Pre-trained CNNs as Feature-Extraction Modules for Image Captioning

Pre-trained CNNs as Feature-Extraction Modules for Image Captioning

In this work, we present a thorough experimental study about feature extraction using Convolutional Neural Networks (CNNs) for the task of image captioning in the context of deep learning. We perform a set of 72 experiments on 12 image classification CNNs pre-trained on the ImageNet [29] dataset. T...

Full description

Bibliographic Details
Main Authors: Muhammad Abdelhadie Al-Malla, Assef Jafar, Nada Ghneim
Format: Article
Language:English
Published: Computer Vision Center Press 2022-05-01
Series:ELCVIA Electronic Letters on Computer Vision and Image Analysis
Subjects:
Convolutional Neural Network
Feature Extraction
Image Captioning
Deep Learning
Online Access:https://elcvia.cvc.uab.cat/article/view/1436

Internet

https://elcvia.cvc.uab.cat/article/view/1436

Similar Items