Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/29495
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Tsapatsoulis, Nicolas | - |
dc.date.accessioned | 2023-06-26T08:59:30Z | - |
dc.date.available | 2023-06-26T08:59:30Z | - |
dc.date.issued | 2022-09-07 | - |
dc.identifier.citation | SETN '22: Proceedings of the 12th Hellenic Conference on Artificial Intelligence, 7 - 9 September 2022, Corfu, Greece, pp 1–7 | en_US |
dc.identifier.isbn | 9781450395977 | - |
dc.identifier.uri | https://hdl.handle.net/20.500.14279/29495 | - |
dc.description.abstract | The existence of pre-trained deep learning models for image classification, such as those trained on the well-known Resnet-50 architecture, allows for easy application of transfer learning to several domains including image retrieval. Recently, we proposed topic modelling for the retrieval of Instagram photos based on the associated hashtags. In this paper we compare content-based image classification, based on transfer learning, with the classification based on topic modelling of Instagram hashtags for a set of 24 different concepts. The comparison was performed on a set of 1944 Instagram photos, 81 per concept. Despite the excellent performance of the pre-trained deep learning models, it appears that text-based retrieval, as performed by the topic models of Instagram hashtags, stills perform better. | en_US |
dc.format | en_US | |
dc.language.iso | en | en_US |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 International | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.subject | image classification | en_US |
dc.subject | transfer learning | en_US |
dc.subject | topic modelling | en_US |
dc.subject | deep learning | en_US |
dc.title | Classification of Instagram photos: Topic modelling vs transfer learning | en_US |
dc.type | Conference Papers | en_US |
dc.collaboration | Cyprus University of Technology | en_US |
dc.subject.category | Media and Communications | en_US |
dc.journals | Open Access | en_US |
dc.country | Cyprus | en_US |
dc.subject.field | Social Sciences | en_US |
dc.publication | Peer Reviewed | en_US |
dc.identifier.doi | 10.1145/3549737.3549759 | en_US |
dc.identifier.scopus | 2-s2.0-85138333325 | - |
dc.identifier.url | https://api.elsevier.com/content/abstract/scopus_id/85138333325 | - |
cut.common.academicyear | 2022-2023 | en_US |
dc.identifier.spage | 1 | en_US |
dc.identifier.epage | 7 | en_US |
item.fulltext | With Fulltext | - |
item.openairecristype | http://purl.org/coar/resource_type/c_c94f | - |
item.openairetype | conferenceObject | - |
item.grantfulltext | open | - |
item.languageiso639-1 | en | - |
item.cerifentitytype | Publications | - |
crisitem.author.dept | Department of Communication and Marketing | - |
crisitem.author.faculty | Faculty of Communication and Media Studies | - |
crisitem.author.orcid | 0000-0002-6739-8602 | - |
crisitem.author.parentorg | Faculty of Communication and Media Studies | - |
Appears in Collections: | Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
tsapatsoulis.pdf | full text | 1.16 MB | Adobe PDF | View/Open |
CORE Recommender
Page view(s) 50
141
Last Week
2
2
Last month
3
3
checked on Feb 14, 2025
Download(s) 50
58
checked on Feb 14, 2025
Google ScholarTM
Check
Altmetric
This item is licensed under a Creative Commons License