{"id":"https://openalex.org/W4385453280","doi":"https://doi.org/10.1109/tip.2023.3299190","title":"MuTrans: Multiple Transformers for Fusing Feature Pyramid on 2D and 3D Object Detection","display_name":"MuTrans: Multiple Transformers for Fusing Feature Pyramid on 2D and 3D Object Detection","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385453280","doi":"https://doi.org/10.1109/tip.2023.3299190","pmid":"https://pubmed.ncbi.nlm.nih.gov/37527315"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3299190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3299190","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5026451492","display_name":"Bangquan Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Bangquan Xie","raw_affiliation_strings":["School of Civil Engineering and Transportation, South China University of Technology, Guangzhou, China","Department of Automotive Engineering, Clemson University International Center for Automotive Research (CU-ICAR), Greenville, SC, USA"],"raw_orcid":"https://orcid.org/0000-0002-4500-8941","affiliations":[{"raw_affiliation_string":"School of Civil Engineering and Transportation, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"Department of Automotive Engineering, Clemson University International Center for Automotive Research (CU-ICAR), Greenville, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101825563","display_name":"Liang Yang","orcid":"https://orcid.org/0000-0002-3454-6242"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Yang","raw_affiliation_strings":["Apple, Inc., Cupertino, CA, USA","Apple Inc, 1 Infinite Loop, Cupertino, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-3454-6242","affiliations":[{"raw_affiliation_string":"Apple, Inc., Cupertino, CA, USA","institution_ids":["https://openalex.org/I4210153776"]},{"raw_affiliation_string":"Apple Inc, 1 Infinite Loop, Cupertino, California, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028860907","display_name":"Ailin Wei","orcid":"https://orcid.org/0000-0002-8626-3973"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ailin Wei","raw_affiliation_strings":["Department of Bioengineering, Clemson University, Clemson, SC, USA"],"raw_orcid":"https://orcid.org/0000-0002-8626-3973","affiliations":[{"raw_affiliation_string":"Department of Bioengineering, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079266909","display_name":"Xiaoxiong Weng","orcid":"https://orcid.org/0000-0002-8215-8463"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxiong Weng","raw_affiliation_strings":["School of Civil Engineering and Transportation, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Civil Engineering and Transportation, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100451327","display_name":"Bing Li","orcid":"https://orcid.org/0000-0003-4987-6129"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bing Li","raw_affiliation_strings":["Department of Automotive Engineering, Clemson University International Center for Automotive Research (CU-ICAR), Greenville, SC, USA"],"raw_orcid":"https://orcid.org/0000-0003-4987-6129","affiliations":[{"raw_affiliation_string":"Department of Automotive Engineering, Clemson University International Center for Automotive Research (CU-ICAR), Greenville, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8509,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.75102629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"4407","last_page":"4415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9916999936103821,"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/object-detection","display_name":"Object detection","score":0.747946560382843},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.741769552230835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7052819728851318},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6759252548217773},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5837922692298889},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.523811936378479},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5080950260162354},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.49714019894599915},{"id":"https://openalex.org/keywords/backbone-network","display_name":"Backbone network","score":0.4808105230331421},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.47939324378967285},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4588935375213623},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4257747530937195},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17763885855674744}],"concepts":[{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.747946560382843},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.741769552230835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7052819728851318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6759252548217773},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5837922692298889},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.523811936378479},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5080950260162354},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.49714019894599915},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.4808105230331421},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.47939324378967285},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4588935375213623},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4257747530937195},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17763885855674744},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3299190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3299190","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:37527315","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37527315","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2601564443","https://openalex.org/W2752782242","https://openalex.org/W2951517617","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