0

Soravit Changpinyo

Papers
4

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
4papers

Authored papers

4

What You See is What You Read? Improving Text-Image Alignment Evaluation

what-you-see-is-what-you-read-improving-text

2023

Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?

arXiv 2023

2023

Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts

CVPR 2021 1

2021

Connecting Vision and Language with Localized Narratives

ECCV 2020 8

2019

Affiliations

No known affiliations.

Frequent co-authors

10

from 4 papers

Radu Soricut

2 shared papers

Alan Ritter

1 shared paper

Eran Ofek

1 shared paper

Haitian Sun

1 shared paper

Hexiang Hu

1 shared paper

Idan Szpektor

1 shared paper

Jasper Uijlings

1 shared paper

Jonathan Herzig

1 shared paper

Jordi Pont-Tuset

1 shared paper

Michal Yarom

1 shared paper