{"id":"https://openalex.org/W7162487921","doi":"https://doi.org/10.1109/3dv69130.2026.00045","title":"MonoSISTR: Monocular 3D Object Detection via Staged Iterative Structure and Target Refinement","display_name":"MonoSISTR: Monocular 3D Object Detection via Staged Iterative Structure and Target Refinement","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7162487921","doi":"https://doi.org/10.1109/3dv69130.2026.00045"},"language":null,"primary_location":{"id":"doi:10.1109/3dv69130.2026.00045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","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/A5137125125","display_name":"Genlin Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I927504317","display_name":"Nanchang Hangkong University","ror":"https://ror.org/0369pvp92","country_code":"CN","type":"education","lineage":["https://openalex.org/I927504317"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Genlin Zhou","raw_affiliation_strings":["Nanchang Hangkong University,Nanchang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanchang Hangkong University,Nanchang,China","institution_ids":["https://openalex.org/I927504317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137113067","display_name":"Cheng Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Feng","raw_affiliation_strings":["Beihang University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137157890","display_name":"Feng Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I927504317","display_name":"Nanchang Hangkong University","ror":"https://ror.org/0369pvp92","country_code":"CN","type":"education","lineage":["https://openalex.org/I927504317"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Lu","raw_affiliation_strings":["Nanchang Hangkong University,Nanchang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanchang Hangkong University,Nanchang,China","institution_ids":["https://openalex.org/I927504317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002097383","display_name":"Zige Wang","orcid":"https://orcid.org/0000-0002-2318-5103"},"institutions":[{"id":"https://openalex.org/I927504317","display_name":"Nanchang Hangkong University","ror":"https://ror.org/0369pvp92","country_code":"CN","type":"education","lineage":["https://openalex.org/I927504317"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zige Wang","raw_affiliation_strings":["Nanchang Hangkong University,Nanchang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanchang Hangkong University,Nanchang,China","institution_ids":["https://openalex.org/I927504317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137099080","display_name":"Zhen Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I927504317","display_name":"Nanchang Hangkong University","ror":"https://ror.org/0369pvp92","country_code":"CN","type":"education","lineage":["https://openalex.org/I927504317"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Chen","raw_affiliation_strings":["Nanchang Hangkong University,Nanchang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanchang Hangkong University,Nanchang,China","institution_ids":["https://openalex.org/I927504317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137099712","display_name":"Congxuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I927504317","display_name":"Nanchang Hangkong University","ror":"https://ror.org/0369pvp92","country_code":"CN","type":"education","lineage":["https://openalex.org/I927504317"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Congxuan Zhang","raw_affiliation_strings":["Nanchang Hangkong University,Nanchang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanchang Hangkong University,Nanchang,China","institution_ids":["https://openalex.org/I927504317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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":0.85172558,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"407","last_page":"416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.4131999909877777,"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":0.4131999909877777,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.07599999755620956,"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":0.04050000011920929,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5365999937057495},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4544999897480011},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.40119999647140503},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3418999910354614},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3197000026702881},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3125},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.2879999876022339}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7099000215530396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6923999786376953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.590499997138977},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5365999937057495},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3197000026702881},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3125},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/3dv69130.2026.00045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7299178015","display_name":null,"funder_award_id":"62222206,U25A20480,U2441241,62272209,62401243","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":44,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2150066425","https://openalex.org/W2520707372","https://openalex.org/W2560544142","https://openalex.org/W2768265037","https://openalex.org/W2799123546","https://openalex.org/W2953941229","https://openalex.org/W2963488291","https://openalex.org/W2963945905","https://openalex.org/W2964166085","https://openalex.org/W2972211064","https://openalex.org/W2981857055","https://openalex.org/W2998421254","https://openalex.org/W2999947750","https://openalex.org/W3034479628","https://openalex.org/W3034603747","https://openalex.org/W3035254347","https://openalex.org/W3035574168","https://openalex.org/W3096609285","https://openalex.org/W3108857005","https://openalex.org/W3114509423","https://openalex.org/W3128100939","https://openalex.org/W3170984066","https://openalex.org/W3176319743","https://openalex.org/W3176821088","https://openalex.org/W3187011621","https://openalex.org/W3191393167","https://openalex.org/W3199093552","https://openalex.org/W3204439495","https://openalex.org/W4200629618","https://openalex.org/W4214627427","https://openalex.org/W4312461898","https://openalex.org/W4312713480","https://openalex.org/W4312865155","https://openalex.org/W4313059105","https://openalex.org/W4317496717","https://openalex.org/W4321021640","https://openalex.org/W4383066343","https://openalex.org/W4390873008","https://openalex.org/W4393154112","https://openalex.org/W4402704555","https://openalex.org/W4402754236","https://openalex.org/W4405197164","https://openalex.org/W4413156733"],"related_works":[],"abstract_inverted_index":{"Monocular":[0],"3D":[1,21,67],"object":[2,7],"detection":[3],"aims":[4],"to":[5,30,48,75],"predict":[6],"category,":[8],"position,":[9],"size,":[10],"and":[11,42,87,128,156],"orientation":[12],"from":[13,24,73],"a":[14,63,94,121,132],"single":[15],"RGB":[16],"image.":[17],"Existing":[18],"DETR-based":[19],"monocular":[20,66],"detectors":[22],"suffer":[23],"maintaining":[25,167],"consistent":[26],"high-confidence":[27,107],"responses":[28],"due":[29],"weak":[31],"or":[32],"incomplete":[33],"target":[34,55,96],"features,":[35,109],"resulting":[36],"in":[37,58,159],"information":[38],"loss":[39],"for":[40,131],"distant":[41,155],"occluded":[43,157],"objects":[44],"during":[45],"encoding-decoding.":[46],"Firstly,":[47],"address":[49],"the":[50,112,136,160,171],"core":[51],"challenge":[52],"of":[53,115,135],"insufficient":[54],"feature":[56,85],"perception":[57,114],"complex":[59],"scenes,":[60],"we":[61,119],"propose":[62],"staged":[64],"iterative":[65],"detector":[68],"that":[69,99,142],"progressively":[70],"refines":[71],"targets":[72],"coarse":[74],"fine":[76],"through":[77],"multiple":[78],"paired":[79],"encoding-decoding":[80],"stages,":[81],"significantly":[82],"improving":[83],"both":[84],"utilization":[86],"network":[88],"convergence.":[89],"Furthermore,":[90],"each":[91],"stage":[92],"integrates":[93],"dynamic":[95],"iteration":[97],"module":[98],"continuously":[100],"enhances":[101],"query":[102],"representation":[103,134],"by":[104],"focusing":[105],"on":[106,151,170],"regional":[108],"thereby":[110],"enhancing":[111],"model's":[113],"potential":[116],"targets.":[117],"Finally,":[118],"design":[120],"dual-branch":[122],"depth":[123,137],"estimator":[124],"with":[125],"parallel":[126],"global":[127],"local":[129],"processing":[130],"comprehensive":[133],"feature.":[138],"Experimental":[139],"results":[140],"show":[141],"our":[143],"method":[144],"achieves":[145],"superior":[146],"performance":[147],"over":[148],"prior":[149],"approaches":[150],"challenging":[152],"scenarios":[153],"(e.g.,":[154],"objects)":[158],"KITTI":[161],"dataset":[162],"without":[163],"auxiliary":[164],"data,":[165],"while":[166],"competitive":[168],"accuracy":[169],"nuScenes":[172],"benchmark":[173],"under":[174],"frontal-view":[175],"settings.":[176]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-28T00:00:00"}