{"id":"https://openalex.org/W4285606661","doi":"https://doi.org/10.24963/ijcai.2022/116","title":"AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection","display_name":"AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285606661","doi":"https://doi.org/10.24963/ijcai.2022/116"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/116","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/116","pdf_url":"https://www.ijcai.org/proceedings/2022/0116.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2022/0116.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100678098","display_name":"Zehui Chen","orcid":"https://orcid.org/0000-0002-1843-4478"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehui Chen","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032381238","display_name":"Zhenyu Li","orcid":"https://orcid.org/0009-0006-9212-6904"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Li","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062999404","display_name":"Shiquan Zhang","orcid":"https://orcid.org/0009-0009-7112-2463"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiquan Zhang","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065691762","display_name":"Liangji Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liangji Fang","raw_affiliation_strings":["Sensetime Research","SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sensetime Research","institution_ids":[]},{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102871046","display_name":"Qinhong Jiang","orcid":"https://orcid.org/0000-0002-5509-7247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinhong Jiang","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101902561","display_name":"Feng Zhao","orcid":"https://orcid.org/0000-0003-3788-4455"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhao","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033444412","display_name":"Bolei Zhou","orcid":"https://orcid.org/0000-0003-4030-0684"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bolei Zhou","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418988","display_name":"Hang Zhao","orcid":"https://orcid.org/0009-0008-7252-3827"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Zhao","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.2945,"has_fulltext":true,"cited_by_count":144,"citation_normalized_percentile":{"value":0.98857772,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"827","last_page":"833"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.993399977684021,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9829999804496765,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7492551207542419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7468114495277405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7344548106193542},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.7177581787109375},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6236922740936279},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5113272070884705},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5062898397445679},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4821767210960388},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4460575580596924},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.43407773971557617}],"concepts":[{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7492551207542419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7468114495277405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7344548106193542},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.7177581787109375},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6236922740936279},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5113272070884705},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5062898397445679},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4821767210960388},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4460575580596924},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.43407773971557617},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/116","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/116","pdf_url":"https://www.ijcai.org/proceedings/2022/0116.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/116","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/116","pdf_url":"https://www.ijcai.org/proceedings/2022/0116.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320325599","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285606661.pdf","grobid_xml":"https://content.openalex.org/works/W4285606661.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2468368736","https://openalex.org/W2555618208","https://openalex.org/W2560544142","https://openalex.org/W2769205412","https://openalex.org/W2769571673","https://openalex.org/W2774996270","https://openalex.org/W2894705404","https://openalex.org/W2897529137","https://openalex.org/W2903870443","https://openalex.org/W2905076052","https://openalex.org/W2915206464","https://openalex.org/W2932447084","https://openalex.org/W2949708697","https://openalex.org/W2962807143","https://openalex.org/W2963091558","https://openalex.org/W2963400571","https://openalex.org/W2963727135","https://openalex.org/W2964062501","https://openalex.org/W2967324759","https://openalex.org/W2968296999","https://openalex.org/W2989996808","https://openalex.org/W2996166203","https://openalex.org/W2997643725","https://openalex.org/W3008105217","https://openalex.org/W3017930107","https://openalex.org/W3035461736","https://openalex.org/W3042403800","https://openalex.org/W3082772998","https://openalex.org/W3107819843","https://openalex.org/W3108426750","https://openalex.org/W3117804044","https://openalex.org/W3130463448","https://openalex.org/W3167095230","https://openalex.org/W3207231145","https://openalex.org/W3213288297","https://openalex.org/W4287265385","https://openalex.org/W4385245566","https://openalex.org/W6786614245","https://openalex.org/W6803771590","https://openalex.org/W6863994431","https://openalex.org/W6864014924"],"related_works":["https://openalex.org/W2283162247","https://openalex.org/W4212983513","https://openalex.org/W2524507886","https://openalex.org/W2314488738","https://openalex.org/W2052518016","https://openalex.org/W2771653066","https://openalex.org/W4293067784","https://openalex.org/W4312857205","https://openalex.org/W2090093270","https://openalex.org/W1781672457"],"abstract_inverted_index":{"Object":[0],"detection":[1],"through":[2,126],"either":[3],"RGB":[4],"images":[5],"or":[6],"the":[7,60,64,81,111,128,155,169],"LiDAR":[8],"point":[9,67],"clouds":[10,68],"has":[11],"been":[12],"extensively":[13],"explored":[14],"in":[15,86],"autonomous":[16],"driving.":[17],"However,":[18],"it":[19],"remains":[20],"challenging":[21],"to":[22,31,79,100,147],"make":[23],"these":[24],"two":[25],"data":[26],"sources":[27],"complementary":[28],"and":[29,66,89,150,157],"beneficial":[30],"each":[32,107],"other.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37,58,117],"propose":[38],"AutoAlign,":[39],"an":[40],"automatic":[41],"feature":[42,95,115,123,132,136],"fusion":[43],"strategy":[44],"for":[45,106],"3D":[46],"object":[47],"detection.":[48],"Instead":[49],"of":[50,83],"establishing":[51],"deterministic":[52],"correspondence":[53],"with":[54,69,134],"camera":[55],"projection":[56],"matrix,":[57],"model":[59,78,129,164],"mapping":[61],"relationship":[62],"between":[63],"image":[65,104],"a":[70,87,93,120],"learnable":[71],"alignment":[72,82,96],"map.":[73],"This":[74],"map":[75],"enables":[76],"our":[77,143,162],"automate":[80],"non-homogenous":[84],"features":[85,105],"dynamic":[88],"data-driven":[90],"manner.":[91],"Specifically,":[92],"cross-attention":[94],"module":[97],"is":[98],"devised":[99],"adaptively":[101],"aggregate":[102],"pixel-level":[103],"voxel.":[108],"To":[109],"enhance":[110],"semantic":[112],"consistency":[113],"during":[114],"alignment,":[116],"also":[118],"design":[119],"self-supervised":[121],"cross-modal":[122],"interaction":[124],"module,":[125],"which":[127],"can":[130,145],"learn":[131],"aggregation":[133],"instance-level":[135],"guidance.":[137],"Extensive":[138],"experimental":[139],"results":[140],"show":[141],"that":[142],"approach":[144],"lead":[146],"2.3":[148],"mAP":[149,152],"7.0":[151],"improvements":[153],"on":[154,168],"KITTI":[156],"nuScenes":[158,170],"datasets":[159],"respectively.":[160],"Notably,":[161],"best":[163],"reaches":[165],"70.9":[166],"NDS":[167],"testing":[171],"leaderboard,":[172],"achieving":[173],"competitive":[174],"performance":[175],"among":[176],"various":[177],"state-of-the-arts.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":43},{"year":2024,"cited_by_count":52},{"year":2023,"cited_by_count":35},{"year":2022,"cited_by_count":3}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}