← Search

M. Hadi Kiapour

2 accepted papers

2018

Conditional Image-Text Embedding Networks

ECCV 2018poster

This paper presents an approach for grounding phrases in images which jointly learns multiple text-conditioned embeddings in a single end-to-end model. In order to differentiate text phrases into semantically distinct subspaces, we propose a concept weight branch that automatically assigns phrases t…

2015

Where to Buy It: Matching Street Clothing Photos in Online Shops

ICCV 2015oral

In this paper, we define a new task, Exact Street to Shop, where our goal is to match a real-world example of a garment item to the same item in an online shop. This is an extremely challenging task due to visual differences between street photos (pictures of people wearing clothing in everyday unco…

Cited by 578PDFScholar