963400571","https://openalex.org/W2963706010","https://openalex.org/W2963857746","https://openalex.org/W2997322677","https://openalex.org/W3009593063","https://openalex.org/W3014641072","https://openalex.org/W3015468748","https://openalex.org/W3034314779","https://openalex.org/W3035316790","https://openalex.org/W3092462694","https://openalex.org/W3096609285","https://openalex.org/W3109675406","https://openalex.org/W3131922516","https://openalex.org/W3166089996","https://openalex.org/W3166470370","https://openalex.org/W3172087149","https://openalex.org/W3172863135","https://openalex.org/W3178887474","https://openalex.org/W3201264086","https://openalex.org/W3203003533","https://openalex.org/W3205005447","https://openalex.org/W3209035582","https://openalex.org/W3209200209","https://openalex.org/W3214740560","https://openalex.org/W3216015562","https://openalex.org/W3217335336","https://openalex.org/W4214624153","https://openalex.org/W4287762561","https://openalex.org/W4293112749","https://openalex.org/W4312707458","https://openalex.org/W4312823573","https://openalex.org/W4312954223","https://openalex.org/W4313149358","https://openalex.org/W4320002812","https://openalex.org/W4382466543","https://openalex.org/W4383066393","https://openalex.org/W4385245566","https://openalex.org/W4386076066","https://openalex.org/W6696085341","https://openalex.org/W6714138976","https://openalex.org/W6743731764","https://openalex.org/W6747139287","https://openalex.org/W6772381481","https://openalex.org/W6776048684","https://openalex.org/W6779435783","https://openalex.org/W6784094891","https://openalex.org/W6797586992","https://openalex.org/W6803021174","https://openalex.org/W6804021995","https://openalex.org/W6804170900","https://openalex.org/W6839131839","https://openalex.org/W6839901555","https://openalex.org/W6842385943"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W4249847449","https://openalex.org/W2894651257","https://openalex.org/W2993564273","https://openalex.org/W4286907753","https://openalex.org/W3208389169","https://openalex.org/W3134004915","https://openalex.org/W3200590620","https://openalex.org/W4200172193","https://openalex.org/W4303926741"],"abstract_inverted_index":{"One":[0],"of":[1,5,174,209,213],"the":[2,6,9,80,143,149,169,172,178,185,205,214],"major":[3],"components":[4],"neural":[7],"network,":[8],"feature":[10,35,63],"pyramid":[11,64],"plays":[12],"a":[13,28,43,224,244],"vital":[14],"part":[15],"in":[16,22,65,168,218,234],"perception":[17],"tasks,":[18],"like":[19],"object":[20,38,220,236],"detection":[21,207,227,237,248],"autonomous":[23],"driving.":[24],"But":[25],"it":[26],"is":[27,181],"challenge":[29],"to":[30,61,183,193],"fuse":[31,62],"multi-level":[32,133],"and":[33,129,145,154,189,198,257],"multi-sensor":[34],"pyramids":[36],"for":[37,107,125,132,252],"detection.":[39,221],"This":[40],"paper":[41],"proposes":[42],"simple":[44],"yet":[45],"effective":[46],"framework":[47],"named":[48],"<italic":[49,53,57,93,97,103,111,115,121,150,155,159,164,230],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[50,54,58,94,98,104,112,116,122,151,156,160,165,231],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">MuTrans</i>":[51],"(":[52,102,120,163],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Mu</i>":[55],"ltiple":[56],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Trans</i>":[59],"formers)":[60],"single-stream":[66],"2D":[67],"detector":[68],"or":[69],"two-stream":[70],"3D":[71,247],"detector.":[72],"The":[73],"MuTrans":[74,86,136,210,222],"based":[75],"on":[76,79,229,238,255,264],"encoder-decoder":[77],"focuses":[78],"significant":[81,140],"features":[82],"via":[83],"multiple":[84],"Transformers.":[85],"encoder":[87,170],"uses":[88],"three":[89],"innovative":[90],"self-attention":[91],"mechanisms:":[92],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">S</i>":[95],"patial-wise":[96],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">B</i>":[99],"oxAlign":[100],"attention":[101,119,131],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">SB</i>":[105],")":[106,124,167],"low-level":[108],"spatial":[109],"locations,":[110],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">C</i>":[113],"ontext-wise":[114],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">A</i>":[117],"ffinity":[118],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">CA</i>":[123],"high-level":[126,130],"context":[127,146],"information,":[128],"features.":[134],"Then":[135],"decoder":[137],"processes":[138],"these":[139],"proposals":[141],"including":[142],"RoI":[144],"affinity.":[147],"Besides,":[148],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">L</i>":[152],"ow":[153],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">H</i>":[157],"igh-level":[158],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">F</i>":[161],"usion":[162],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">LHF</i>":[166],"reduces":[171],"number":[173],"computational":[175,196],"parameters.":[176],"And":[177],"Pre-LN":[179,190],"[1]":[180],"utilized":[182],"accelerate":[184],"training":[186,200],"convergence.":[187,201],"LHF":[188],"are":[191],"proven":[192],"reduce":[194],"self-attention\u2019s":[195],"complexity":[197],"slow":[199],"Our":[202],"result":[203],"demonstrates":[204,223],"higher":[206,226,246,259],"accuracy":[208,228,249],"than":[211],"that":[212],"baseline":[215],"method,":[216],"particularly":[217],"small":[219,235,253],"2.1":[225],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">AP<sub>S</sub></i>":[232],"index":[233,261],"MS-COCO":[239],"2017":[240],"with":[241],"ResNeXt-101":[242],"backbone,":[243],"2.18":[245],"(moderate":[250],"difficulty)":[251],"object-pedestrian":[254],"KITTI,":[256],"6.85":[258],"RC":[260],"(Town05":[262],"Long)":[263],"CARLA":[265],"urban":[266],"driving":[267],"simulator":[268],"platform.":[269]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}