{"id":"https://openalex.org/W4402978451","doi":"https://doi.org/10.1109/tits.2024.3462795","title":"Transformer-Based Stereo-Aware 3D Object Detection From Binocular Images","display_name":"Transformer-Based Stereo-Aware 3D Object Detection From Binocular Images","publication_year":2024,"publication_date":"2024-09-30","ids":{"openalex":"https://openalex.org/W4402978451","doi":"https://doi.org/10.1109/tits.2024.3462795"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2024.3462795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2024.3462795","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/A5017943691","display_name":"Hanqing Sun","orcid":"https://orcid.org/0000-0002-8022-4172"},"institutions":[{"id":"https://openalex.org/I4210088164","display_name":"Changchun Institute of Optics, Fine Mechanics and Physics","ror":"https://ror.org/012rct222","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210088164"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hanqing Sun","raw_affiliation_strings":["Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, China"],"affiliations":[{"raw_affiliation_string":"Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, China","institution_ids":["https://openalex.org/I4210088164","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009590084","display_name":"Yanwei Pang","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Pang","raw_affiliation_strings":["Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China","School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037129512","display_name":"Jiale Cao","orcid":"https://orcid.org/0000-0002-5160-6841"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Cao","raw_affiliation_strings":["Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China","School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin Key Laboratory of Brain-Inspired Intelligence Technology, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089409762","display_name":"Jin Xie","orcid":"https://orcid.org/0000-0001-6978-8834"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Xie","raw_affiliation_strings":["School of Big Data and Software Engineering, Chongqing University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Big Data and Software Engineering, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107678602","display_name":"Xuelong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["School of Computer Science and the School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and the School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017943691"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210088164"],"apc_list":null,"apc_paid":null,"fwci":2.0994,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8871038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"25","issue":"12","first_page":"19675","last_page":"19687"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13579","display_name":"Image and Video Stabilization","score":0.9735000133514404,"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/T13579","display_name":"Image and Video Stabilization","score":0.9735000133514404,"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":0.9721999764442444,"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/T10638","display_name":"Optical measurement and interference techniques","score":0.9635000228881836,"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/computer-vision","display_name":"Computer vision","score":0.7722344398498535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7197748422622681},{"id":"https://openalex.org/keywords/stereopsis","display_name":"Stereopsis","score":0.6377578973770142},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5446618795394897},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4994058609008789},{"id":"https://openalex.org/keywords/binocular-disparity","display_name":"Binocular disparity","score":0.4619240164756775},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4524692893028259},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.24147909879684448},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.219483882188797},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0748370885848999}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7722344398498535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7197748422622681},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.6377578973770142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5446618795394897},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4994058609008789},{"id":"https://openalex.org/C90790637","wikidata":"https://www.wikidata.org/wiki/Q11681118","display_name":"Binocular