Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Soravit Changpinyo

Soravit Changpinyo

Connecting Vision and Language with Video Localized Narratives

Mar 15, 2023
Paul Voigtlaender, Soravit Changpinyo, Jordi Pont-Tuset, Radu Soricut, Vittorio Ferrari

Figure 1 for Connecting Vision and Language with Video Localized Narratives

Figure 2 for Connecting Vision and Language with Video Localized Narratives

Figure 3 for Connecting Vision and Language with Video Localized Narratives

Figure 4 for Connecting Vision and Language with Video Localized Narratives

* Accepted at CVPR 2023

Access Paper or Ask Questions

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

Feb 24, 2023
Yang Chen, Hexiang Hu, Yi Luan, Haitian Sun, Soravit Changpinyo, Alan Ritter, Ming-Wei Chang

Figure 1 for Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?

Figure 2 for Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?

Figure 3 for Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?

Figure 4 for Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?

* Our dataset and evaluation is available at https://open-vision-language.github.io/infoseek/

Access Paper or Ask Questions

All You May Need for VQA are Image Captions

May 04, 2022
Soravit Changpinyo, Doron Kukliansky, Idan Szpektor, Xi Chen, Nan Ding, Radu Soricut

Figure 1 for All You May Need for VQA are Image Captions

Figure 2 for All You May Need for VQA are Image Captions

Figure 3 for All You May Need for VQA are Image Captions

Figure 4 for All You May Need for VQA are Image Captions

* 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022)

Access Paper or Ask Questions