Please use this identifier to cite or link to this item: http://thuvienso.dut.udn.vn/handle/DUT/6181
Title: Enhanced attention-based multimodal Deep Learning for product categorization on E-commerce platform
Authors: Lê, Việt Hưng
Keywords: Enhanced Attention-based;Deep Learning;E-commerce platform
Issue Date: 2024
Publisher: Trường Đại học Bách khoa - Đại học Đà Nẵng
Abstract: 
Labeling and classifying a large number of products is one of the key challenges that ecommerce managers face. Building an automatic model that can accurately classify
products helps to optimize the consumer search experience and ensure that they can
easily find the products that meet their needs. In this study, we propose an improved
Multimodal Deep Learning Model, based on the attention mechanism. This model has
the ability to significantly improve accuracy over both traditional Unimodal Deep
Learning and Multimodal Deep Learning models. The accuracy of our proposed model
reaches 91.18% in classifying 16 different product categories. Meanwhile, traditional
Multimodal Deep Learning models only achieved a modest accuracy of 77.21%. This
result not only improves the searchability and online shopping experience of consumers,
but also makes a significant contribution to solving the challenge of product
classification on e-commerce platforms
Description: 
52 tr.
URI: http://thuvienso.dut.udn.vn/handle/DUT/6181
Appears in Collections:DA.Khoa học dữ liệu - Trí tuệ nhân tạo

Files in This Item:
File Description SizeFormat
4.TI.24.979.LEVIETHUNG.pdfThuyết minh2.06 MBAdobe PDFThumbnail
View/Open
Show full item record

CORE Recommender

Page view(s)

5
checked on Jun 7, 2025

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.