Large-scale image search with text for information retrieval

Authors

  • Janardan Bhatta

DOI:

https://doi.org/10.3126/jiee.v4i1.35390

Keywords:

Computer vision, Attention mechanism, Contrastive loss function, Natural language processing, Information retrieval systems

Abstract

Searching images in a large database is a major requirement in Information Retrieval Systems. Expecting image search results based on a text query is a challenging task. In this paper, we leverage the power of Computer Vision and Natural Language Processing in Distributed Machines to lower the latency of search results. Image pixel features are computed based on contrastive loss function for image search. Text features are computed based on the Attention Mechanism for text search. These features are aligned together preserving the information in each text and image feature. Previously, the approach was tested only in multilingual models. However, we have tested it in image-text dataset and it enabled us to search in any form of text or images with high accuracy.

Downloads

Download data is not yet available.
Abstract
54
PDF
51

Downloads

Published

2021-03-05

How to Cite

Bhatta, J. (2021). Large-scale image search with text for information retrieval. Journal of Innovations in Engineering Education, 4(1), 87–89. https://doi.org/10.3126/jiee.v4i1.35390

Issue

Section

Articles