{"id":"https://openalex.org/W7147295327","doi":"https://doi.org/10.1109/cnml68938.2026.11453228","title":"CAFF-Net: A multimodal fusion network based on diffusion enhancement and cross-modal feature modulation","display_name":"CAFF-Net: A multimodal fusion network based on diffusion enhancement and cross-modal feature modulation","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7147295327","doi":"https://doi.org/10.1109/cnml68938.2026.11453228"},"language":null,"primary_location":{"id":"doi:10.1109/cnml68938.2026.11453228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11453228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","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/A5114116585","display_name":"Jiaxue Han","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaxue Han","raw_affiliation_strings":["Xinjiang University,School of Software,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Software,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132549844","display_name":"Zhou Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Fu","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132556720","display_name":"Rui Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Gao","raw_affiliation_strings":["Xinjiang University,Science and Technology Department,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,Science and Technology Department,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132695270","display_name":"Cheng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Chen","raw_affiliation_strings":["Xinjiang University,School of Software,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Software,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132565208","display_name":"Guangjian Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangjian Liu","raw_affiliation_strings":["Xinjiang University,School of Software,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Software,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132729394","display_name":"Jianjie Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianjie Zhang","raw_affiliation_strings":["Xinjiang University,School of Electrical Engineering,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Electrical Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425353","display_name":"Mingwei Li","orcid":"https://orcid.org/0000-0002-0805-6477"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Li","raw_affiliation_strings":["Xinjiang University,Xinjiang Aiqiside Testing Technology Co., Ltd. School of Computer Science and Technology,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,Xinjiang Aiqiside Testing Technology Co., Ltd. School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5114116585"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83851708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"789","last_page":"794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10392","display_name":"Cutaneous Melanoma Detection and Management","score":0.8424999713897705,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10392","display_name":"Cutaneous Melanoma Detection and Management","score":0.8424999713897705,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.02800000086426735,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.01860000006854534,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6585000157356262},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6201000213623047},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.5135999917984009},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5041000247001648},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.46560001373291016},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4602000117301941},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43709999322891235},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.40779998898506165},{"id":"https://openalex.org/keywords/feature-detection","display_name":"Feature detection (computer vision)","score":0.39969998598098755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6615999937057495},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6585000157356262},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.5135999917984009},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.46560001373291016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.40779998898506165},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.39969998598098755},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39899998903274536},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2865999937057495},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.26809999346733093},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cnml68938.2026.11453228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11453228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1529623688","https://openalex.org/W2063552117","https://openalex.org/W3001760905","https://openalex.org/W3026316716","https://openalex.org/W3081500256","https://openalex.org/W3133356497","https://openalex.org/W4223452607","https://openalex.org/W4293162951","https://openalex.org/W4311692525","https://openalex.org/W4322625967","https://openalex.org/W4400306894","https://openalex.org/W4401442820","https://openalex.org/W4403071891","https://openalex.org/W4409261936","https://openalex.org/W4410296428"],"related_works":[],"abstract_inverted_index":{"In":[0],"dermatology":[1,83],"diagnosis,":[2],"while":[3],"images":[4,45],"and":[5,10,34,46,48,91,115,137,149,171,186],"meta-":[6],"data":[7],"provide":[8],"crucial":[9],"complementary":[11],"information,":[12],"existing":[13],"multimodal":[14,82],"fusion":[15,162,179],"methods":[16,180],"still":[17],"face":[18],"three":[19],"major":[20],"challenges:":[21],"first,":[22],"they":[23,37,50],"neglect":[24],"feature":[25,53,93],"degradation":[26],"in":[27,181],"local":[28],"image":[29,100,110,118,142],"regions":[30],"due":[31],"to":[32,39,63,65,103],"noise":[33],"blurring;":[35],"second,":[36],"struggle":[38],"establish":[40],"fine-grained":[41],"semantic":[42,132],"interactions":[43],"between":[44],"meta-data;":[47],"third,":[49],"lack":[51],"dynamic":[52,139],"enhancement":[54],"based":[55],"on":[56,108,165],"metadata,":[57],"making":[58],"it":[59],"difficult":[60],"for":[61,134],"models":[62],"adapt":[64],"the":[66,154,166],"personalized":[67,160],"diagnostic":[68],"needs":[69],"of":[70,141,183],"different":[71],"diseases.":[72],"To":[73],"address":[74],"these":[75],"challenges,":[76],"this":[77],"paper":[78],"proposes":[79],"CAFF-Net,":[80],"a":[81,98,121],"classification":[84],"framework":[85],"that":[86,174],"integrates":[87],"cross-modal":[88,122,161],"attention":[89,123],"guidance":[90,133],"metadata":[92,126],"modulation.":[94],"First,":[95],"we":[96],"design":[97],"diffusion-based":[99],"patching":[101],"module":[102],"independently":[104],"perform":[105],"diffusion":[106],"reconstruction":[107],"each":[109],"patch,":[111],"obtaining":[112],"clearer,":[113],"texture-consistent,":[114],"structurally":[116],"stable":[117],"tokens.":[119],"Then,":[120],"mechanism":[124],"using":[125],"vectors":[127],"as":[128],"queries":[129],"provides":[130],"explicit":[131],"disease-related":[135],"regions;":[136],"further":[138],"modulation":[140,156],"features":[143],"is":[144],"achieved":[145],"through":[146],"channel-level":[147],"scaling":[148],"bias":[150],"parameters":[151],"generated":[152],"by":[153],"FiLM":[155],"mechanism,":[157],"thus":[158],"realizing":[159],"representations.":[163],"Experiments":[164],"two":[167],"public":[168],"datasets":[169],"PAD-UFES-20":[170],"Derm7pt":[172],"show":[173],"CAFF-Net":[175],"significantly":[176],"outperforms":[177],"mainstream":[178],"terms":[182],"accuracy,":[184],"BACC,":[185],"other":[187],"metrics.":[188]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-02T00:00:00"}