{"id":"https://openalex.org/W4366378409","doi":"https://doi.org/10.1109/tits.2023.3266487","title":"Multi-Modal Feature Pyramid Transformer for RGB-Infrared Object Detection","display_name":"Multi-Modal Feature Pyramid Transformer for RGB-Infrared Object Detection","publication_year":2023,"publication_date":"2023-04-19","ids":{"openalex":"https://openalex.org/W4366378409","doi":"https://doi.org/10.1109/tits.2023.3266487"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2023.3266487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2023.3266487","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-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/A5101408827","display_name":"Yaohui Zhu","orcid":"https://orcid.org/0000-0003-4091-4782"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaohui Zhu","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4091-4782","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100745402","display_name":"Xiaoyu Sun","orcid":"https://orcid.org/0009-0005-1249-142X"},"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":"Xiaoyu Sun","raw_affiliation_strings":["School of Computer, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100415842","display_name":"Miao Wang","orcid":"https://orcid.org/0000-0002-4102-8582"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao Wang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022334521","display_name":"Hua Huang","orcid":"https://orcid.org/0000-0003-2587-1702"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Huang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2587-1702","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.0422,"has_fulltext":false,"cited_by_count":92,"citation_normalized_percentile":{"value":0.98900276,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"24","issue":"9","first_page":"9984","last_page":"9995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9980999827384949,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.993399977684021,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7632273435592651},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6812281012535095},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6526274681091309},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6231058835983276},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.5957233905792236},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.547595202922821},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5463261604309082},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5399399399757385},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5265929102897644},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.48083290457725525},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4424195885658264},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.41041332483291626},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1821460723876953},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16684290766716003}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7632273435592651},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6812281012535095},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6526274681091309},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6231058835983276},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5957233905792236},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.547595202922821},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5463261604309082},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5399399399757385},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5265929102897644},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.48083290457725525},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4424195885658264},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.41041332483291626},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1821460723876953},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16684290766716003},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2023.3266487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2023.3266487","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2865637635","display_name":null,"funder_award_id":"62202058","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":72,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1910108985","https://openalex.org/W2037227137","https://openalex.org/W2194775991","https://openalex.org/W2281954672","https://openalex.org/W2560023338","https://openalex.org/W2565639579","https://openalex.org/W2630837129","https://openalex.org/W2741620214","https://openalex.org/W2788097838","https://openalex.org/W2792925809","https://openalex.org/W2887564556","https://openalex.org/W2913889214","https://openalex.org/W2929607865","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963188557","https://openalex.org/W2963263347","https://openalex.org/W2963351448","https://openalex.org/W2963579094","https://openalex.org/W2963815618","https://openalex.org/W2963857746","https://openalex.org/W2964027659","https://openalex.org/W2968906080","https://openalex.org/W2987131085","https://openalex.org/W3008115128","https://openalex.org/W3033210410","https://openalex.org/W3036931590","https://openalex.org/W3084389333","https://openalex.org/W3090763579","https://openalex.org/W3096609285","https://openalex.org/W3106728613","https://openalex.org/W3114896399","https://openalex.org/W3116967329","https://openalex.org/W3118570274","https://openalex.org/W3130394099","https://openalex.org/W3131500599","https://openalex.org/W3133696297","https://openalex.org/W3138516171","https://openalex.org/W3139633126","https://openalex.org/W3158128549","https://openalex.org/W3159481202","https://openalex.org/W3164576087","https://openalex.org/W3165924482","https://openalex.org/W3168649818","https://openalex.org/W3171516518","https://openalex.org/W3171583481","https://openalex.org/W3175199633","https://openalex.org/W3179869055","https://openalex.org/W3186570689","https://openalex.org/W3194643899","https://openalex.org/W3195903836","https://openalex.org/W3206600220","https://openalex.org/W3206968953","https://openalex.org/W3209478434","https://openalex.org/W3209635225","https://openalex.org/W4200632941","https://openalex.org/W4214493665","https://openalex.org/W4214614183","https://openalex.org/W4313007055","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6639102338","https://openalex.org/W6726497184","https://openalex.org/W6739901393","https://openalex.org/W6753836424","https://openalex.org/W6779248606","https://openalex.org/W6787826751","https://openalex.org/W6790690058","https://openalex.org/W6841129745","https://openalex.org/W6845935626"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W4306353150","https://openalex.org/W8219677","https://openalex.org/W2168054807","https://openalex.org/W2058990474","https://openalex.org/W2026860389","https://openalex.org/W2043363698","https://openalex.org/W3207883763","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"RGB-Infrared":[0,20,56,202],"multi-modal":[1],"object":[2,21,73],"detection":[3,22,203],"utilizes":[4],"diverse":[5],"and":[6,92,106,122],"complementary":[7,51,94,148],"information,":[8],"showing":[9],"some":[10,54],"advantages":[11],"in":[12,36,72,130],"intelligent":[13],"transportation":[14],"field.":[15],"The":[16,30,87,111,133],"main":[17],"challenge":[18],"of":[19,32,61,128,192],"is":[23,34,179,209],"how":[24],"to":[25,48,82,96,118,146,171,186,211],"fuse":[26,83],"the":[27,59,84,125,154,206],"two":[28,37,85,201],"modalities.":[29,86,152,197],"difficulty":[31,60],"fusion":[33],"reflected":[35],"aspects:":[38],"1)":[39],"large":[40],"visual":[41],"differences":[42],"between":[43,141,165,190],"modalities":[44],"make":[45],"it":[46],"difficult":[47],"learn":[49,147,161],"effective":[50],"features,":[52],"2)":[53],"misaligned":[55,172],"images":[57],"increase":[58],"fusion.":[62],"To":[63],"this":[64],"end,":[65],"based":[66],"on":[67,200],"feature":[68,103,108,113,135,139,156],"pyramid":[69,104,109,114,136,157],"commonly":[70],"used":[71],"detection,":[74],"we":[75],"propose":[76],"Multi-modal":[77],"Feature":[78],"Pyramid":[79],"Transformer":[80],"(MFPT)":[81],"proposed":[88,207],"MFPT":[89,185],"learns":[90],"semantic":[91,126],"modal":[93,99],"information":[95],"enhance":[97],"each":[98,131,144],"features":[100,117,129,149],"via":[101],"intra-modal":[102,112],"transformer":[105,115,137,158],"inter-modal":[107,134,155],"transformer.":[110],"enables":[116],"interact":[119],"across":[120],"space":[121],"scales,":[123],"improving":[124],"representations":[127],"modality.":[132],"conducts":[138],"interaction":[140],"modalities,":[142,166],"enabling":[143],"modality":[145],"from":[150],"other":[151],"Meanwhile,":[153],"can":[159],"also":[160],"distance":[162],"independent":[163],"dependencies":[164],"which":[167],"are":[168],"not":[169],"sensitive":[170],"images.":[173],"Furthermore,":[174],"a":[175],"local":[176],"attention":[177],"mechanism":[178],"introduced":[180],"within":[181],"different":[182,193,196],"windows":[183],"into":[184],"achieve":[187],"efficient":[188],"correlation":[189],"regions":[191],"scales":[194],"or":[195],"Experimental":[198],"results":[199],"datasets":[204],"demonstrate":[205],"method":[208],"superior":[210],"state-of-the-art":[212],"methods.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":23},{"year":2025,"cited_by_count":44},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}