On the Limitations of Visual-Semantic Embedding Networks for Image-to-Text Information Retrieval _ Enhanced Reader.pdf (9.52 MB)
On the limitations of visual-semantic embedding networks for image-to-text information retrieval
journal contribution
posted on 2021-08-02, 10:35 authored by Yan Gong, Georgina CosmaGeorgina Cosma, Hui FangHui FangVisual-semantic embedding (VSE) networks create joint image–text representations to map images and texts in a shared embedding space to enable various information retrieval-related tasks, such as image–text retrieval, image captioning, and visual question answering. The most recent state-of-the-art VSE-based networks are: VSE++, SCAN, VSRN, and UNITER. This study evaluates the performance of those VSE networks for the task of image-to-text retrieval and identifies and analyses their strengths and limitations to guide future research on the topic. The experimental results on Flickr30K revealed that the pre-trained network, UNITER, achieved 61.5% on average Recall@5 for the task of retrieving all relevant descriptions. The traditional networks, VSRN, SCAN, and VSE++, achieved 50.3%, 47.1%, and 29.4% on average Recall@5, respectively, for the same task. An additional analysis was performed on image–text pairs from the top 25 worst-performing classes using a subset of the Flickr30K-based dataset to identify the limitations of the performance of the best-performing models, VSRN and UNITER. These limitations are discussed from the perspective of image scenes, image objects, image semantics, and basic functions of neural networks. This paper discusses the strengths and limitations of VSE networks to guide further research into the topic of using VSE networks for cross-modal information retrieval tasks.
History
School
- Science
Department
- Computer Science
Published in
Journal of ImagingVolume
7Issue
8Publisher
MDPI AGVersion
- VoR (Version of Record)
Rights holder
© The AuthorsPublisher statement
This is an Open Access Article. It is published my MDPI under the Creative Commons Attribution 4.0 International Licence (CC BY 4.0). Full details of this licence are available at: https://creativecommons.org/licenses/by/4.0/Acceptance date
2021-07-23Publication date
2021-07-26Copyright date
2021eISSN
2313-433XPublisher version
Language
- en
Depositor
Dr Georgina Cosma. Deposit date: 27 July 2021Article number
125Usage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC