Conquering High Packet-Loss Erasure: MoE Swin Transformer-Based Video Semantic Communication Article Swipe

PDF

Chen Dong , Zhicheng Bao , Xiaodong Xu , Rui Meng , Ping Zhang ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2508.01205

Semantic communication with joint semantic-channel coding robustly transmits diverse data modalities but faces challenges in mitigating semantic information loss due to packet drops in packet-based systems. Under current protocols, packets with errors are discarded, preventing the receiver from utilizing erroneous semantic data for robust decoding. To address this issue, a packet-loss-resistant MoE Swin Transformer-based Video Semantic Communication (MSTVSC) system is proposed in this paper. Semantic vectors are encoded by MSTVSC and transmitted through upper-layer protocol packetization. To investigate the impact of the packetization, a theoretical analysis of the packetization strategy is provided. To mitigate the semantic loss caused by packet loss, a 3D CNN at the receiver recovers missing information using un-lost semantic data and an packet-loss mask matrix. Semantic-level interleaving is employed to reduce concentrated semantic loss from packet drops. To improve compression, a common-individual decomposition approach is adopted, with downsampling applied to individual information to minimize redundancy. The model is lightweighted for practical deployment. Extensive simulations and comparisons demonstrate strong performance, achieving an MS-SSIM greater than 0.6 and a PSNR exceeding 20 dB at a 90% packet loss rate.

Related Topics

High Table

Mceachern High School

High Middle Ages

Ouran High School Host Club

Stuyvesant High School

High-Speed Rail In China

Monster High

High-Fructose Corn Syrup

High School Musical 2

High-A

The Irregular At Magic High School

Gm High Feature Engine

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2508.01205
PDF: https://arxiv.org/pdf/2508.01205
OA Status: green
OpenAlex ID: https://openalex.org/W4417098598

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4417098598

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2508.01205

Digital Object Identifier
Title: Conquering High Packet-Loss Erasure: MoE Swin Transformer-Based Video Semantic Communication

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-08-02

Full publication date if available
Authors: Chen Dong, Zhicheng Bao, Xiaodong Xu, Rui Meng, Ping Zhang

