HIGHLIGHTS
- who: Combining Unsupervised and collaborators from the University of Essex, United Kingdom have published the research: Combining Unsupervised and Supervised Learning for Sample Ef cient Continuous Language Grounding, in the Journal: (JOURNAL)
- what: This study proposes and evaluates a hybrid grounding framework that combines both paradigms. The approach proposed in Roesler (2020b) has been chosen for the unsupervised grounding component because it was able to ground actions, shapes, and colors more accurately and faster than probabilistic model based approaches, while also being able to successfully handle synonyms.
- how: The results showed that two . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.