Pith. sign in

Bottom-up and top-down attention for image captioning and visual question answering

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2019 1

verdicts

CONDITIONAL 1

representative citing papers

Scene-based Factored Attention for Image Captioning

cs.CV · 2019-08-07 · conditional · novelty 4.0

A scene-conditioned factored attention module, which multiplies attention weights by the image's predicted scene vector, improves MS COCO captioning scores over an Up-Down re-implementation.

citing papers explorer

Showing 1 of 1 citing paper.

  • Scene-based Factored Attention for Image Captioning cs.CV · 2019-08-07 · conditional · none · ref 2

    A scene-conditioned factored attention module, which multiplies attention weights by the image's predicted scene vector, improves MS COCO captioning scores over an Up-Down re-implementation.