{"id":"https://openalex.org/W7124176547","doi":"https://doi.org/10.1109/icpads67057.2025.11323107","title":"AS-Mamba: Multimodal Semantic Segmentation via Mamba with Asymmetric Cross and Spatial Perception","display_name":"AS-Mamba: Multimodal Semantic Segmentation via Mamba with Asymmetric Cross and Spatial Perception","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124176547","doi":"https://doi.org/10.1109/icpads67057.2025.11323107"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11323107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122994909","display_name":"Guohao Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guohao Shen","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University,Zhengzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University,Zhengzhou,China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008871967","display_name":"Hongzhao Li","orcid":"https://orcid.org/0009-0002-6611-7896"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhao Li","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University,Zhengzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University,Zhengzhou,China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101604667","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0002-1303-0482"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University,Zhengzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University,Zhengzhou,China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111489389","display_name":"Xianglong Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianglong Shen","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University,Zhengzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University,Zhengzhou,China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123029126","display_name":"Jingya Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingya Dong","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University,Zhengzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University,Zhengzhou,China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068024080","display_name":"Shupan Li","orcid":"https://orcid.org/0000-0002-5823-2037"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shupan Li","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University,Zhengzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University,Zhengzhou,China","institution_ids":["https://openalex.org/I38877650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5122994909"],"corresponding_institution_ids":["https://openalex.org/I38877650"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6670763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6207000017166138,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6207000017166138,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.05530000105500221,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0544000007212162,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/crossmodal","display_name":"Crossmodal","score":0.6937000155448914},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6140000224113464},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5648000240325928},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5562000274658203},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.527999997138977},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4641999900341034},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.45719999074935913},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.41029998660087585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267000079154968},{"id":"https://openalex.org/C60115397","wikidata":"https://www.wikidata.org/wiki/Q5188732","display_name":"Crossmodal","level":4,"score":0.6937000155448914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6448000073432922},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6140000224113464},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5648000240325928},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5562000274658203},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.527999997138977},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4641999900341034},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3950999975204468},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2768000066280365},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.26759999990463257}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6609555856","display_name":null,"funder_award_id":"62272422","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2075787635","https://openalex.org/W3010665872","https://openalex.org/W3212332191","https://openalex.org/W4238477212","https://openalex.org/W4309412778","https://openalex.org/W4382598168","https://openalex.org/W4385847765","https://openalex.org/W4386421066","https://openalex.org/W4401049789","https://openalex.org/W4402194559","https://openalex.org/W4402274014","https://openalex.org/W4409140194","https://openalex.org/W4410303976","https://openalex.org/W4411889467","https://openalex.org/W4412102587","https://openalex.org/W4412474795","https://openalex.org/W4412515117","https://openalex.org/W4412792698","https://openalex.org/W4412838271","https://openalex.org/W4412934573","https://openalex.org/W4412951205"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"semantic":[1,12,59,112],"segmentation":[2],"integrates":[3],"information":[4,19,97],"from":[5,20,98],"multiple":[6],"data":[7],"sources":[8],"to":[9,93,130],"perform":[10],"pixel-wise":[11],"classification":[13],"of":[14,48,82,149],"images.":[15],"By":[16],"fusing":[17],"complementary":[18,96],"modalities":[21,102],"such":[22,44],"as":[23,45],"thermal":[24],"infrared":[25],"and":[26,32,57,100,109,118,143],"depth":[27],"with":[28,76],"traditional":[29],"RGB,":[30],"robust":[31],"reliable":[33],"predictions":[34],"can":[35],"be":[36],"achieved.":[37],"However,":[38],"existing":[39],"methods":[40],"still":[41],"face":[42],"challenges":[43],"insufficient":[46],"utilization":[47],"cross-modal":[49,111],"information,":[50],"limitations":[51],"imposed":[52],"by":[53],"local":[54],"receptive":[55],"fields,":[56],"cross-category":[58],"confusion.":[60],"To":[61],"address":[62],"these":[63],"issues,":[64],"this":[65],"paper":[66],"proposes":[67],"the":[68,80,147],"AS-Mamba":[69],"framework,":[70],"which":[71],"introduces":[72],"a":[73,123,136],"Mamba":[74,89,126],"structure":[75],"linear":[77],"complexity":[78],"into":[79],"field":[81],"image":[83],"segmentation.":[84],"Firstly,":[85],"an":[86,104],"Asymmetric":[87],"Cross":[88],"module":[90,127],"is":[91,128],"constructed":[92],"dynamically":[94],"integrate":[95],"RGB":[99],"X":[101],"through":[103,135],"attention":[105,138],"weight":[106],"allocation":[107],"strategy":[108],"enhanced":[110],"alignment,":[113],"enabling":[114],"crossmodal":[115],"dynamic":[116],"interaction":[117],"global":[119],"feature":[120,133],"fusion.":[121],"Secondly,":[122],"Spatial":[124],"Perception":[125],"designed":[129],"enhance":[131],"fine-grained":[132],"representation":[134],"spatial-channel":[137],"mechanism.":[139],"Experiments":[140],"on":[141],"RGB-Thermal":[142],"RGBDepth":[144],"tasks":[145],"demonstrate":[146],"superiority":[148],"AS-Mamba.":[150]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-15T00:00:00"}