{"id":"https://openalex.org/W4401247105","doi":"https://doi.org/10.1109/tip.2024.3430473","title":"Graph-DETR4D: Spatio-Temporal Graph Modeling for Multi-View 3D Object Detection","display_name":"Graph-DETR4D: Spatio-Temporal Graph Modeling for Multi-View 3D Object Detection","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401247105","doi":"https://doi.org/10.1109/tip.2024.3430473","pmid":"https://pubmed.ncbi.nlm.nih.gov/39093681"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3430473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3430473","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","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/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":["MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1843-4478","affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665777","display_name":"Zheng Chen","orcid":"https://orcid.org/0000-0003-2834-7455"},"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":"Zheng Chen","raw_affiliation_strings":["MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, School of Information Science and Technology, University of Science and Technology of China, Hefei, 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/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Zhenyu Li","raw_affiliation_strings":["School of Computer, Electrical and Mathematical Sciences and Engineering, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Electrical and Mathematical Sciences and Engineering, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062999404","display_name":"Shiquan Zhang","orcid":"https://orcid.org/0009-0009-7112-2463"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiquan Zhang","raw_affiliation_strings":["SenseTime Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065691762","display_name":"Liangji Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangji Fang","raw_affiliation_strings":["SenseTime Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102871046","display_name":"Qinhong Jiang","orcid":"https://orcid.org/0000-0002-5509-7247"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinhong Jiang","raw_affiliation_strings":["SenseTime Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5509-7247","affiliations":[{"raw_affiliation_string":"SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103150943","display_name":"Feng Wu","orcid":"https://orcid.org/0000-0001-7266-5579"},"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 Wu","raw_affiliation_strings":["MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7266-5579","affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100401202","display_name":"Feng Zhao","orcid":"https://orcid.org/0000-0001-6767-8105"},"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":["MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6767-8105","affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.635,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8469299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"33","issue":null,"first_page":"4488","last_page":"4500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9973000288009644,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9973000288009644,"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":0.9927999973297119,"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":0.9767000079154968,"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":0.6481457948684692},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.52084881067276},{"id":"https://openalex.org/keywords/graph-theory","display_name":"Graph theory","score":0.43883851170539856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.422235906124115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3520125150680542},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3399125933647156},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3085836172103882},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24158021807670593},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.13251081109046936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6481457948684692},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.52084881067276},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.43883851170539856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.422235906124115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3520125150680542},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3399125933647156},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3085836172103882},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24158021807670593},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.13251081109046936}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2024.3430473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3430473","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:39093681","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39093681","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G179212483","display_name":null,"funder_award_id":"2108085UD12","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"}],"funders":[{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W2122122381","https://openalex.org/W2194775991","https://openalex.org/W2468368736","https://openalex.org/W2565639579","https://openalex.org/W2604784247","https://openalex.org/W2731516819","https://openalex.org/W2750432752","https://openalex.org/W2790548477","https://openalex.org/W2954174912","https://openalex.org/W2963794551","https://openalex.org/W2982770724","https://openalex.org/W2984013788","https://openalex.org/W2999947750","https://openalex.org/W3034314779","https://openalex.org/W3035172746","https://openalex.org/W3035180028","https://openalex.org/W3035574