{"id":"https://openalex.org/W4415316366","doi":"https://doi.org/10.1109/icassp55912.2026.11460485","title":"RIS-FUSION: Rethinking Text-Driven Infrared and Visible Image Fusion from the Perspective of Referring Image Segmentation","display_name":"RIS-FUSION: Rethinking Text-Driven Infrared and Visible Image Fusion from the Perspective of Referring Image Segmentation","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W4415316366","doi":"https://doi.org/10.1109/icassp55912.2026.11460485"},"language":"en","primary_location":{"id":"doi:10.1109/icassp55912.2026.11460485","doi":"https://doi.org/10.1109/icassp55912.2026.11460485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp55912.2026.11460485","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.12710","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Siju Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I137867983","display_name":"Central University of Finance and Economics","ror":"https://ror.org/008e3hf02","country_code":"CN","type":"education","lineage":["https://openalex.org/I137867983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siju Ma","raw_affiliation_strings":["Central University of Finance and Economics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central University of Finance and Economics,Beijing,China","institution_ids":["https://openalex.org/I137867983"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Changsiyu Gong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I137867983","display_name":"Central University of Finance and Economics","ror":"https://ror.org/008e3hf02","country_code":"CN","type":"education","lineage":["https://openalex.org/I137867983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsiyu Gong","raw_affiliation_strings":["Central University of Finance and Economics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central University of Finance and Economics,Beijing,China","institution_ids":["https://openalex.org/I137867983"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaofeng Fan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I137867983","display_name":"Central University of Finance and Economics","ror":"https://ror.org/008e3hf02","country_code":"CN","type":"education","lineage":["https://openalex.org/I137867983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Fan","raw_affiliation_strings":["Central University of Finance and Economics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central University of Finance and Economics,Beijing,China","institution_ids":["https://openalex.org/I137867983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443245","display_name":"Yong Ma","orcid":"https://orcid.org/0000-0002-8398-4118","observed_orcids":["https://orcid.org/0000-0002-8398-4118"]},"institutions":[{"id":"https://openalex.org/I137867983","display_name":"Central University of Finance and Economics","ror":"https://ror.org/008e3hf02","country_code":"CN","type":"education","lineage":["https://openalex.org/I137867983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Ma","raw_affiliation_strings":["Central University of Finance and Economics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central University of Finance and Economics,Beijing,China","institution_ids":["https://openalex.org/I137867983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056841900","display_name":"Chengjie Jiang","orcid":"https://orcid.org/0009-0002-7747-4506","observed_orcids":["https://orcid.org/0009-0002-7747-4506"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengjie Jiang","raw_affiliation_strings":["Tsinghua University,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.6156,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9600551,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"11902","last_page":"11906"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9883000254631042,"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"}},"topics":[{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9883000254631042,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.010300000198185444,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00039999998989515007,"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/infrared-and-visible-image-fusion","display_name":"infrared and visible image fusion","score":0.8930000066757202},{"id":"https://openalex.org/keywords/referring-image-segmentation","display_name":"referring image segmentation","score":0.9980000257492065},{"id":"https://openalex.org/keywords/multimodal-benchmark","display_name":"multimodal benchmark","score":0.5199999809265137},{"id":"https://openalex.org/keywords/semantic-alignment","display_name":"semantic alignment","score":0.6420000195503235}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7759000062942505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.736299991607666},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6834999918937683},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.6567000150680542},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5917999744415283},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5713000297546387},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5608999729156494},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5340999960899353},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5128999948501587},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.47859999537467957},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.37869998812675476},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.35409998893737793},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3138999938964844},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29019999504089355},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp55912.2026.11460485","doi":"https://doi.org/10.1109/icassp55912.2026.11460485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp55912.2026.11460485","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.12710","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12710","pdf_url":"https://arxiv.org/pdf/2509.12710","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.12710","doi":"https://doi.org/10.48550/arxiv.2509.12710","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.12710","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.12710","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12710","pdf_url":"https://arxiv.org/pdf/2509.12710","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-driven":[0],"infrared":[1],"and":[2,27,46,73,113,127,148],"visible":[3],"image":[4,43,101,122],"fusion":[5,16,37,48,72,91],"has":[6],"gained":[7],"attention":[8],"for":[9],"enabling":[10],"natural":[11],"language":[12],"to":[13,25,35,57,93],"guide":[14],"the":[15,31,36,54,59,82,90],"process.":[17],"However,":[18],"existing":[19,140],"methods":[20,141],"lack":[21],"a":[22,50,67,107,124,128],"goal-aligned":[23],"task":[24],"supervise":[26],"evaluate":[28],"how":[29],"effectively":[30],"input":[32],"text":[33],"contributes":[34],"outcome.":[38],"We":[39],"observe":[40],"that":[41,70,134],"referring":[42,100,129],"segmentation":[44,102,125],"(RIS)":[45],"text-driven":[47],"share":[49],"common":[51],"objective:":[52],"highlighting":[53],"object":[55],"referred":[56],"by":[58,62,142],"text.":[60],"Motivated":[61],"this,":[63],"we":[64,104],"propose":[65],"RIS-FUSION,":[66],"cascaded":[68],"framework":[69],"unifies":[71],"RIS":[74],"through":[75],"joint":[76],"optimization.":[77],"At":[78],"its":[79],"core":[80],"is":[81],"LangGatedFusion":[83],"module,":[84],"which":[85],"injects":[86],"textual":[87],"features":[88],"into":[89],"backbone":[92],"enhance":[94],"semantic":[95],"alignment.":[96],"To":[97],"support":[98],"multimodal":[99],"task,":[103],"introduce":[105],"MM-RIS,":[106],"large-scale":[108],"benchmark":[109],"with":[110],"12.5k":[111],"training":[112],"3.5k":[114],"testing":[115],"triplets,":[116],"each":[117],"consisting":[118],"of":[119],"an":[120],"infrared-visible":[121],"pair,":[123],"mask,":[126],"expression.":[130],"Extensive":[131],"experiments":[132],"show":[133],"RIS-FUSION":[135],"achieves":[136],"state-ofthe-art":[137],"performance,":[138],"outperforming":[139],"over":[143],"11%":[144],"in":[145],"mIoU.":[146],"Code":[147],"dataset":[149],"will":[150],"be":[151],"released":[152],"at":[153],"https://github.com/SijuMa2003/RIS-FUSION.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-18T00:00:00"}