Cargando…
Video captioning based on vision transformer and reinforcement learning
Global encoding of visual features in video captioning is important for improving the description accuracy. In this paper, we propose a video captioning method that combines Vision Transformer (ViT) and reinforcement learning. Firstly, Resnet-152 and ResNeXt-101 are used to extract features from vid...
| Autores principales: | , , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
PeerJ Inc.
2022
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9044334/ https://www.ncbi.nlm.nih.gov/pubmed/35494808 http://dx.doi.org/10.7717/peerj-cs.916 |