{"id":"https://openalex.org/W4401567667","doi":"https://doi.org/10.1109/tpami.2024.3443335","title":"Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection","display_name":"Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection","publication_year":2024,"publication_date":"2024-08-14","ids":{"openalex":"https://openalex.org/W4401567667","doi":"https://doi.org/10.1109/tpami.2024.3443335","pmid":"https://pubmed.ncbi.nlm.nih.gov/39141469"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3443335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3443335","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5019575462","display_name":"Yifan Zhang","orcid":"https://orcid.org/0000-0003-0958-9934"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yifan Zhang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006743312","display_name":"Zhiyu Zhu","orcid":"https://orcid.org/0000-0002-0726-4522"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiyu Zhu","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031957432","display_name":"Junhui Hou","orcid":"https://orcid.org/0000-0003-3431-2021"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Junhui Hou","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001469325","display_name":"Dapeng Wu","orcid":"https://orcid.org/0000-0003-1755-0183"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dapeng Wu","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019575462"],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":1.5444,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84081787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"46","issue":"12","first_page":"10614","last_page":"10628"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.995199978351593,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.988099992275238,"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-science","display_name":"Computer science","score":0.8259761929512024},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5628265738487244},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5590655207633972},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5522156953811646},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5045803785324097},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4880181849002838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4805165231227875},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4617571532726288},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35754233598709106},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.31483030319213867},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2807995080947876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259761929512024},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5628265738487244},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5590655207633972},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5522156953811646},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5045803785324097},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4880181849002838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4805165231227875},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4617571532726288},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35754233598709106},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31483030319213867},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2807995080947876},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3443335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3443335","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:39141469","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39141469","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5892297415","display_name":null,"funder_award_id":"MHP/117/21","funder_id":"https://openalex.org/F4320324196","funder_display_name":"Innovation and Technology Commission - Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320324196","display_name":"Innovation and Technology Commission - Hong Kong","ror":"https://ror.org/04vf9tr09"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2896457183","https://openalex.org/W2897529137","https://openalex.org/W2907492528","https://openalex.org/W2948519073","https://openalex.org/W2949708697","https://openalex.org/W2963727135","https://openalex.org/W2964054038","https://openalex.org/W2964121718","https://openalex.org/W3008105217","https://openalex.org/W3033591146","https://openalex.org/W3034314779","https://openalex.org/W3034602892","https://openalex.org/W3034681945","https://openalex.org/W3035172746","https://openalex.org/W3035346742","https://openalex.org/W3035574168","https://openalex.org/W3046791050","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3097237405","https://openalex.org/W3117805350","https://openalex.org/W3117901461","https://openalex.org/W3118341329","https://openalex.org/W3138516171","https://openalex.org/W3167095230","https://openalex.org/W3167732492","https://openalex.org/W3171377125","https://openalex.org/W3172863135","https://openalex.org/W3176888779","https://openalex.org/W3212953023","https://openalex.org/W3214740560","https://openalex.org/W4206138502","https://openalex.org/W4310078553","https://openalex.org/W4312307873","https://openalex.org/W4312312588","https://openalex.org/W4312437143","https://openalex.org/W4312501532","https://openalex.org/W4312546175","https://openalex.org/W4312562010","https://openalex.org/W4312617306","https://openalex.org/W4312707458","https://openalex.org/W4312893480","https://openalex.org/W4312916565","https://openalex.org/W4312976258","https://openalex.org/W4313024968","https://openalex.org/W4313149358","https://openalex.org/W4319300493","https://openalex.org/W4385245566","https://openalex.org/W4385835750","https://openalex.org/W4386057711","https://openalex.org/W4386065368","https://openalex.org/W4386065416","https://openalex.org/W6620707391","https://openalex.org/W6726873649","https://openalex.org/W6739778489","https://openalex.org/W6745537798","https://openalex.org/W6766904570","https://openalex.org/W6784094891","https://openalex.org/W6800161232","https://openalex.org/W6809665764","https://openalex.org/W6849137104"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W4299904075"],"abstract_inverted_index":{"The":[0],"Detection":[1],"Transformer":[2],"(DETR)":[3],"has":[4],"revolutionized":[5],"the":[6,20,42,63,73,99,106,110,113,118,121,126,130,138,143,154,185,192],"design":[7],"of":[8,22,90,101,109,120,129,194],"CNN-based":[9],"object":[10,25,48,91],"detection":[11,26,49],"systems,":[12],"showcasing":[13],"impressive":[14],"performance.":[15],"However,":[16],"its":[17],"potential":[18],"in":[19,83,105,112,197],"domain":[21],"multi-frame":[23,46],"3D":[24,47],"remains":[27],"largely":[28],"unexplored.":[29],"In":[30],"this":[31,58,171],"paper,":[32],"we":[33,71,116,190],"present":[34],"STEMD,":[35],"a":[36,84,94,135,204],"novel":[37],"end-to-end":[38],"framework":[39],"that":[40,151],"enhances":[41],"DETR-like":[43],"paradigm":[44],"for":[45,57,137],"by":[50],"addressing":[51],"three":[52],"key":[53],"aspects":[54],"specifically":[55],"tailored":[56],"task.":[59],"First,":[60],"to":[61,124,140,181],"model":[62],"inter-object":[64],"spatial":[65],"interaction":[66],"and":[67,86,146,163],"complex":[68],"temporal":[69],"dependencies,":[70],"introduce":[72],"spatial-temporal":[74],"graph":[75,85],"attention":[76],"network,":[77],"which":[78],"represents":[79],"queries":[80,150,159,180],"as":[81],"nodes":[82],"enables":[87],"effective":[88],"modeling":[89],"interactions":[92],"within":[93],"social":[95],"context.":[96],"To":[97,169],"solve":[98],"problem":[100],"missing":[102],"hard":[103],"cases":[104],"proposed":[107,174],"output":[108,119],"encoder":[111],"current":[114],"frame,":[115],"incorporate":[117],"previous":[122],"frame":[123],"initialize":[125],"query":[127,145],"input":[128],"decoder.":[131],"Finally,":[132],"it":[133],"poses":[134],"challenge":[136],"network":[139],"distinguish":[141],"between":[142],"positive":[144],"other":[147],"highly":[148],"similar":[149,158,179],"are":[152,160],"not":[153],"best":[155],"match.":[156],"And":[157],"insufficiently":[161],"suppressed":[162],"turn":[164],"into":[165],"redundant":[166],"prediction":[167],"boxes.":[168],"address":[170],"issue,":[172],"our":[173,195],"IoU":[175],"regularization":[176],"term":[177],"encourages":[178],"be":[182],"distinct":[183],"during":[184],"refinement.":[186],"Through":[187],"extensive":[188],"experiments,":[189],"demonstrate":[191],"effectiveness":[193],"approach":[196],"handling":[198],"challenging":[199],"scenarios,":[200],"while":[201],"incurring":[202],"only":[203],"minor":[205],"additional":[206],"computational":[207],"overhead.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}