List of authors in order
Landing page: https://arxiv.org/abs/2508.01205

Publisher landing page
PDF URL: https://arxiv.org/pdf/2508.01205

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/2508.01205

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4417098598
doi	https://doi.org/10.48550/arxiv.2508.01205
ids.doi	https://doi.org/10.48550/arxiv.2508.01205
ids.openalex	https://openalex.org/W4417098598
fwci
type	preprint
title	Conquering High Packet-Loss Erasure: MoE Swin Transformer-Based Video Semantic Communication
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2508.01205
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/2508.01205
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/2508.01205
locations[1].id	doi:10.48550/arxiv.2508.01205
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.2508.01205
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5101492344
authorships[0].author.orcid	https://orcid.org/0000-0002-3443-1453
authorships[0].author.display_name	Chen Dong
authorships[0].author_position	middle
authorships[0].raw_author_name	Dong, Chen
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5051705103
authorships[1].author.orcid	https://orcid.org/0000-0002-2605-2007
authorships[1].author.display_name	Zhicheng Bao
authorships[1].author_position	last
authorships[1].raw_author_name	Bao, Zhicheng
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5061030501
authorships[2].author.orcid	https://orcid.org/0000-0003-4245-5989
authorships[2].author.display_name	Xiaodong Xu
authorships[2].author_position	middle
authorships[2].raw_author_name	Xu, Xiaodong
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5023884578
authorships[3].author.orcid	https://orcid.org/0000-0003-0486-1409
authorships[3].author.display_name	Rui Meng
authorships[3].author_position	middle
authorships[3].raw_author_name	Meng, Rui
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5100405787
authorships[4].author.orcid	https://orcid.org/0000-0002-0269-104X
authorships[4].author.display_name	Ping Zhang
authorships[4].author_position	middle
authorships[4].raw_author_name	Zhang, Ping
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://arxiv.org/pdf/2508.01205
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Conquering High Packet-Loss Erasure: MoE Swin Transformer-Based Video Semantic Communication
has_fulltext	False
is_retracted	False
updated_date	2025-12-08T09:52:09.977550
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2508.01205
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/2508.01205
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/2508.01205
primary_location.id	pmh:oai:arXiv.org:2508.01205
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/2508.01205
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/2508.01205
publication_date	2025-08-02
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	49, 83, 101, 134, 170, 176
abstract_inverted_index.20	173
abstract_inverted_index.3D	102
abstract_inverted_index.To	45, 76, 92, 131
abstract_inverted_index.an	115, 164
abstract_inverted_index.at	104, 175
abstract_inverted_index.by	68, 98
abstract_inverted_index.dB	174
abstract_inverted_index.in	14, 23, 61
abstract_inverted_index.is	59, 90, 121, 138, 151
abstract_inverted_index.of	80, 86
abstract_inverted_index.to	20, 123, 143, 146
abstract_inverted_index.0.6	168
abstract_inverted_index.90%	177
abstract_inverted_index.CNN	103
abstract_inverted_index.MoE	51
abstract_inverted_index.The	149
abstract_inverted_index.and	70, 114, 158, 169
abstract_inverted_index.are	32, 66
abstract_inverted_index.but	11
abstract_inverted_index.due	19
abstract_inverted_index.for	42, 153
abstract_inverted_index.the	35, 78, 81, 87, 94, 105
abstract_inverted_index.PSNR	171
abstract_inverted_index.Swin	52
abstract_inverted_index.data	9, 41, 113
abstract_inverted_index.from	37, 128
abstract_inverted_index.loss	18, 96, 127, 179
abstract_inverted_index.mask	117
abstract_inverted_index.than	167
abstract_inverted_index.this	47, 62
abstract_inverted_index.with	2, 30, 140
abstract_inverted_index.Under	26
abstract_inverted_index.Video	54
abstract_inverted_index.drops	22
abstract_inverted_index.faces	12
abstract_inverted_index.joint	3
abstract_inverted_index.loss,	100
abstract_inverted_index.model	150
abstract_inverted_index.rate.	180
abstract_inverted_index.using	110
abstract_inverted_index.MSTVSC	69
abstract_inverted_index.caused	97
abstract_inverted_index.coding	5
abstract_inverted_index.drops.	130
abstract_inverted_index.errors	31
abstract_inverted_index.impact	79
abstract_inverted_index.issue,	48
abstract_inverted_index.packet	21, 99, 129, 178
abstract_inverted_index.paper.	63
abstract_inverted_index.reduce	124
abstract_inverted_index.robust	43
abstract_inverted_index.strong	161
abstract_inverted_index.system	58
abstract_inverted_index.MS-SSIM	165
abstract_inverted_index.address	46
abstract_inverted_index.applied	142
abstract_inverted_index.current	27
abstract_inverted_index.diverse	8
abstract_inverted_index.encoded	67
abstract_inverted_index.greater	166
abstract_inverted_index.improve	132
abstract_inverted_index.matrix.	118
abstract_inverted_index.missing	108
abstract_inverted_index.packets	29
abstract_inverted_index.through	72
abstract_inverted_index.un-lost	111
abstract_inverted_index.vectors	65
abstract_inverted_index.(MSTVSC)	57
abstract_inverted_index.Semantic	0, 55, 64
abstract_inverted_index.adopted,	139
abstract_inverted_index.analysis	85
abstract_inverted_index.approach	137
abstract_inverted_index.employed	122
abstract_inverted_index.minimize	147
abstract_inverted_index.mitigate	93
abstract_inverted_index.proposed	60
abstract_inverted_index.protocol	74
abstract_inverted_index.receiver	36, 106
abstract_inverted_index.recovers	107
abstract_inverted_index.robustly	6
abstract_inverted_index.semantic	16, 40, 95, 112, 126
abstract_inverted_index.strategy	89
abstract_inverted_index.systems.	25
abstract_inverted_index.Extensive	156
abstract_inverted_index.achieving	163
abstract_inverted_index.decoding.	44
abstract_inverted_index.erroneous	39
abstract_inverted_index.exceeding	172
abstract_inverted_index.practical	154
abstract_inverted_index.provided.	91
abstract_inverted_index.transmits	7
abstract_inverted_index.utilizing	38
abstract_inverted_index.challenges	13
abstract_inverted_index.discarded,	33
abstract_inverted_index.individual	144
abstract_inverted_index.mitigating	15
abstract_inverted_index.modalities	10
abstract_inverted_index.preventing	34
abstract_inverted_index.protocols,	28
abstract_inverted_index.comparisons	159
abstract_inverted_index.demonstrate	160
abstract_inverted_index.deployment.	155
abstract_inverted_index.information	17, 109, 145
abstract_inverted_index.investigate	77
abstract_inverted_index.packet-loss	116
abstract_inverted_index.redundancy.	148
abstract_inverted_index.simulations	157
abstract_inverted_index.theoretical	84
abstract_inverted_index.transmitted	71
abstract_inverted_index.upper-layer	73
abstract_inverted_index.compression,	133
abstract_inverted_index.concentrated	125
abstract_inverted_index.downsampling	141
abstract_inverted_index.interleaving	120
abstract_inverted_index.packet-based	24
abstract_inverted_index.performance,	162
abstract_inverted_index.Communication	56
abstract_inverted_index.communication	1
abstract_inverted_index.decomposition	136
abstract_inverted_index.lightweighted	152
abstract_inverted_index.packetization	88
abstract_inverted_index.Semantic-level	119
abstract_inverted_index.packetization,	82
abstract_inverted_index.packetization.	75
abstract_inverted_index.semantic-channel	4
abstract_inverted_index.Transformer-based	53
abstract_inverted_index.common-individual	135
abstract_inverted_index.packet-loss-resistant	50
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	5
citation_normalized_percentile