the open
    research
    Contribute
    Back to the reading lists

    Computer vision & multimodal· 2017

    Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

    Peter Anderson (first author) · 2017 · published 2018

    Read the original

    DOI 10.1109/cvpr.2018.00636arXiv 1707.07998OpenAlex W2745461083

    On the reading lists

    Why it matters

    Established object-region features as standard inputs for captioning and early vision-language Transformers.

    Condensed from the expert lists' notes.

    The record

    First released
    2017 (from arXiv 1707.07998)
    Published
    2018
    Citations
    5,119 citations, as counted by OpenAlex (CC0)
    Named by
    both expert lists
    Score
    0.477 · computed rank 264 · consensus 0.82, must-read 0.5, citations percentile 0.518 (2010s · vision), awards 0, existing lists 0. Method

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.