{"id":"https://openalex.org/W7138194557","doi":"https://doi.org/10.1609/aaai.v40i32.39928","title":"DuGI-MAE: Improving Infrared Mask Autoencoders via Dual-Domain Guidance","display_name":"DuGI-MAE: Improving Infrared Mask Autoencoders via Dual-Domain Guidance","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138194557","doi":"https://doi.org/10.1609/aaai.v40i32.39928"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i32.39928","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i32.39928","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i32.39928","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yinghui Xing","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yinghui Xing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoting Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoting Su","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shizhou Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shizhou Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Donghao Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donghao Chu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Di Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Xu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.58617818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"32","first_page":"27135","last_page":"27143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.3095000088214874,"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":0.3095000088214874,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.14800000190734863,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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":0.08139999955892563,"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/masking","display_name":"Masking (illustration)","score":0.602400004863739},{"id":"https://openalex.org/keywords/infrared","display_name":"Infrared","score":0.517300009727478},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4544000029563904},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.42730000615119934},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4108999967575073},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4041999876499176},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.3458000123500824},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.33660000562667847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7179999947547913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6534000039100647},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.602400004863739},{"id":"https://openalex.org/C158355884","wikidata":"https://www.wikidata.org/wiki/Q11388","display_name":"Infrared","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47589999437332153},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.42730000615119934},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4108999967575073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i32.39928","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i32.39928","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i32.39928","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i32.39928","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.5556327104568481,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Infrared":[0,91],"imaging":[1],"plays":[2],"a":[3,88,101,121,150],"critical":[4],"role":[5],"in":[6,35,140],"low-light":[7],"and":[8,53,78,132,161,183,199],"adverse":[9],"weather":[10],"conditions.":[11],"However,":[12],"due":[13],"to":[14,115],"the":[15,68,190,193],"distinct":[16],"characteristics":[17],"of":[18,70,75,80,192],"infrared":[19,36,45,57,141,152,178],"images,":[20],"existing":[21],"foundation":[22,46,92],"models":[23],"such":[24],"as":[25,49],"Masked":[26],"Autoencoder":[27],"(MAE)":[28],"trained":[29],"on":[30,55,95,106,166],"visible":[31],"data":[32],"perform":[33],"suboptimal":[34],"image":[37,153],"interpretation":[38],"tasks.":[39],"To":[40,143],"bridge":[41],"this":[42,84],"gap,":[43],"an":[44],"model":[47,93],"known":[48],"InfMAE":[50,62],"was":[51],"developed":[52],"pre-trained":[54],"large-scale":[56,145],"datasets.":[58],"Despite":[59],"its":[60],"effectiveness,":[61],"still":[63],"faces":[64],"several":[65],"limitations,":[66],"including":[67,177],"omission":[69],"informative":[71],"tokens,":[72],"insufficient":[73],"modeling":[74],"global":[76,129],"associations,":[77],"neglect":[79],"non-uniform":[81,135],"noise.":[82],"In":[83],"paper,":[85],"we":[86,99,119,147],"propose":[87],"Dual-domain":[89],"Guided":[90],"based":[94,105],"MAE":[96],"(DuGI-MAE).":[97],"First,":[98],"design":[100],"deterministic":[102],"masking":[103],"strategy":[104],"token":[107,130],"entropy,":[108],"preserving":[109],"only":[110],"high-entropy":[111],"tokens":[112],"for":[113],"reconstruction":[114],"enhance":[116],"informativeness.":[117],"Next,":[118],"introduce":[120],"Dual-Domain":[122],"Guidance":[123],"(DDG)":[124],"module,":[125],"which":[126],"simultaneously":[127],"captures":[128],"relationships":[131],"adaptively":[133],"filters":[134],"background":[136],"noise":[137],"commonly":[138],"present":[139],"imagery.":[142],"facilitate":[144],"pretraining,":[146],"construct":[148],"Inf-590K,":[149,167],"comprehensive":[151],"dataset":[154],"encompassing":[155],"diverse":[156],"scenes,":[157],"various":[158,174],"target":[159,185],"types,":[160],"multiple":[162],"spatial":[163],"resolutions.":[164],"Pretrained":[165],"DuGI-MAE":[168],"demonstrates":[169],"strong":[170],"generalization":[171],"capabilities":[172],"across":[173],"downstream":[175],"tasks,":[176],"object":[179],"detection,":[180],"semantic":[181],"segmentation,":[182],"small":[184],"detection.":[186],"Experimental":[187],"results":[188],"validate":[189],"superiority":[191],"proposed":[194],"method":[195],"over":[196],"both":[197],"supervised":[198],"self-supervised":[200],"comparison":[201],"methods.":[202]},"counts_by_year":[],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2026-02-07T00:00:00"}