Search Results for author: Doron Kukliansky

Found 2 papers, 1 papers with code

All You May Need for VQA are Image Captions

2 code implementations • NAACL 2022 • Soravit Changpinyo, Doron Kukliansky, Idan Szpektor, Xi Chen, Nan Ding, Radu Soricut

Visual Question Answering (VQA) has benefited from increasingly sophisticated models, but has not enjoyed the same level of engagement in terms of data creation.

Image Captioning Question Answering +3

1,070

Paper
Code

Attribute Efficient Linear Regression with Data-Dependent Sampling

no code implementations • 23 Oct 2014 • Doron Kukliansky, Ohad Shamir

In this paper we analyze a budgeted learning setting, in which the learner can only choose and observe a small subset of the attributes of each training example.

Attribute regression

Paper
Add Code

Cannot find the paper you are looking for? You can Submit a new open access paper.