disparity","level":3,"score":0.4619240164756775},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4524692893028259},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.24147909879684448},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.219483882188797},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0748370885848999},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2024.3462795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2024.3462795","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/G2199262417","display_name":null,"funder_award_id":"62206031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5074938571","display_name":null,"funder_award_id":"62271346","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5135811258","display_name":null,"funder_award_id":"2022ZD0160400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7594118645","display_name":null,"funder_award_id":"62401538","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2259424905","https://openalex.org/W2555618208","https://openalex.org/W2565639579","https://openalex.org/W2911486422","https://openalex.org/W2954174912","https://openalex.org/W2956908398","https://openalex.org/W2962807143","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963619659","https://openalex.org/W2963857746","https://openalex.org/W2991095133","https://openalex.org/W2991514044","https://openalex.org/W2997558685","https://openalex.org/W2997575304","https://openalex.org/W3034402935","https://openalex.org/W3034407526","https://openalex.org/W3034971973","https://openalex.org/W3035574168","https://openalex.org/W3035651586","https://openalex.org/W3035749845","https://openalex.org/W3090896893","https://openalex.org/W3096609285","https://openalex.org/W3096678291","https://openalex.org/W3108346482","https://openalex.org/W3114276215","https://openalex.org/W3130618527","https://openalex.org/W3157177884","https://openalex.org/W3175630421","https://openalex.org/W3204217726","https://openalex.org/W3205005447","https://openalex.org/W3206528488","https://openalex.org/W4200200310","https://openalex.org/W4205319213","https://openalex.org/W4206123889","https://openalex.org/W4225793049","https://openalex.org/W4312312588","https://openalex.org/W4312713480","https://openalex.org/W4312894406","https://openalex.org/W4319265052","https://openalex.org/W4323338774","https://openalex.org/W4366378409","https://openalex.org/W4367182782","https://openalex.org/W6620707391","https://openalex.org/W6638523607","https://openalex.org/W6757817989","https://openalex.org/W6764514022","https://openalex.org/W6766978945","https://openalex.org/W6771062828","https://openalex.org/W6780507750","https://openalex.org/W6784094891","https://openalex.org/W6802311648","https://openalex.org/W6803376173","https://openalex.org/W6838895621","https://openalex.org/W6839364997","https://openalex.org/W6844406868"],"related_works":["https://openalex.org/W98522529","https://openalex.org/W3179676481","https://openalex.org/W2390004782","https://openalex.org/W2114267838","https://openalex.org/W2102713649","https://openalex.org/W125675508","https://openalex.org/W1536406305","https://openalex.org/W4234766120","https://openalex.org/W2069381083","https://openalex.org/W2356962014"],"abstract_inverted_index":{"Transformers":[0,71,87],"have":[1],"shown":[2],"promising":[3],"progress":[4],"in":[5,24,33,88,147,228],"various":[6],"visual":[7],"object":[8,49,91,114],"detection":[9,14,50,202],"tasks,":[10],"including":[11],"monocular":[12],"2D/3D":[13],"and":[15,28,55,97,144,189,210,233],"surround-view":[16],"3D":[17,30,48,90,113,157],"detection.":[18],"More":[19],"importantly,":[20],"the":[21,25,29,73,83,117,129,156,161,183,206],"attention":[22],"mechanism":[23],"Transformer":[26],"model":[27,84],"information":[31,132,159,185],"extraction":[32],"binocular":[34,46,89,219],"stereo":[35,47,134,166,192],"are":[36],"both":[37,231],"similarity-based.":[38],"However,":[39],"directly":[40],"applying":[41],"existing":[42,70],"Transformer-based":[43,111],"detectors":[44],"to":[45,52,127,154,181,214],"leads":[51],"slow":[53],"convergence":[54],"significant":[56],"precision":[57,204,232],"drops.":[58],"We":[59],"argue":[60],"that":[61,66,69],"a":[62,110,119,170,198],"key":[63],"cause":[64],"of":[65,86,160,230],"defect":[67],"is":[68,125,138,145,179,223],"ignore":[72],"binocular-stereo-specific":[74],"image":[75,100,130,220],"correspondence":[76,101,131,137,184],"information.":[77,102],"In":[78,116],"this":[79,105],"paper,":[80],"we":[81,107,168],"explore":[82],"design":[85],"detection,":[92],"focusing":[93],"particularly":[94],"on":[95,205],"extracting":[96],"encoding":[98,153],"task-specific":[99],"To":[103,163],"achieve":[104],"goal,":[106],"present":[108],"TS3D,":[109,118],"Stereo-aware":[112],"detector.":[115],"Disparity-Aware":[120],"Positional":[121],"Encoding":[122],"(DAPE)":[123],"module":[124],"proposed":[126,195],"embed":[128],"into":[133],"features.":[135,193],"The":[136,177],"encoded":[139],"as":[140],"normalized":[141],"sub-pixel-level":[142],"disparity":[143],"used":[146],"conjunction":[148],"with":[149,225],"sinusoidal":[150],"2D":[151],"positional":[152],"provide":[155],"location":[158],"scene.":[162],"enrich":[164],"multi-scale":[165],"features,":[167],"propose":[169],"Stereo":[171],"Preserving":[172],"Feature":[173],"Pyramid":[174],"Network":[175],"(SPFPN).":[176],"SPFPN":[178],"designed":[180],"preserve":[182],"while":[186],"fusing":[187],"intra-scale":[188],"aggregating":[190],"cross-scale":[191],"Our":[194],"TS3D":[196],"achieves":[197],"41.29%":[199],"Moderate":[200],"Car":[201],"average":[203],"KITTI":[207],"test":[208],"set":[209],"takes":[211],"88":[212],"ms":[213],"detect":[215],"objects":[216],"from":[217],"each":[218],"pair.":[221],"It":[222],"competitive":[224],"advanced":[226],"counterparts":[227],"terms":[229],"inference":[234],"speed.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}