{"id":"https://openalex.org/W4403791949","doi":"https://doi.org/10.1145/3664647.3681103","title":"RayFormer: Improving Query-Based Multi-Camera 3D Object Detection via Ray-Centric Strategies","display_name":"RayFormer: Improving Query-Based Multi-Camera 3D Object Detection via Ray-Centric Strategies","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791949","doi":"https://doi.org/10.1145/3664647.3681103"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681103","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5079831764","display_name":"Xiaomeng Chu","orcid":"https://orcid.org/0000-0002-7164-7245"},"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":true,"raw_author_name":"Xiaomeng Chu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089561793","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0001-9624-7451"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiajun Deng","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034921190","display_name":"Guoliang You","orcid":null},"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":"Guoliang You","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066206169","display_name":"Yifan Duan","orcid":"https://orcid.org/0009-0004-0754-3953"},"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":"Yifan Duan","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034825117","display_name":"Yao Li","orcid":"https://orcid.org/0000-0002-6063-3331"},"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":"Yao Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103041851","display_name":"Yanyong Zhang","orcid":"https://orcid.org/0000-0001-9046-798X"},"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":"Yanyong Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5079831764"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.9971,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77848721,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4620","last_page":"4629"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9987000226974487,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9987000226974487,"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/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9980000257492065,"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":0.7965036630630493},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6037105321884155},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5874975919723511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5236489772796631},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4736969470977783},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.44474539160728455},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4433591663837433},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2541007995605469},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.1750994622707367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7965036630630493},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6037105321884155},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5874975919723511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5236489772796631},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4736969470977783},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.44474539160728455},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4433591663837433},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2541007995605469},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.1750994622707367}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681103","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2747329762","https://openalex.org/W2911486422","https://openalex.org/W2964062501","https://openalex.org/W2966926453","https://openalex.org/W3023742835","https://openalex.org/W3035574168","https://openalex.org/W3109395584","https://openalex.org/W3176287975","https://openalex.org/W3178544809","https://openalex.org/W4214558638","https://openalex.org/W4214708455","https://openalex.org/W4225793049","https://openalex.org/W4312894406","https://openalex.org/W4382464460","https://openalex.org/W4386066258","https://openalex.org/W4386072002","https://openalex.org/W4390872833","https://openalex.org/W4390873371","https://openalex.org/W4390873443","https://openalex.org/W4390874049","https://openalex.org/W4390874137","https://openalex.org/W4390874146","https://openalex.org/W4390874170","https://openalex.org/W4390874598","https://openalex.org/W4392872544","https://openalex.org/W4393149498","https://openalex.org/W4402754046","https://openalex.org/W4402776467"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W2006459955","https://openalex.org/W2146885082","https://openalex.org/W2066605394","https://openalex.org/W1982237068","https://openalex.org/W2572349046","https://openalex.org/W2538384344","https://openalex.org/W4386051213","https://openalex.org/W185198413","https://openalex.org/W3125756434"],"abstract_inverted_index":{"The":[0,218],"recent":[1],"advances":[2],"in":[3,15,53,136],"query-based":[4,69],"multi-camera":[5],"3D":[6,17,70],"object":[7,13,71,81,156,168],"detection":[8,59,169],"are":[9,42,118,205],"featured":[10],"by":[11,158],"initializing":[12],"queries":[14,82,117,132,157,162],"the":[16,38,75,84,101,106,113,128,137,146,153,164,190,208],"space,":[18],"and":[19,57,77,104,120,199,224],"then":[20],"sampling":[21,185,194],"features":[22,47,56,94,175],"from":[23,48,166],"perspective-view":[24,92],"images":[25,150,198],"to":[26,44,109,139,151,178,211],"perform":[27],"multi-round":[28],"query":[29,35,55],"refinement.":[30],"In":[31],"such":[32],"a":[33,67,183],"framework,":[34],"points":[36,195],"near":[37],"same":[39],"camera":[40,114,125],"ray":[41,165,184],"likely":[43],"sample":[45],"similar":[46],"very":[49],"close":[50],"pixels,":[51],"resulting":[52],"ambiguous":[54],"degraded":[58],"accuracy.":[60],"To":[61,171],"this":[62],"end,":[63],"we":[64,144,181],"introduce":[65],"RayFormer,":[66],"camera-ray-inspired":[68],"detector":[72],"that":[73,176,187],"aligns":[74],"initialization":[76],"feature":[78,193],"extraction":[79],"of":[80,87,130,149,192],"with":[83],"optical":[85],"characteristics":[86],"cameras.":[88],"Specifically,":[89],"RayFormer":[90,220],"transforms":[91],"image":[93,138],"into":[95],"bird's":[96,200],"eye":[97,201],"view":[98],"(BEV)":[99],"via":[100],"lift-splat-shoot":[102],"method":[103,186],"segments":[105],"BEV":[107],"map":[108],"sectors":[110],"based":[111],"on":[112,196,207],"rays.":[115],"Object":[116],"uniformly":[119,154],"sparsely":[121],"initialized":[122,155],"along":[123,163],"each":[124],"ray,":[126],"facilitating":[127],"projection":[129],"different":[131,134],"onto":[133],"areas":[135],"extract":[140,172],"distinct":[141,179],"features.":[142],"Besides,":[143],"leverage":[145],"instance":[147],"information":[148],"supplement":[152],"further":[159],"involving":[160],"additional":[161],"2D":[167],"boxes.":[170],"unique":[173],"object-level":[174],"cater":[177],"queries,":[180],"design":[182],"suitably":[188],"organizes":[189],"distribution":[191],"both":[197],"view.":[202],"Extensive":[203],"experiments":[204],"conducted":[206],"nuScenes":[209],"dataset":[210],"validate":[212],"our":[213],"proposed":[214,219],"ray-inspired":[215],"model":[216],"design.":[217],"achieves":[221],"55.5%":[222],"mAP":[223],"63.3%":[225],"NDS,":[226],"respectively.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}