168","https://openalex.org/W3096609285","https://openalex.org/W3103438692","https://openalex.org/W3107191128","https://openalex.org/W3109395584","https://openalex.org/W3136714643","https://openalex.org/W3167095230","https://openalex.org/W3173270634","https://openalex.org/W3176459575","https://openalex.org/W3215100485","https://openalex.org/W4214558638","https://openalex.org/W4221159041","https://openalex.org/W4224947594","https://openalex.org/W4225793049","https://openalex.org/W4226305814","https://openalex.org/W4282936033","https://openalex.org/W4283027141","https://openalex.org/W4283399795","https://openalex.org/W4285606661","https://openalex.org/W4288099366","https://openalex.org/W4289283268","https://openalex.org/W4297899592","https://openalex.org/W4303443326","https://openalex.org/W4304098216","https://openalex.org/W4306833423","https://openalex.org/W4309395078","https://openalex.org/W4309795819","https://openalex.org/W4312242710","https://openalex.org/W4312842574","https://openalex.org/W4312894406","https://openalex.org/W4313141028","https://openalex.org/W4313303921","https://openalex.org/W4372337605","https://openalex.org/W4376481110","https://openalex.org/W4378468525","https://openalex.org/W4382464460","https://openalex.org/W4382466543","https://openalex.org/W4383066393","https://openalex.org/W4386066615","https://openalex.org/W4386075696","https://openalex.org/W4386076493","https://openalex.org/W4386083125","https://openalex.org/W4388757371","https://openalex.org/W4390872833","https://openalex.org/W4390874146","https://openalex.org/W4390874598","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6740493225","https://openalex.org/W6743188669","https://openalex.org/W6756392615","https://openalex.org/W6789011712","https://openalex.org/W6799331316","https://openalex.org/W6802311648","https://openalex.org/W6802716934","https://openalex.org/W6810001583","https://openalex.org/W6811230113","https://openalex.org/W6838603739","https://openalex.org/W6838873368","https://openalex.org/W6839131839","https://openalex.org/W6839198999","https://openalex.org/W6839364997","https://openalex.org/W6840525788","https://openalex.org/W6843796254","https://openalex.org/W6845491643","https://openalex.org/W6846811668","https://openalex.org/W6846912360","https://openalex.org/W6848294565","https://openalex.org/W6853295911"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2775347418","https://openalex.org/W2779427294","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W4385627933","https://openalex.org/W2532801570","https://openalex.org/W2480127678","https://openalex.org/W2806270048","https://openalex.org/W4310605282"],"abstract_inverted_index":{"Multi-View":[0],"3D":[1,32,60,80,140,182,213],"object":[2,61,183,214],"detection":[3,62,193,215],"(MV3D)":[4],"has":[5],"made":[6],"tremendous":[7],"progress":[8],"by":[9],"leveraging":[10],"multiple":[11],"perspective":[12],"features":[13,76],"through":[14,27,77],"surrounding":[15],"cameras.":[16],"Despite":[17],"demonstrating":[18],"promising":[19],"prospects":[20],"in":[21,30,42,55,169],"various":[22],"applications,":[23],"accurately":[24],"detecting":[25],"objects":[26],"camera":[28],"view":[29],"the":[31,39,70,94,116,121,127,132,138,143,164,170,187,230],"space":[33,145],"is":[34,248],"extremely":[35],"difficult":[36],"due":[37,92],"to":[38,93,113,126,151,185],"ill-posed":[40],"issue":[41],"monocular":[43],"depth":[44,87],"estimation.":[45],"Recently,":[46],"Graph-DETR3D":[47],"presents":[48],"a":[49,78,97,107,175,208],"novel":[50,176],"graph-based":[51],"3D-2D":[52],"query":[53,71],"paradigm":[54],"aggregating":[56],"multi-view":[57,117,181,212],"images":[58],"for":[59,180,199],"and":[63,88,129,159,210,226,232],"achieves":[64,240],"competitive":[65],"performance.":[66],"Although":[67],"it":[68,82,196],"enriches":[69],"representations":[72],"with":[73,146],"2D":[74],"image":[75,171],"learnable":[79],"graph,":[81],"still":[83],"suffers":[84],"from":[85],"limited":[86],"velocity":[89],"estimation":[90],"abilities":[91],"adoption":[95],"of":[96,131,220,234],"single-frame":[98],"input":[99],"setting.":[100,124],"To":[101,202],"solve":[102],"this":[103,203],"problem,":[104],"we":[105,136,173,205],"introduce":[106],"unified":[108],"spatial-temporal":[109],"graph":[110,134,141],"modeling":[111],"framework":[112,179],"fully":[114],"leverage":[115],"imagery":[118,154],"cues":[119],"under":[120],"multi-frame":[122],"inputs":[123],"Thanks":[125],"flexibility":[128],"sparsity":[130],"dynamic":[133],"architecture,":[135],"lift":[137],"original":[139],"into":[142],"4D":[144],"an":[147],"effective":[148],"attention":[149],"mechanism":[150],"automatically":[152],"perceive":[153],"information":[155],"at":[156,250],"both":[157],"spatial":[158],"temporal":[160],"levels.":[161],"Moreover,":[162],"considering":[163],"main":[165],"latency":[166],"bottleneck":[167],"lies":[168],"backbone,":[172],"propose":[174,206],"dense-sparse":[177],"distillation":[178],"detection,":[184],"reduce":[186],"computational":[188],"budget":[189],"while":[190],"sacrificing":[191],"no":[192],"accuracy,":[194],"making":[195],"more":[197],"suitable":[198],"real-world":[200],"deployment.":[201],"end,":[204],"Graph-DETR4D,":[207],"faster":[209],"stronger":[211],"framework,":[216],"built":[217],"on":[218,224,243],"top":[219],"Graph-DETR3D.":[221],"Extensive":[222],"experiments":[223],"nuScenes":[225,244],"Waymo":[227],"benchmarks":[228],"demonstrate":[229],"effectiveness":[231],"efficiency":[233],"Graph-DETR4D.":[235],"Notably,":[236],"our":[237],"best":[238],"model":[239],"62.0%":[241],"NDS":[242],"test":[245],"leaderboard.":[246],"Code":[247],"available":[249],"https://github.com/zehuichen123/Graph-DETR4D.":[251]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}