{"id":"https://openalex.org/W4415708560","doi":"https://doi.org/10.1109/icme59968.2025.11209345","title":"MMPX: Multi-modal Mamba Prompter to Large Vision Foundation Model for RGB-X Semantic Segmentation","display_name":"MMPX: Multi-modal Mamba Prompter to Large Vision Foundation Model for RGB-X Semantic Segmentation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708560","doi":"https://doi.org/10.1109/icme59968.2025.11209345"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5061120675","display_name":"Pengfei Wu","orcid":"https://orcid.org/0000-0003-3404-3474"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Wu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications,School of Automation and Artificial Intelligence,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications,School of Automation and Artificial Intelligence,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346566","display_name":"Ye Liu","orcid":"https://orcid.org/0000-0002-9274-0430"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Liu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications,School of Automation and Artificial Intelligence,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications,School of Automation and Artificial Intelligence,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085096384","display_name":"Hao Gao","orcid":"https://orcid.org/0000-0002-4253-7418"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Gao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications,School of Automation and Artificial Intelligence,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications,School of Automation and Artificial Intelligence,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115602422","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0001-6766-5611"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["Lancaster University,School of Computing and Communications,Lancaster,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lancaster University,School of Computing and Communications,Lancaster,United Kingdom","institution_ids":["https://openalex.org/I67415387"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9460999965667725,"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":0.9460999965667725,"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":0.007199999876320362,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.006500000134110451,"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/segmentation","display_name":"Segmentation","score":0.7128999829292297},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5221999883651733},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5005000233650208},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.46070000529289246},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45669999718666077},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4560000002384186},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3560999929904938}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7350000143051147},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7128999829292297},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6779000163078308},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5221999883651733},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5005000233650208},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4693000018596649},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4560000002384186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4553999900817871},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3328000009059906},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2703000009059906},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1923184257","https://openalex.org/W2884822772","https://openalex.org/W2965867763","https://openalex.org/W3035467948","https://openalex.org/W3091001089","https://openalex.org/W3151130473","https://openalex.org/W3170885821","https://openalex.org/W3194841206","https://openalex.org/W3198062544","https://openalex.org/W3206439726","https://openalex.org/W4200630704","https://openalex.org/W4200635035","https://openalex.org/W4221147914","https://openalex.org/W4285247752","https://openalex.org/W4285600783","https://openalex.org/W4296913506","https://openalex.org/W4312402232","https://openalex.org/W4312594135","https://openalex.org/W4313139043","https://openalex.org/W4367663172","https://openalex.org/W4381300351","https://openalex.org/W4384519183","https://openalex.org/W4385245566","https://openalex.org/W4386065698","https://openalex.org/W4386076222","https://openalex.org/W4386179772","https://openalex.org/W4387967911","https://openalex.org/W4390489106","https://openalex.org/W4390873110","https://openalex.org/W4393156115","https://openalex.org/W4394597128","https://openalex.org/W4394597798","https://openalex.org/W4401807704","https://openalex.org/W4405785392","https://openalex.org/W4409262789"],"related_works":[],"abstract_inverted_index":{"Multi-modal":[0],"semantic":[1],"segmentation":[2,21,60],"leverages":[3],"multiple":[4],"types":[5],"of":[6,13,20,73,107,113,181],"input":[7,138],"data":[8,57],"to":[9,44,125],"perform":[10],"pixel-level":[11],"classification":[12],"images,":[14],"enhancing":[15],"the":[16,71,76,98,105,110,116,133,142,176,182],"accuracy":[17],"and":[18,139,178,186],"robustness":[19],"tasks.":[22],"Mainstream":[23],"methods":[24,67],"use":[25],"small-scale":[26],"models":[27,36,51],"which":[28,41,79,173],"have":[29],"limited":[30],"generalization":[31,179],"ability.":[32],"Training":[33],"large-scale":[34,48,127],"multi-modal":[35,39,59,100,121,167],"requires":[37],"massive":[38],"data,":[40],"is":[42,61],"difficult":[43],"obtain.":[45],"Thus,":[46],"fine-tuning":[47],"vision":[49],"foundation":[50,128],"(LVFMs)":[52],"trained":[53],"with":[54],"abundant":[55],"RGB":[56,77],"for":[58],"a":[62],"more":[63],"practical":[64],"solution.":[65],"Existing":[66],"only":[68],"tap":[69],"into":[70],"potential":[72,82,106],"LVFMs":[74,108],"in":[75,83,109],"modality":[78],"ignores":[80],"their":[81],"non-RGB":[84],"modalities.":[85],"In":[86],"this":[87],"paper,":[88],"we":[89,119],"propose":[90],"an":[91],"innovative":[92],"universal":[93],"prompting":[94],"framework,":[95],"MMPX.":[96],"Specifically,":[97],"effective":[99],"Mamba":[101,122],"fuser":[102],"(MMF)":[103],"explores":[104],"integrated":[111,134],"representation":[112,136],"RGB+X.":[114],"On":[115],"other":[117],"hand,":[118],"introduce":[120],"prompters":[123],"(MMPs)":[124],"fine-tune":[126],"models.":[129],"This":[130],"prompter":[131],"takes":[132],"RGB+X":[135],"as":[137],"dynamically":[140],"adjusts":[141],"model":[143],"parameters":[144],"using":[145],"Mamba,":[146],"eliminating":[147],"redundant":[148],"information":[149],"while":[150],"retaining":[151],"key":[152],"features,":[153],"thus":[154],"achieving":[155],"efficient":[156],"prompt":[157],"generation.":[158],"The":[159,184],"proposed":[160],"method":[161],"achieves":[162],"SOTA":[163],"performance":[164],"on":[165],"five":[166],"benchmarks,":[168],"including":[169],"RGB+Depth,":[170],"RGB+Thermal,":[171],"RGB+Event,":[172],"fully":[174],"validate":[175],"effectiveness":[177],"ability":[180],"approach.":[183],"code":[185],"results":[187],"are":[188],"available":[189],"at:":[190],"https://github.com/CauchyCat/MMPX.":[191]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}