Dual-Branch Dynamic Graph Convolutional Network for Robust Multi-Label Image Classification Article Swipe

View

Bing Xing Wang , Hongye Zheng , Yingbin Liang , Guanming Huang , Junliang Du ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.55524/ijircst.2024.12.5.13

For the intricate task of multi-label image classification, this paper introduces an innovative approach: an attention-guided dual-branch dynamic graph convolutional network. This methodology is designed to address the difficulties faced by current models when handling multiple labels within images. By integrating multi-scale features, it enhances the retention of original category information and boosts the robustness of feature learning. Utilizing a semantic attention module, the study dynamically reweights feature categories in the training dataset, enhancing the network's capability to identify smaller objects and generate context-sensitive category representations. The effectiveness of the proposed model was evaluated using the MS-COCO2014 imagery dataset, demonstrating superior performance in critical metrics such as classification precision (CP), recall (CR), and F1 score (CF1), outperforming other state-of-the-art models. Furthermore, a cascaded classification structure was implemented to leverage the prior information from static images to inform the processing of dynamic ones, and to utilize original image category data to augment label correlations, thereby enhancing overall classification accuracy.

Related Topics

Computer Science

Artificial Intelligence

Theoretical Computer Science

Literature

Art

Concepts

Computer science Dual (grammatical number) Graph Artificial intelligence Image (mathematics) Pattern recognition (psychology) Theoretical computer science Literature Art

Metadata

Type: article
Language: en
Landing Page: https://doi.org/10.55524/ijircst.2024.12.5.13
OA Status: diamond
Cited By: 13
Related Works: 10
OpenAlex ID: https://openalex.org/W4403488604

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4403488604

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.55524/ijircst.2024.12.5.13

Digital Object Identifier
Title: Dual-Branch Dynamic Graph Convolutional Network for Robust Multi-Label Image Classification

Work title
Type: article

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-09-01

Full publication date if available
Authors: Bing Xing Wang, Hongye Zheng, Yingbin Liang, Guanming Huang, Junliang Du

List of authors in order
Landing page: https://doi.org/10.55524/ijircst.2024.12.5.13

Publisher landing page
Open access: Yes

Whether a free full text is available
OA status: diamond

Open access status per OpenAlex
OA URL: https://doi.org/10.55524/ijircst.2024.12.5.13

Direct OA link when available
Concepts: Computer science, Dual (grammatical number), Graph, Artificial intelligence, Image (mathematics), Pattern recognition (psychology), Theoretical computer science, Literature, Art

