Authors: Obeida ElJundi, Mohamad Dhaybi, Kotaiba Mokadam, Hazem Hajj, and Daniel Asmar
{oae15, mad45, kam38, hh63, da20}@aub.edu.lb
Introduction
Image Captioning refers to the art of describing the content of an image by computers. It is a well-known problem in CV and NLP. It has many applications, such as improved information retrieval, early childhood education, for visually impaired persons, for social media, and so on. Although remarkable work has been accomplished recently for English, and due to the lack of large and publicly available datasets, the progress on Arabic Image Captioning is still lagging. Therefore, we developed our own dataset based on Flickr8K. It can be found under data/Flickr8k_text/ folder, named Flickr8k.arabic.full.txt. It has the exact same format as the original Flickr8K.
Paper: here
Dataset: ./data/Flickr8k_text/Flickr8k.arabic.full.txt
Presentation: here
Model
Inspired by recent advances in neural machine translation, the sequence-to-sequence encoder-decoder approach was adopted here. For more details, please check the paper.
Results
Results show that developing language specific datasets and end-to-end models outperforms translating English generated captions to a destination language as the later may accumulate both models errors: image captioning and translation.
Citation
Please cite this paper:
@conference{visapp20,
author={Obeida ElJundi. and Mohamad Dhaybi. and Kotaiba Mokadam. and Hazem Hajj. and Daniel Asmar.},
title={Resources and End-to-End Neural Network Models for Arabic Image Captioning},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2020},
pages={233-241},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008881202330241},
isbn={978-989-758-402-2},
}
Contact information
For help, issues, or personal communication related to this work, please contact Obeida ElJundi: oae15@mail.aub.edu
Many thanks for the great posting. I am glad I have taken the time to see this. IGNOU Project
I like this site because so much useful stuff on here : D. digital marknadsföringsbyrå
You created some decent points there. I looked over the internet for your issue and discovered most people will go along with together with your site. https://pg-slot.review/
This is the correct blog for anybody who would like to learn about this topic. You are aware of a lot its virtually challenging to argue on hand (not that I actually would want…HaHa). You actually put the latest spin over a topic thats been revealed for many years. Fantastic stuff, just fantastic! basement walkout construction
Most heavy duty trailer hitches are designed using cutting edge computer aided models and fatigue stress testing to ensure optimal strength. Share new discoveries with your child and keep your child safe by purchasing the correct design for your lifestyle by following the Perfect Stroller Buyers Guideline. 부산 고구려
There is noticeably big money to understand about this. I suppose you made particular nice points in features also. trekking near bangalore
Hey there, You have done an incredible job. I’ll certainly digg it and personally suggest to my friends. I’m confident they’ll be benefited from this site. facebook video downloader
Real clear website , regards for this post. 슬롯사이트
I’m finding your blog an incredibly helpful resource for learning to read the Quran correctly. The detailed explanations and practical examples are greatly appreciated. Noorani Qaida lesson 13, with its focus on exercises, has been particularly useful in reinforcing what I’ve learned. Thank you!
This article is really amazing i hope we will see again this type of article in future..
E-ZPassNJ