Revisiting Image-Language Networks for Open-ended Phrase Detection

Plummer Bryan A.
Plummer Bryan A.
Shih Kevin J.
Shih Kevin J.
Xu Ke
Xu Ke

IEEE transactions on pattern analysis and machine intelligence, pp. 1-1, 2019.

Cited by: 6|Bibtex|Views44|DOI:https://doi.org/10.1109/TPAMI.2020.3029008
WOS
Other Links: arxiv.org|pubmed.ncbi.nlm.nih.gov|academic.microsoft.com

Abstract:

Most existing work that grounds natural language phrases in images starts with the assumption that the phrase in question is relevant to the image. In this paper we address a more realistic version of the natural language grounding task where we must both identify whether the phrase is relevant to an image \textbf{and} localize the phrase...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments