{"id":"https://openalex.org/W4400717318","doi":"https://doi.org/10.48550/arxiv.2407.10753","title":"OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection","display_name":"OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4400717318","doi":"https://doi.org/10.48550/arxiv.2407.10753"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2407.10753","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.10753","pdf_url":"https://arxiv.org/pdf/2407.10753","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.10753","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071942934","display_name":"Jinghua Hou","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hou, Jinghua","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451020","display_name":"Tong Wang","orcid":"https://orcid.org/0000-0003-0053-2376"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087798118","display_name":"Xiaoqing Ye","orcid":"https://orcid.org/0000-0003-3268-880X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Xiaoqing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595442","display_name":"Zhe Liu","orcid":"https://orcid.org/0009-0004-1429-9207"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112108113","display_name":"Shi Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Shi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074507868","display_name":"Xiao Tan","orcid":"https://orcid.org/0000-0003-3109-9114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Xiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050031109","display_name":"Errui Ding","orcid":"https://orcid.org/0000-0002-1867-5378"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Errui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075880303","display_name":"Jingdong Wang","orcid":"https://orcid.org/0000-0002-4888-4445"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jingdong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039363991","display_name":"Xiang Bai","orcid":"https://orcid.org/0000-0002-3449-5940"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Xiang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5071942934"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9991000294685364,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.994700014591217,"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/object","display_name":"Object (grammar)","score":0.6904959082603455},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6741654872894287},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.666208028793335},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.6314016580581665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6141327619552612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5848550200462341},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5123473405838013},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.245988130569458},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.1600399911403656}],"concepts":[{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6904959082603455},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6741654872894287},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.666208028793335},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.6314016580581665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6141327619552612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5848550200462341},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5123473405838013},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.245988130569458},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.1600399911403656},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2407.10753","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.10753","pdf_url":"https://arxiv.org/pdf/2407.10753","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.10753","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.10753","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.10753","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.10753","pdf_url":"https://arxiv.org/pdf/2407.10753","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4400717318.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Accurate":[0],"depth":[1,25,34,65,75,90,123,140,146,169],"information":[2,124,170],"is":[3,40,50,81,97,118],"crucial":[4],"for":[5,71,99,180],"enhancing":[6],"the":[7,15,33,44,47,61,64,78,88,95,126,144,154,160,167,172,186,206],"performance":[8,198],"of":[9,17,46,63,66,77,94,188],"multi-view":[10,20,109],"3D":[11,21,57,67,92,110,177],"object":[12,68,80,111],"detection.":[13,101,182],"Despite":[14],"success":[16],"some":[18],"existing":[19,55],"detectors":[22,58],"utilizing":[23],"pixel-wise":[24,145],"supervision,":[26],"they":[27],"overlook":[28],"two":[29],"significant":[30],"phenomena:":[31],"1)":[32],"supervision":[35],"obtained":[36],"from":[37],"LiDAR":[38],"points":[39],"usually":[41],"distributed":[42],"on":[43,205],"surface":[45],"object,":[48],"which":[49,142],"not":[51],"so":[52],"friendly":[53],"to":[54,60,119,151,165],"DETR-based":[56],"due":[59],"lack":[62],"center;":[69],"2)":[70],"distant":[72],"objects,":[73],"fine-grained":[74],"estimation":[76],"whole":[79],"more":[82],"challenging.":[83],"Therefore,":[84],"we":[85,105,135,158],"argue":[86],"that":[87],"object-wise":[89,122,131,139,155,162,168],"(or":[91],"center":[93],"object)":[96],"essential":[98],"accurate":[100],"In":[102],"this":[103],"paper,":[104],"propose":[106],"a":[107,149,195],"new":[108,196],"detector":[112],"named":[113],"OPEN,":[114],"whose":[115],"main":[116],"idea":[117],"effectively":[120],"inject":[121],"into":[125,171],"network":[127],"through":[128],"our":[129,189],"proposed":[130,161,190],"position":[132,163],"embedding.":[133],"Specifically,":[134],"first":[136],"employ":[137],"an":[138],"encoder,":[141],"takes":[143],"map":[147],"as":[148],"prior,":[150],"accurately":[152],"estimate":[153],"depth.":[156],"Then,":[157],"utilize":[159],"embedding":[164],"encode":[166],"transformer":[173],"decoder,":[174],"thereby":[175],"producing":[176],"object-aware":[178],"features":[179],"final":[181],"Extensive":[183],"experiments":[184],"verify":[185],"effectiveness":[187],"method.":[191],"Furthermore,":[192],"OPEN":[193],"achieves":[194],"state-of-the-art":[197],"with":[199],"64.4%":[200],"NDS":[201],"and":[202],"56.7%":[203],"mAP":[204],"nuScenes":[207],"test":[208],"benchmark.":[209]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}