Video captioning based on dual learning via multiple reconstruction blocks.
Bahy Helmi Hartoyo PutraCheol JeongPublished in: Image Vis. Comput. (2024)
Keyphrases
- learning process
- multiple tasks
- learning scenarios
- multimedia
- video sequences
- active learning
- learning algorithm
- unsupervised learning
- learning systems
- learning tasks
- online learning
- interactive video
- combining multiple
- learning community
- learning analytics
- supervised learning
- prior knowledge
- three dimensional
- e learning
- computer vision