Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.14747847 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866901051936866304 |
|---|---|
| author | Dr. A. Naresh J. Ayesha N. Ganga Devi J. Thasneem Khanam |
| author_facet | Dr. A. Naresh J. Ayesha N. Ganga Devi J. Thasneem Khanam |
| contents | <p>One of the great achievements of AI is text to video generation which allows production of high-quality videos based on descriptions in natural language. Since constrained text is the input to the creation of short and high-quality films, this research proposes a deep learning approach that incorporates both GAN and VAE attributes. Static attributes make layouts and backgrounds, while change is created through text. A new procedure also addresses data scarcity issues by automatically creating corresponding text-video datasets from the web. From experimental results, the improvement of video outputs compared to baseline models is accurate as well as diverse. This paper also uses evaluations to affirm the success of the framework which includes visual assessments and an inception score with slight modifications made to it. This work presents practical implications for AI-generated multimedia content, as it advances text-to-video synthesis.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_14747847 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Leveraging AI for Automated Text-to-Video Generation: Advances and Application Dr. A. Naresh J. Ayesha N. Ganga Devi J. Thasneem Khanam <p>One of the great achievements of AI is text to video generation which allows production of high-quality videos based on descriptions in natural language. Since constrained text is the input to the creation of short and high-quality films, this research proposes a deep learning approach that incorporates both GAN and VAE attributes. Static attributes make layouts and backgrounds, while change is created through text. A new procedure also addresses data scarcity issues by automatically creating corresponding text-video datasets from the web. From experimental results, the improvement of video outputs compared to baseline models is accurate as well as diverse. This paper also uses evaluations to affirm the success of the framework which includes visual assessments and an inception score with slight modifications made to it. This work presents practical implications for AI-generated multimedia content, as it advances text-to-video synthesis.</p> |
| title | Leveraging AI for Automated Text-to-Video Generation: Advances and Application |
| url | https://doi.org/10.5281/zenodo.14747847 |