{"id":"https://openalex.org/W4402351102","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650924","title":"Focus on your Geometry: Exploiting the Potential of Multi-Frame Stereo Depth Estimation Pre-training for 3D Object Detection","display_name":"Focus on your Geometry: Exploiting the Potential of Multi-Frame Stereo Depth Estimation Pre-training for 3D Object Detection","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351102","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650924"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650924","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5057489840","display_name":"Zichen Wang","orcid":"https://orcid.org/0000-0002-2532-4816"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zichen Wang","raw_affiliation_strings":["JD Logistics,Autonomous Driving Department of X Division,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Logistics,Autonomous Driving Department of X Division,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066962884","display_name":"Zhuokun Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuokun Yao","raw_affiliation_strings":["JD Logistics,Autonomous Driving Department of X Division,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Logistics,Autonomous Driving Department of X Division,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112468275","display_name":"Jianwei Zhang","orcid":"https://orcid.org/0000-0002-3178-0607"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Zhang","raw_affiliation_strings":["JD Logistics,Autonomous Driving Department of X Division,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Logistics,Autonomous Driving Department of X Division,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005687284","display_name":"Ye Zheng","orcid":"https://orcid.org/0000-0003-1484-8646"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Zheng","raw_affiliation_strings":["JD Logistics,Autonomous Driving Department of X Division,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Logistics,Autonomous Driving Department of X Division,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714173","display_name":"Zhengyuan Zhang","orcid":"https://orcid.org/0000-0003-2383-7738"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyuan Zhang","raw_affiliation_strings":["JD Logistics,Autonomous Driving Department of X Division,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Logistics,Autonomous Driving Department of X Division,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011138272","display_name":"Shuang Deng","orcid":"https://orcid.org/0000-0001-5844-1093"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Deng","raw_affiliation_strings":["JD Logistics,Autonomous Driving Department of X Division,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Logistics,Autonomous Driving Department of X Division,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100629029","display_name":"Yajing Liu","orcid":"https://orcid.org/0000-0001-5467-5976"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yajing Liu","raw_affiliation_strings":["JD Logistics,Autonomous Driving Department of X Division,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Logistics,Autonomous Driving Department of X Division,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115594348","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0002-9071-6859"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":["JD Logistics,Autonomous Driving Department of X Division,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Logistics,Autonomous Driving Department of X Division,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13147959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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/focus","display_name":"Focus (optics)","score":0.747921347618103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6688056588172913},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.656294584274292},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6407910585403442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6372695565223694},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6088405251502991},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5620201826095581},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5581282377243042},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4161662459373474},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.35796764492988586},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2007429301738739},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16434746980667114},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09909048676490784},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.08975553512573242},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.059900641441345215}],"concepts":[{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.747921347618103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6688056588172913},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.656294584274292},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6407910585403442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6372695565223694},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6088405251502991},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5620201826095581},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5581282377243042},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4161662459373474},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.35796764492988586},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2007429301738739},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16434746980667114},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09909048676490784},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.08975553512573242},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.059900641441345215},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650924","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2468368736","https://openalex.org/W2555618208","https://openalex.org/W2897529137","https://openalex.org/W2926429807","https://openalex.org/W2962793285","https://openalex.org/W2963351448","https://openalex.org/W2963727135","https://openalex.org/W2968296999","https://openalex.org/W2985066174","https://openalex.org/W3034524082","https://openalex.org/W3034530552","https://openalex.org/W3035254347","https://openalex.org/W3035461736","https://openalex.org/W3035574168","https://openalex.org/W3109395584","https://openalex.org/W3173476881","https://openalex.org/W3204267695","https://openalex.org/W3215100485","https://openalex.org/W4214558638","https://openalex.org/W4224947594","https://openalex.org/W4225793049","https://openalex.org/W4226305814","https://openalex.org/W4303443326","https://openalex.org/W4310561607","https://openalex.org/W4312660290","https://openalex.org/W4312894406","https://openalex.org/W4378468525","https://openalex.org/W4382450829","https://openalex.org/W4382464460","https://openalex.org/W4385245566","https://openalex.org/W4388692139","https://openalex.org/W4390872833","https://openalex.org/W4390874598","https://openalex.org/W4396941548","https://openalex.org/W6631190155","https://openalex.org/W6797298677","https://openalex.org/W6799331316","https://openalex.org/W6802311648","https://openalex.org/W6810001583","https://openalex.org/W6811230113","https://openalex.org/W6845491643","https://openalex.org/W6847112178","https://openalex.org/W6853295911"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Existing":[0],"camera-based":[1,42,90,131,184],"3D":[2,43,72,91,118,132],"object":[3,44,73,92,133],"detection":[4,74,134,145,175],"methods":[5],"yield":[6],"inaccurate":[7],"position,":[8],"scale,":[9],"and":[10,102,106,173,182],"orientation":[11],"results":[12,153],"due":[13],"to":[14,115,136],"the":[15,39,55,60,113,160,168],"inherent":[16],"challenge":[17],"of":[18,41,178],"ill-posed":[19],"depth":[20,31,85],"estimation":[21,32,86],"from":[22,33,121,163],"2D":[23],"images.":[24],"Recent":[25],"research":[26],"has":[27],"demonstrated":[28],"that":[29,48,158],"pre-training":[30,87],"a":[34,83,96,103],"single":[35],"frame":[36],"substantially":[37],"enhances":[38],"quality":[40],"detection.":[45,93],"We":[46],"hypothesize":[47],"integrating":[49],"multi-view":[50],"stereo":[51,125],"matching":[52],"technology":[53],"into":[54],"pretraining":[56],"process":[57],"can":[58,165],"equip":[59],"backbone":[61,114,141],"model":[62],"with":[63],"superior":[64],"geometric":[65,119],"feature":[66],"extraction":[67],"capabilities,":[68],"thereby":[69,143],"further":[70],"improving":[71],"performance.":[75],"Building":[76],"upon":[77],"this":[78],"premise,":[79],"we":[80],"propose":[81],"MVS3D,":[82],"novel":[84],"method":[88,128],"for":[89],"MVS3D":[94,164],"incorporates":[95],"VMS":[97],"(Video-stream-based":[98],"Multi-view":[99],"Stereo)":[100],"module":[101],"PME":[104],"(Pose":[105],"Motion":[107],"Estimation)":[108],"module,":[109],"which":[110],"collectively":[111],"encourage":[112],"explicitly":[116],"learning":[117],"information":[120],"image":[122],"streams":[123],"through":[124],"matching.":[126],"Our":[127],"enables":[129],"existing":[130,180],"frameworks":[135],"seamlessly":[137],"integrate":[138],"our":[139],"pre-trained":[140,161],"weight,":[142],"enhancing":[144],"performance":[146],"without":[147],"necessitating":[148],"extensive":[149],"modifications.":[150],"Extensive":[151],"experimental":[152],"on":[154],"nuScenes":[155,174],"dataset":[156],"show":[157],"loading":[159],"weight":[162],"significantly":[166],"improve":[167],"mean":[169],"average":[170],"precision":[171],"(mAP)":[172],"score":[176],"(NDS)":[177],"both":[179],"single-frame":[181],"multi-frame":[183],"methods.":[185]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}