Top concepts (fields/topics) attached by OpenAlex
Cited by: 13

Total citation count in OpenAlex
Citations by year (recent): 2025: 4, 2024: 9

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4403488604
doi	https://doi.org/10.55524/ijircst.2024.12.5.13
ids.doi	https://doi.org/10.55524/ijircst.2024.12.5.13
ids.openalex	https://openalex.org/W4403488604
fwci	8.30412114
type	article
title	Dual-Branch Dynamic Graph Convolutional Network for Robust Multi-Label Image Classification
biblio.issue	5
biblio.volume	12
biblio.last_page	99
biblio.first_page	94
topics[0].id	https://openalex.org/T11550
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9519000053405762
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Text and Document Classification Technologies
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.6338222622871399
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C2780980858
concepts[1].level	2
concepts[1].score	0.5690036416053772
concepts[1].wikidata	https://www.wikidata.org/wiki/Q110022
concepts[1].display_name	Dual (grammatical number)
concepts[2].id	https://openalex.org/C132525143
concepts[2].level	2
concepts[2].score	0.538092315196991
concepts[2].wikidata	https://www.wikidata.org/wiki/Q141488
concepts[2].display_name	Graph
concepts[3].id	https://openalex.org/C154945302
concepts[3].level	1
concepts[3].score	0.4532247483730316
concepts[3].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[3].display_name	Artificial intelligence
concepts[4].id	https://openalex.org/C115961682
concepts[4].level	2
concepts[4].score	0.4350818991661072
concepts[4].wikidata	https://www.wikidata.org/wiki/Q860623
concepts[4].display_name	Image (mathematics)
concepts[5].id	https://openalex.org/C153180895
concepts[5].level	2
concepts[5].score	0.3665153384208679
concepts[5].wikidata	https://www.wikidata.org/wiki/Q7148389
concepts[5].display_name	Pattern recognition (psychology)
concepts[6].id	https://openalex.org/C80444323
concepts[6].level	1
concepts[6].score	0.2387685477733612
concepts[6].wikidata	https://www.wikidata.org/wiki/Q2878974
concepts[6].display_name	Theoretical computer science
concepts[7].id	https://openalex.org/C124952713
concepts[7].level	1
concepts[7].score	0.0
concepts[7].wikidata	https://www.wikidata.org/wiki/Q8242
concepts[7].display_name	Literature
concepts[8].id	https://openalex.org/C142362112
concepts[8].level	0
concepts[8].score	0.0
concepts[8].wikidata	https://www.wikidata.org/wiki/Q735
concepts[8].display_name	Art
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.6338222622871399
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/dual
keywords[1].score	0.5690036416053772
keywords[1].display_name	Dual (grammatical number)
keywords[2].id	https://openalex.org/keywords/graph
keywords[2].score	0.538092315196991
keywords[2].display_name	Graph
keywords[3].id	https://openalex.org/keywords/artificial-intelligence
keywords[3].score	0.4532247483730316
keywords[3].display_name	Artificial intelligence
keywords[4].id	https://openalex.org/keywords/image
keywords[4].score	0.4350818991661072
keywords[4].display_name	Image (mathematics)
keywords[5].id	https://openalex.org/keywords/pattern-recognition
keywords[5].score	0.3665153384208679
keywords[5].display_name	Pattern recognition (psychology)
keywords[6].id	https://openalex.org/keywords/theoretical-computer-science
keywords[6].score	0.2387685477733612
keywords[6].display_name	Theoretical computer science
language	en
locations[0].id	doi:10.55524/ijircst.2024.12.5.13
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4210230306
locations[0].source.issn	2347-5552
locations[0].source.type	journal
locations[0].source.is_oa	True
locations[0].source.issn_l	2347-5552
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	International Journal of Innovative Research in Computer Science & Technology
locations[0].source.host_organization
locations[0].source.host_organization_name
locations[0].license
locations[0].pdf_url
locations[0].version	publishedVersion
locations[0].raw_type	journal-article
locations[0].license_id
locations[0].is_accepted	True
locations[0].is_published	True
locations[0].raw_source_name	International Journal of Innovative Research in Computer Science and Technology
locations[0].landing_page_url	https://doi.org/10.55524/ijircst.2024.12.5.13
indexed_in	crossref
authorships[0].author.id	https://openalex.org/A5056241262
authorships[0].author.orcid	https://orcid.org/0000-0003-0633-9999
authorships[0].author.display_name	Bing Xing Wang
authorships[0].author_position	first
authorships[0].raw_author_name	Bingxing Wang
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5022901348
authorships[1].author.orcid
authorships[1].author.display_name	Hongye Zheng
authorships[1].author_position	middle
authorships[1].raw_author_name	Hongye Zheng
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5100384384
authorships[2].author.orcid	https://orcid.org/0000-0003-2631-4262
authorships[2].author.display_name	Yingbin Liang
authorships[2].author_position	middle
authorships[2].raw_author_name	Yingbin Liang
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5112390502
authorships[3].author.orcid
authorships[3].author.display_name	Guanming Huang
authorships[3].author_position	middle
authorships[3].raw_author_name	Guanming Huang
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5010332378
authorships[4].author.orcid	https://orcid.org/0000-0002-2794-2327
authorships[4].author.display_name	Junliang Du
authorships[4].author_position	last
authorships[4].raw_author_name	Junliang Du
authorships[4].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://doi.org/10.55524/ijircst.2024.12.5.13
open_access.oa_status	diamond
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Dual-Branch Dynamic Graph Convolutional Network for Robust Multi-Label Image Classification
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T03:46:38.306776
primary_topic.id	https://openalex.org/T11550
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9519000053405762
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Text and Document Classification Technologies
related_works	https://openalex.org/W2317351040, https://openalex.org/W2952466936, https://openalex.org/W1988622314, https://openalex.org/W2393949104, https://openalex.org/W3046201198, https://openalex.org/W4293061921, https://openalex.org/W2807441102, https://openalex.org/W2033914206, https://openalex.org/W2042327336, https://openalex.org/W2352553236
cited_by_count	13
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	4
counts_by_year[1].year	2024
counts_by_year[1].cited_by_count	9
locations_count	1
