Long-Term Feature Banks for Detailed Video Understanding

    CVPR, Volume abs/1812.05038, 2019, Pages 284-293.

    Cited by: 65|Bibtex|Views207|Links
    EI

    Abstract:

    To understand the world, we humans constantly need to relate the present to the past, and put events in context. In this paper, we enable existing video models to do the same. We propose a long-term feature bank---supportive information extracted over the entire span of a video---to augment state-of-the-art video models that otherwise wou...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments