Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation Article Swipe

PDF

Jinxiang Liu , Chen Ju , Chaofan Ma , Yanfeng Wang , Yu Wang , Ya Zhang ·

YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2307.13236

The goal of the audio-visual segmentation (AVS) task is to segment the sounding objects in the video frames using audio cues. However, current fusion-based methods have the performance limitations due to the small receptive field of convolution and inadequate fusion of audio-visual features. To overcome these issues, we propose a novel \textbf{Au}dio-aware query-enhanced \textbf{TR}ansformer (AuTR) to tackle the task. Unlike existing methods, our approach introduces a multimodal transformer architecture that enables deep fusion and aggregation of audio-visual features. Furthermore, we devise an audio-aware query-enhanced transformer decoder that explicitly helps the model focus on the segmentation of the pinpointed sounding objects based on audio signals, while disregarding silent yet salient objects. Experimental results show that our method outperforms previous methods and demonstrates better generalization ability in multi-sound and open-set scenarios.

Related Topics

Artificial Intelligence

Concepts

Computer science Segmentation Transformer Audio visual Artificial intelligence Salient Speech recognition Computer vision Multimedia Quantum mechanics Physics Voltage

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2307.13236
PDF: https://arxiv.org/pdf/2307.13236
OA Status: green
Cited By: 5
Related Works: 10
OpenAlex ID: https://openalex.org/W4385292115

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4385292115

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2307.13236

Digital Object Identifier
Title: Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2023

Year of publication
Publication date: 2023-07-25

Full publication date if available
Authors: Jinxiang Liu, Chen Ju, Chaofan Ma, Yanfeng Wang, Yu Wang, Ya Zhang

List of authors in order
Landing page: https://arxiv.org/abs/2307.13236

Publisher landing page
PDF URL: https://arxiv.org/pdf/2307.13236

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2307.13236

Direct OA link when available
Concepts: Computer science, Segmentation, Transformer, Audio visual, Artificial intelligence, Salient, Speech recognition, Computer vision, Multimedia, Quantum mechanics, Physics, Voltage

Top concepts (fields/topics) attached by OpenAlex
Cited by: 5

Total citation count in OpenAlex
Citations by year (recent): 2025: 2, 2024: 3

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

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4385292115
doi	https://doi.org/10.48550/arxiv.2307.13236
ids.doi	https://doi.org/10.48550/arxiv.2307.13236
ids.openalex	https://openalex.org/W4385292115
fwci
type	preprint
title	Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10860
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9995999932289124
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1711
topics[0].subfield.display_name	Signal Processing
topics[0].display_name	Speech and Audio Processing
topics[1].id	https://openalex.org/T11309
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9991000294685364
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1711
topics[1].subfield.display_name	Signal Processing
topics[1].display_name	Music and Audio Processing
topics[2].id	https://openalex.org/T10283
topics[2].field.id	https://openalex.org/fields/28
topics[2].field.display_name	Neuroscience
topics[2].score	0.9936000108718872
topics[2].domain.id	https://openalex.org/domains/1
topics[2].domain.display_name	Life Sciences
topics[2].subfield.id	https://openalex.org/subfields/2805
topics[2].subfield.display_name	Cognitive Neuroscience
topics[2].display_name	Hearing Loss and Rehabilitation
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.8517049551010132
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C89600930
concepts[1].level	2
concepts[1].score	0.6198641657829285
concepts[1].wikidata	https://www.wikidata.org/wiki/Q1423946
concepts[1].display_name	Segmentation
concepts[2].id	https://openalex.org/C66322947
concepts[2].level	3
concepts[2].score	0.5651654005050659
concepts[2].wikidata	https://www.wikidata.org/wiki/Q11658
concepts[2].display_name	Transformer
concepts[3].id	https://openalex.org/C3017588708
concepts[3].level	2
concepts[3].score	0.5587079524993896
concepts[3].wikidata	https://www.wikidata.org/wiki/Q758901
concepts[3].display_name	Audio visual
concepts[4].id	https://openalex.org/C154945302
concepts[4].level	1
concepts[4].score	0.5071156024932861
concepts[4].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[4].display_name	Artificial intelligence
concepts[5].id	https://openalex.org/C2780719617
concepts[5].level	2
concepts[5].score	0.4857045114040375
concepts[5].wikidata	https://www.wikidata.org/wiki/Q1030752
concepts[5].display_name	Salient
concepts[6].id	https://openalex.org/C28490314
concepts[6].level	1
concepts[6].score	0.45910289883613586
concepts[6].wikidata	https://www.wikidata.org/wiki/Q189436
concepts[6].display_name	Speech recognition
concepts[7].id	https://openalex.org/C31972630
concepts[7].level	1
concepts[7].score	0.38088735938072205
concepts[7].wikidata	https://www.wikidata.org/wiki/Q844240
concepts[7].display_name	Computer vision
concepts[8].id	https://openalex.org/C49774154
concepts[8].level	1
concepts[8].score	0.19375252723693848
concepts[8].wikidata	https://www.wikidata.org/wiki/Q131765
concepts[8].display_name	Multimedia
concepts[9].id	https://openalex.org/C62520636
concepts[9].level	1
concepts[9].score	0.0
concepts[9].wikidata	https://www.wikidata.org/wiki/Q944
concepts[9].display_name	Quantum mechanics
concepts[10].id	https://openalex.org/C121332964
concepts[10].level	0
concepts[10].score	0.0
concepts[10].wikidata	https://www.wikidata.org/wiki/Q413
concepts[10].display_name	Physics
concepts[11].id	https://openalex.org/C165801399
concepts[11].level	2
concepts[11].score	0.0
concepts[11].wikidata	https://www.wikidata.org/wiki/Q25428
concepts[11].display_name	Voltage
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.8517049551010132
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/segmentation
keywords[1].score	0.6198641657829285
keywords[1].display_name	Segmentation
keywords[2].id	https://openalex.org/keywords/transformer
keywords[2].score	0.5651654005050659
keywords[2].display_name	Transformer
keywords[3].id	https://openalex.org/keywords/audio-visual
keywords[3].score	0.5587079524993896
keywords[3].display_name	Audio visual
keywords[4].id	https://openalex.org/keywords/artificial-intelligence
keywords[4].score	0.5071156024932861
keywords[4].display_name	Artificial intelligence
keywords[5].id	https://openalex.org/keywords/salient
keywords[5].score	0.4857045114040375
keywords[5].display_name	Salient
keywords[6].id	https://openalex.org/keywords/speech-recognition
keywords[6].score	0.45910289883613586
keywords[6].display_name	Speech recognition
keywords[7].id	https://openalex.org/keywords/computer-vision
keywords[7].score	0.38088735938072205
keywords[7].display_name	Computer vision
keywords[8].id	https://openalex.org/keywords/multimedia
keywords[8].score	0.19375252723693848
keywords[8].display_name	Multimedia
language	en
locations[0].id	pmh:oai:arXiv.org:2307.13236
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2307.13236
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2307.13236
locations[1].id	doi:10.48550/arxiv.2307.13236
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2307.13236
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5101682289
authorships[0].author.orcid	https://orcid.org/0000-0003-2583-8881
authorships[0].author.display_name	Jinxiang Liu
authorships[0].author_position	first
authorships[0].raw_author_name	Liu, Jinxiang
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5100774574
authorships[1].author.orcid	https://orcid.org/0000-0001-8472-7677
authorships[1].author.display_name	Chen Ju
authorships[1].author_position	middle
authorships[1].raw_author_name	Ju, Chen
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5102703207
authorships[2].author.orcid