best_oa_location.id	doi:10.55524/ijircst.2024.12.5.13
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4210230306
best_oa_location.source.issn	2347-5552
best_oa_location.source.type	journal
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l	2347-5552
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	International Journal of Innovative Research in Computer Science & Technology
best_oa_location.source.host_organization
best_oa_location.source.host_organization_name
best_oa_location.license
best_oa_location.pdf_url
best_oa_location.version	publishedVersion
best_oa_location.raw_type	journal-article
best_oa_location.license_id
best_oa_location.is_accepted	True
best_oa_location.is_published	True
best_oa_location.raw_source_name	International Journal of Innovative Research in Computer Science and Technology
best_oa_location.landing_page_url	https://doi.org/10.55524/ijircst.2024.12.5.13
primary_location.id	doi:10.55524/ijircst.2024.12.5.13
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4210230306
primary_location.source.issn	2347-5552
primary_location.source.type	journal
primary_location.source.is_oa	True
primary_location.source.issn_l	2347-5552
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	International Journal of Innovative Research in Computer Science & Technology
primary_location.source.host_organization
primary_location.source.host_organization_name
primary_location.license
primary_location.pdf_url
primary_location.version	publishedVersion
primary_location.raw_type	journal-article
primary_location.license_id
primary_location.is_accepted	True
primary_location.is_published	True
primary_location.raw_source_name	International Journal of Innovative Research in Computer Science and Technology
primary_location.landing_page_url	https://doi.org/10.55524/ijircst.2024.12.5.13
publication_date	2024-09-01
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	59, 121
abstract_inverted_index.By	39
abstract_inverted_index.F1	113
abstract_inverted_index.an	11, 14
abstract_inverted_index.as	106
abstract_inverted_index.by	30
abstract_inverted_index.in	69, 102
abstract_inverted_index.is	23
abstract_inverted_index.it	43
abstract_inverted_index.of	4, 47, 55, 88, 139
abstract_inverted_index.to	25, 77, 127, 135, 143, 149
abstract_inverted_index.For	0
abstract_inverted_index.The	86
abstract_inverted_index.and	51, 81, 112, 142
abstract_inverted_index.the	1, 27, 45, 53, 63, 70, 74, 89, 95, 129, 137
abstract_inverted_index.was	92, 125
abstract_inverted_index.This	21
abstract_inverted_index.data	148
abstract_inverted_index.from	132
abstract_inverted_index.such	105
abstract_inverted_index.task	3
abstract_inverted_index.this	8
abstract_inverted_index.when	33
abstract_inverted_index.(CP),	109
abstract_inverted_index.(CR),	111
abstract_inverted_index.faced	29
abstract_inverted_index.graph	18
abstract_inverted_index.image	6, 146
abstract_inverted_index.label	151
abstract_inverted_index.model	91
abstract_inverted_index.ones,	141
abstract_inverted_index.other	117
abstract_inverted_index.paper	9
abstract_inverted_index.prior	130
abstract_inverted_index.score	114
abstract_inverted_index.study	64
abstract_inverted_index.using	94
abstract_inverted_index.(CF1),	115
abstract_inverted_index.boosts	52
abstract_inverted_index.images	134
abstract_inverted_index.inform	136
abstract_inverted_index.labels	36
abstract_inverted_index.models	32
abstract_inverted_index.recall	110
abstract_inverted_index.static	133
abstract_inverted_index.within	37
abstract_inverted_index.address	26
abstract_inverted_index.augment	150
abstract_inverted_index.current	31
abstract_inverted_index.dynamic	17, 140
abstract_inverted_index.feature	56, 67
abstract_inverted_index.imagery	97
abstract_inverted_index.images.	38
abstract_inverted_index.metrics	104
abstract_inverted_index.models.	119
abstract_inverted_index.module,	62
abstract_inverted_index.objects	80
abstract_inverted_index.overall	155
abstract_inverted_index.smaller	79
abstract_inverted_index.thereby	153
abstract_inverted_index.utilize	144
abstract_inverted_index.cascaded	122
abstract_inverted_index.category	49, 84, 147
abstract_inverted_index.critical	103
abstract_inverted_index.dataset,	72, 98
abstract_inverted_index.designed	24
abstract_inverted_index.enhances	44
abstract_inverted_index.generate	82
abstract_inverted_index.handling	34
abstract_inverted_index.identify	78
abstract_inverted_index.leverage	128
abstract_inverted_index.multiple	35
abstract_inverted_index.network.	20
abstract_inverted_index.original	48, 145
abstract_inverted_index.proposed	90
abstract_inverted_index.semantic	60
abstract_inverted_index.superior	100
abstract_inverted_index.training	71
abstract_inverted_index.Utilizing	58
abstract_inverted_index.accuracy.	157
abstract_inverted_index.approach:	13
abstract_inverted_index.attention	61
abstract_inverted_index.enhancing	73, 154
abstract_inverted_index.evaluated	93
abstract_inverted_index.features,	42
abstract_inverted_index.intricate	2
abstract_inverted_index.learning.	57
abstract_inverted_index.network's	75
abstract_inverted_index.precision	108
abstract_inverted_index.retention	46
abstract_inverted_index.reweights	66
abstract_inverted_index.structure	124
abstract_inverted_index.capability	76
abstract_inverted_index.categories	68
abstract_inverted_index.innovative	12
abstract_inverted_index.introduces	10
abstract_inverted_index.processing	138
abstract_inverted_index.robustness	54
abstract_inverted_index.MS-COCO2014	96
abstract_inverted_index.dual-branch	16
abstract_inverted_index.dynamically	65
abstract_inverted_index.implemented	126
abstract_inverted_index.information	50, 131
abstract_inverted_index.integrating	40
abstract_inverted_index.methodology	22
abstract_inverted_index.multi-label	5
abstract_inverted_index.multi-scale	41
abstract_inverted_index.performance	101
abstract_inverted_index.Furthermore,	120
abstract_inverted_index.difficulties	28
abstract_inverted_index.convolutional	19
abstract_inverted_index.correlations,	152
abstract_inverted_index.demonstrating	99
abstract_inverted_index.effectiveness	87
abstract_inverted_index.outperforming	116
abstract_inverted_index.classification	107, 123, 156
abstract_inverted_index.classification,	7
abstract_inverted_index.attention-guided	15
abstract_inverted_index.representations.	85
abstract_inverted_index.state-of-the-art	118
abstract_inverted_index.context-sensitive	83
cited_by_percentile_year.max	99
cited_by_percentile_year.min	97
countries_distinct_count	0
institutions_distinct_count	5
citation_normalized_percentile.value	0.96907506
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	True