Video Description Generation Method Based on Latent Feature Augmented Network
Video description generation aims to use natural language to describe objects and their interactions in videos. The existing methods do not fully utilize the spatio-temporal semantic information in videos, which limits the model's ability to generate accurate descriptive statements. To this end, a L...
Tallennettuna:
| Päätekijä: | |
|---|---|
| Aineistotyyppi: | Artigo |
| Kieli: | Inglês |
| Julkaistu: |
Editorial Office of Computer Engineering
2024-02-01
|
| Sarja: | Jisuanji gongcheng |
| Aiheet: | |
| Linkit: | https://www.ecice06.com/fileup/1000-3428/PDF/20240229.pdf |
| Tagit: |
Ei tageja, Lisää ensimmäinen tagi!
|