{"id":"https://openalex.org/W4417428976","doi":"https://doi.org/10.1109/iccv51701.2025.00023","title":"IRGPT: Understanding Real-World Infrared Image with Bi-Cross-Modal Curriculum on Large-Scale Benchmark","display_name":"IRGPT: Understanding Real-World Infrared Image with Bi-Cross-Modal Curriculum on Large-Scale Benchmark","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417428976","doi":"https://doi.org/10.1109/iccv51701.2025.00023"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.14449","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102721252","display_name":"Zhe Cao","orcid":"https://orcid.org/0000-0002-8704-473X"},"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":"Zhe Cao","raw_affiliation_strings":["Beijing Institute of Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405898","display_name":"Jin Zhang","orcid":"https://orcid.org/0000-0001-5462-3631"},"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":"Jin Zhang","raw_affiliation_strings":["Beijing Institute of Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005703475","display_name":"Ruiheng Zhang","orcid":"https://orcid.org/0000-0002-5460-7196"},"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":"Ruiheng Zhang","raw_affiliation_strings":["Beijing Institute of Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38120649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"166","last_page":"176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5795999765396118,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5795999765396118,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.19850000739097595,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.01640000008046627,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7871999740600586},{"id":"https://openalex.org/keywords/infrared","display_name":"Infrared","score":0.7422999739646912},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.4020000100135803},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.37950000166893005},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.3671000003814697},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.321399986743927}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7871999740600586},{"id":"https://openalex.org/C158355884","wikidata":"https://www.wikidata.org/wiki/Q11388","display_name":"Infrared","level":2,"score":0.7422999739646912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6593000292778015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5055999755859375},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34119999408721924},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3005000054836273},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.2727000117301941}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccv51701.2025.00023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.14449","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14449","pdf_url":"https://arxiv.org/pdf/2507.14449","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.14449","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14449","pdf_url":"https://arxiv.org/pdf/2507.14449","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[{"id":"https://openalex.org/G7023371304","display_name":null,"funder_award_id":"62201058,62475016,62306311","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real-world":[0],"infrared":[1,31,51,67,88,132],"imagery":[2],"presents":[3],"unique":[4,47],"challenges":[5],"for":[6,65],"vision-language":[7],"models":[8],"due":[9],"to":[10,44,131],"the":[11,25,46,50,59,96,136],"scarcity":[12],"of":[13,49,107,114,139,148],"aligned":[14],"text":[15],"data":[16],"and":[17,110,142],"domain-specific":[18],"characteristics.":[19],"Although":[20],"existing":[21],"methods":[22],"have":[23],"advanced":[24],"field,":[26],"their":[27,42],"reliance":[28],"on":[29,145],"synthetic":[30],"images":[32,89],"generated":[33],"through":[34],"style":[35],"transfer":[36,122],"from":[37,100,129],"visible":[38,108,130],"images,":[39,68,109],"which":[40],"limits":[41],"ability":[43],"capture":[45],"characteristics":[48],"modality.":[52],"To":[53],"address":[54],"this,":[55],"we":[56,117],"propose":[57],"IRGPT,":[58],"first":[60],"multi-modal":[61],"large":[62],"language":[63],"model":[64],"real-world":[66],"built":[69],"upon":[70],"a":[71,119,146],"large-scale":[72],"InfraRed-Text":[73],"Dataset":[74],"(IR-TD)":[75],"comprising":[76],"over":[77],"260K":[78],"authentic":[79],"image-text":[80],"pairs.":[81],"The":[82],"proposed":[83],"IR-TD":[84],"dataset":[85],"contains":[86],"real":[87],"paired":[90],"with":[91,160],"meticulously":[92],"handcrafted":[93],"texts,":[94],"where":[95],"initial":[97],"drafts":[98],"originated":[99],"two":[101],"complementary":[102],"processes:":[103],"(1)":[104],"LLM-generated":[105],"descriptions":[106,113],"(2)":[111],"rule-based":[112],"annotations.":[115],"Furthermore,":[116],"introduce":[118],"bi-cross-modal":[120],"curriculum":[121],"learning":[123],"strategy":[124],"that":[125],"systematically":[126],"transfers":[127],"knowledge":[128],"domains":[133],"by":[134],"considering":[135],"difficulty":[137],"scores":[138],"both":[140],"infrared-visible":[141],"infrared-text.":[143],"Evaluated":[144],"benchmark":[147],"9":[149],"tasks":[150],"(e.g.,":[151],"recognition,":[152],"grounding),":[153],"IRGPT":[154],"achieves":[155],"state-of-the-art":[156],"performance":[157],"even":[158],"compared":[159],"larger-scale":[161],"models.":[162]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}