{"id":"https://openalex.org/W4415538957","doi":"https://doi.org/10.1145/3746027.3755182","title":"Infrared and Visible Image Fusion with Language-Driven Loss in CLIP Embedding Space","display_name":"Infrared and Visible Image Fusion with Language-Driven Loss in CLIP Embedding Space","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538957","doi":"https://doi.org/10.1145/3746027.3755182"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5109678066","display_name":"Yuhao Wang","orcid":"https://orcid.org/0009-0001-5633-7927"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhao Wang","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348913","display_name":"Lingjuan Miao","orcid":"https://orcid.org/0000-0003-1782-4535"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingjuan Miao","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029710781","display_name":"Zhiqiang Zhou","orcid":"https://orcid.org/0000-0001-6871-8236"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Zhou","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110152558","display_name":"Lei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101878092","display_name":"Yajun Qiao","orcid":"https://orcid.org/0009-0007-8120-9146"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao Yajun","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5109678066"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":2.5606,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92024274,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1443","last_page":"1451"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":1.0,"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":1.0,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.9976000189781189,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9958000183105469,"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/embedding","display_name":"Embedding","score":0.8468000292778015},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.7698000073432922},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.6632999777793884},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6489999890327454},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4927999973297119},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.3319999873638153},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.33160001039505005}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8468000292778015},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.7698000073432922},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.6632999777793884},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6489999890327454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5873000025749207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5644000172615051},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49549999833106995},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4927999973297119},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3319999873638153},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C2778971668","wikidata":"https://www.wikidata.org/wiki/Q5510284","display_name":"Fusion rules","level":4,"score":0.32280001044273376},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C158355884","wikidata":"https://www.wikidata.org/wiki/Q11388","display_name":"Infrared","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1580436348","https://openalex.org/W1997596006","https://openalex.org/W2603777577","https://openalex.org/W2798987894","https://openalex.org/W2963890275","https://openalex.org/W3011768656","https://openalex.org/W3039415429","https://openalex.org/W3046194589","https://openalex.org/W3107998196","https://openalex.org/W3159235206","https://openalex.org/W3181367324","https://openalex.org/W3216156094","https://openalex.org/W4220893768","https://openalex.org/W4220927862","https://openalex.org/W4283732315","https://openalex.org/W4286611278","https://openalex.org/W4312052673","https://openalex.org/W4312594135","https://openalex.org/W4312737473","https://openalex.org/W4362014679","https://openalex.org/W4376126900","https://openalex.org/W4377091052","https://openalex.org/W4379209584","https://openalex.org/W4386076504","https://openalex.org/W4386083029","https://openalex.org/W4390871856","https://openalex.org/W4392640789","https://openalex.org/W4401944810","https://openalex.org/W4402715923"],"related_works":[],"abstract_inverted_index":{"Infrared-visible":[0],"image":[1,16,52,153],"fusion":[2,27,60,87,105,115,130,149,171,185],"(IVIF)":[3],"has":[4],"attracted":[5],"much":[6,183],"attention":[7],"owing":[8],"to":[9,19,46,69,73,102,161],"the":[10,14,20,26,37,50,56,75,82,97,104,122,136,141,144,148,163,168],"highly-complementary":[11],"properties":[12],"of":[13,22,29,58,77,86,96,99],"two":[15],"modalities.":[17,154],"Due":[18],"lack":[21],"ground-truth":[23],"fused":[24,51],"images,":[25],"output":[28,88],"current":[30,90],"deep-learning":[31],"based":[32],"methods":[33,61],"heavily":[34],"depends":[35],"on":[36],"loss":[38,158],"functions":[39],"defined":[40],"mathematically.":[41],"As":[42],"it":[43],"is":[44,62,132,159],"hard":[45],"well":[47],"mathematically":[48],"define":[49],"without":[53],"ground":[54],"truth,":[55],"performance":[57],"existing":[59,188],"limited.":[63],"In":[64],"this":[65,108],"paper,":[66],"we":[67,110],"propose":[68],"use":[70,95],"natural":[71],"language":[72,100],"express":[74],"objective":[76,150],"IVIF,":[78],"which":[79],"can":[80,181],"avoid":[81],"explicit":[83],"mathematical":[84],"modeling":[85],"in":[89,135],"losses,":[91],"and":[92,117,151],"make":[93,162],"full":[94],"advantage":[98],"expression":[101],"improve":[103],"performance.":[106],"For":[107],"purpose,":[109],"present":[111],"a":[112,156],"comprehensive":[113],"language-expressed":[114],"objective,":[116],"encode":[118],"relevant":[119],"texts":[120],"into":[121],"multi-modal":[123],"embedding":[124,137],"space":[125],"using":[126],"CLIP.":[127],"A":[128],"language-driven":[129,157,170],"model":[131,172],"then":[133],"constructed":[134],"space,":[138],"by":[139],"establishing":[140],"relationship":[142],"among":[143],"embedded":[145,169],"vectors":[146],"representing":[147],"input":[152],"Finally,":[155],"derived":[160],"actual":[164],"IVIF":[165],"aligned":[166],"with":[167],"via":[173],"supervised":[174],"training.":[175],"Experiments":[176],"show":[177],"that":[178],"our":[179],"method":[180],"obtain":[182],"better":[184],"results":[186],"than":[187],"techniques.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-25T00:00:00"}