

## What is Exemplar-based Video Colorization?

Exemplar-based video colorization is a technique used to add color to black-and-white or monochrome videos. It leverages the concept of exemplars, which are reference images that contain color information similar to the target video frames. By analyzing the exemplars and the target frames, the colorization algorithm transfers the colors from the exemplars to the corresponding regions in the target frames.

Our proposed model represents a significant advancement in video colorization technology. By harnessing the potential of the Vision Transformer architecture, specifically the Swin Transformer variant, we have established a state-of-the-art solution that combines exceptional speed optimization with the generation of colorful and vivid videos. The benchmark results are shown in the "Report" above.

## Achievements & Publications
- We won the 🥈 **The First Runner-up Award** in the [FPT Research Festival HCMC 2023]().
- We won the 🏆 **The Champion Award** in the FPT Research Festival Edu 2023.
- We published 📝 an accepted paper in the **ICTC 2023** conference.

## Citation
If you find our work useful in your research, please consider citing:
```
@INPROCEEDINGS{duong2023vitexco,
  author={Tran, Duong Thanh and Nguyen, Nguyen Doan Hieu and Pham, Trung Thanh and Tran, Phuong-Nam and Vu, Thuy-Duong Thi and Dang, Duc Ngoc Minh},
  booktitle={2023 14th International Conference on Information and Communication Technology Convergence (ICTC)}, 
  title={Vitexco: Exemplar-based Video Colorization using Vision Transformer}, 
  year={2023},
  volume={},
  number={},
  pages={59-64},
  doi={},
}
```
'''