authorships[2].author.display_name	Chaofan Ma
authorships[2].author_position	middle
authorships[2].raw_author_name	Ma, Chaofan
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5100645705
authorships[3].author.orcid	https://orcid.org/0000-0002-3196-2347
authorships[3].author.display_name	Yanfeng Wang
authorships[3].author_position	middle
authorships[3].raw_author_name	Wang, Yanfeng
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5100445356
authorships[4].author.orcid	https://orcid.org/0000-0003-2883-1087
authorships[4].author.display_name	Yu Wang
authorships[4].author_position	middle
authorships[4].raw_author_name	Wang, Yu
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5100342828
authorships[5].author.orcid	https://orcid.org/0000-0002-5390-9053
authorships[5].author.display_name	Ya Zhang
authorships[5].author_position	last
authorships[5].raw_author_name	Zhang, Ya
authorships[5].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://arxiv.org/pdf/2307.13236
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10860
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9995999932289124
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1711
primary_topic.subfield.display_name	Signal Processing
primary_topic.display_name	Speech and Audio Processing
related_works	https://openalex.org/W2329500892, https://openalex.org/W2271369634, https://openalex.org/W3147472394, https://openalex.org/W2047100085, https://openalex.org/W2350550760, https://openalex.org/W28991112, https://openalex.org/W578794879, https://openalex.org/W2370726991, https://openalex.org/W2625296515, https://openalex.org/W3137890128
cited_by_count	5
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	2
counts_by_year[1].year	2024
counts_by_year[1].cited_by_count	3
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2307.13236
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2307.13236
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2307.13236
primary_location.id	pmh:oai:arXiv.org:2307.13236
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2307.13236
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2307.13236
publication_date	2023-07-25
publication_year	2023
referenced_works_count	0
abstract_inverted_index.a	49, 65
abstract_inverted_index.To	43
abstract_inverted_index.an	81
abstract_inverted_index.in	14, 124
abstract_inverted_index.is	8
abstract_inverted_index.of	2, 35, 40, 75, 95
abstract_inverted_index.on	92, 101
abstract_inverted_index.to	9, 30, 55
abstract_inverted_index.we	47, 79
abstract_inverted_index.The	0
abstract_inverted_index.and	37, 73, 119, 126
abstract_inverted_index.due	29
abstract_inverted_index.our	62, 114
abstract_inverted_index.the	3, 11, 15, 26, 31, 57, 89, 93, 96
abstract_inverted_index.yet	107
abstract_inverted_index.deep	71
abstract_inverted_index.goal	1
abstract_inverted_index.have	25
abstract_inverted_index.show	112
abstract_inverted_index.task	7
abstract_inverted_index.that	69, 86, 113
abstract_inverted_index.(AVS)	6
abstract_inverted_index.audio	19, 102
abstract_inverted_index.based	100
abstract_inverted_index.cues.	20
abstract_inverted_index.field	34
abstract_inverted_index.focus	91
abstract_inverted_index.helps	88
abstract_inverted_index.model	90
abstract_inverted_index.novel	50
abstract_inverted_index.small	32
abstract_inverted_index.task.	58
abstract_inverted_index.these	45
abstract_inverted_index.using	18
abstract_inverted_index.video	16
abstract_inverted_index.while	104
abstract_inverted_index.(AuTR)	54
abstract_inverted_index.Unlike	59
abstract_inverted_index.better	121
abstract_inverted_index.devise	80
abstract_inverted_index.frames	17
abstract_inverted_index.fusion	39, 72
abstract_inverted_index.method	115
abstract_inverted_index.silent	106
abstract_inverted_index.tackle	56
abstract_inverted_index.ability	123
abstract_inverted_index.current	22
abstract_inverted_index.decoder	85
abstract_inverted_index.enables	70
abstract_inverted_index.issues,	46
abstract_inverted_index.methods	24, 118
abstract_inverted_index.objects	13, 99
abstract_inverted_index.propose	48
abstract_inverted_index.results	111
abstract_inverted_index.salient	108
abstract_inverted_index.segment	10
abstract_inverted_index.However,	21
abstract_inverted_index.approach	63
abstract_inverted_index.existing	60
abstract_inverted_index.methods,	61
abstract_inverted_index.objects.	109
abstract_inverted_index.open-set	127
abstract_inverted_index.overcome	44
abstract_inverted_index.previous	117
abstract_inverted_index.signals,	103
abstract_inverted_index.sounding	12, 98
abstract_inverted_index.features.	42, 77
abstract_inverted_index.receptive	33
abstract_inverted_index.explicitly	87
abstract_inverted_index.inadequate	38
abstract_inverted_index.introduces	64
abstract_inverted_index.multimodal	66
abstract_inverted_index.pinpointed	97
abstract_inverted_index.scenarios.	128
abstract_inverted_index.aggregation	74
abstract_inverted_index.audio-aware	82
abstract_inverted_index.convolution	36
abstract_inverted_index.limitations	28
abstract_inverted_index.multi-sound	125
abstract_inverted_index.outperforms	116
abstract_inverted_index.performance	27
abstract_inverted_index.transformer	67, 84
abstract_inverted_index.Experimental	110
abstract_inverted_index.Furthermore,	78
abstract_inverted_index.architecture	68
abstract_inverted_index.audio-visual	4, 41, 76
abstract_inverted_index.demonstrates	120
abstract_inverted_index.disregarding	105
abstract_inverted_index.fusion-based	23
abstract_inverted_index.segmentation	5, 94
abstract_inverted_index.generalization	122
abstract_inverted_index.query-enhanced	52, 83
abstract_inverted_index.\textbf{Au}dio-aware	51
abstract_inverted_index.\textbf{TR}ansformer	53
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile