nocaps: novel object captioning at scale

    Karan Desai
    Karan Desai
    Yufei Wang
    Yufei Wang
    Rishabh Jain
    Rishabh Jain
    Mark Johnson
    Mark Johnson

    pp. 8948-8957, 2019.

    Cited by: 2|Bibtex|Views46|

    Abstract:

    Image captioning models have achieved impressive results on datasets containing limited visual concepts and large amounts of paired image-caption training data. However, if these models are to ever function in the wild, a much larger variety of visual concepts must be learned, ideally from less supervision. To encourage the development ...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments