Learning structured video descriptions: Automated video knowledge extraction for video understanding tasks
Vision to language problems, such as video annotation, or visual question answering, stand out from the perceptual video understanding tasks (e.g., classification) through their cognitive nature and their tight connection to the field of natural language processing. While most of the current solutio...
| Main Authors: | , |
|---|---|
| Format: | Conference item |
| Published: |
Springer
2018
|