{"id":"https://openalex.org/W7138296746","doi":"https://doi.org/10.1609/aaai.v40i14.38204","title":"FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection","display_name":"FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138296746","doi":"https://doi.org/10.1609/aaai.v40i14.38204"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i14.38204","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38204","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i14.38204","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129711398","display_name":"Jiangyong Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091958","display_name":"Hanoi Open University","ror":"https://ror.org/00gjkwr85","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210091958"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Jiangyong Yu","raw_affiliation_strings":["Houmo AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Houmo AI","institution_ids":["https://openalex.org/I4210091958"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129731211","display_name":"Changyong Shu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091958","display_name":"Hanoi Open University","ror":"https://ror.org/00gjkwr85","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210091958"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Changyong Shu","raw_affiliation_strings":["Houmo AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Houmo AI","institution_ids":["https://openalex.org/I4210091958"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103268513","display_name":"Sifan Zhou","orcid":"https://orcid.org/0000-0003-3602-7566"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sifan Zhou","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129721229","display_name":"Zichen Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zichen Yu","raw_affiliation_strings":["Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129703358","display_name":"Xing Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091958","display_name":"Hanoi Open University","ror":"https://ror.org/00gjkwr85","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210091958"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Xing Hu","raw_affiliation_strings":["Houmo AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Houmo AI","institution_ids":["https://openalex.org/I4210091958"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129699859","display_name":"Dawei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091958","display_name":"Hanoi Open University","ror":"https://ror.org/00gjkwr85","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210091958"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dawei Yang","raw_affiliation_strings":["Houmo AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Houmo AI","institution_ids":["https://openalex.org/I4210091958"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"14","first_page":"12144","last_page":"12152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.2296999990940094,"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":0.2296999990940094,"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/T11448","display_name":"Face recognition and analysis","score":0.22339999675750732,"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":0.12030000239610672,"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/quantization","display_name":"Quantization (signal processing)","score":0.7595999836921692},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7304999828338623},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6424999833106995},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4341000020503998},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4138999879360199},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37549999356269836},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3709999918937683},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.3589000105857849}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7595999836921692},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7304999828338623},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6424999833106995},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5958999991416931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5884000062942505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4844000041484833},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4138999879360199},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3917999863624573},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.33340001106262207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32510000467300415},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.30489999055862427},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28940001130104065},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i14.38204","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38204","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i14.38204","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38204","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Camera-based":[0],"multi-view":[1],"3D":[2],"detection":[3],"is":[4,30],"crucial":[5],"for":[6,34,110],"autonomous":[7],"driving.":[8],"PETR":[9],"and":[10,26,46,78,83,87,129,137,167],"its":[11],"variants":[12],"(PETRs)":[13],"excel":[14],"in":[15],"benchmarks":[16],"but":[17],"face":[18],"deployment":[19],"challenges":[20],"due":[21],"to":[22,54,57],"high":[23,162],"computational":[24],"cost":[25],"memory":[27],"footprint.":[28],"Quantization":[29,172],"an":[31],"effective":[32],"technique":[33],"compressing":[35],"deep":[36],"neural":[37],"networks":[38],"by":[39],"reducing":[40],"the":[41,85],"bit":[42],"width":[43],"of":[44,90],"weights":[45],"activations.":[47],"However,":[48],"directly":[49],"applying":[50],"existing":[51],"quantization":[52,178],"methods":[53],"PETRs":[55,190],"leads":[56],"severe":[58],"accuracy":[59,201],"degradation.":[60],"This":[61,150],"issue":[62],"primarily":[63],"arises":[64],"from":[65,186],"two":[66,157],"key":[67,114],"challenges:":[68],"(1)":[69,116],"significant":[70],"magnitude":[71],"disparity":[72],"between":[73],"multi-modal":[74],"features\u2014specifically,":[75],"image":[76,142],"features":[77],"camera-ray":[79],"positional":[80],"embeddings":[81],"(PE),":[82],"(2)":[84,146],"inefficiency":[86],"approximation":[88],"error":[89],"quantizing":[91],"non-linear":[92,154],"operators,":[93],"which":[94],"commonly":[95],"rely":[96],"on":[97],"hardware-unfriendly":[98],"computations.":[99],"In":[100],"this":[101],"paper,":[102],"we":[103],"propose":[104],"FQ-PETR,":[105],"a":[106],"fully":[107],"quantized":[108],"framework":[109],"PETRs,":[111],"featuring":[112],"three":[113],"innovations:":[115],"Quantization-Friendly":[117],"LiDAR-ray":[118],"Position":[119],"Embedding":[120],"(QFPE):":[121],"Replacing":[122],"multi-point":[123],"sampling":[124,128],"with":[125,141,164],"LiDAR-prior-guided":[126],"single-point":[127],"anchor-based":[130],"embedding":[131],"eliminates":[132],"problematic":[133],"non-linearities":[134],"(e.g.,":[135,191],"inverse-sigmoid)":[136],"aligns":[138],"PE":[139],"scale":[140],"features,":[143],"preserving":[144],"accuracy.":[145],"Dual-Lookup":[147],"Table":[148],"(DULUT):":[149],"algorithm":[151],"approximates":[152],"complex":[153],"functions":[155],"using":[156],"cascaded":[158],"linear":[159],"LUTs,":[160],"achieving":[161],"fidelity":[163],"minimal":[165],"entries":[166],"no":[168],"specialized":[169],"hardware.":[170],"(3)":[171],"After":[173],"Numerical":[174],"Stabilization":[175],"(QANS):":[176],"Performing":[177],"after":[179],"softmax":[180],"numerical":[181],"stabilization":[182],"mitigates":[183],"attention":[184],"distortion":[185],"large":[187],"inputs.":[188],"On":[189],"PETR,":[192],"StreamPETR,":[193],"PETRv2,":[194],"MV2d),":[195],"FQ-PETR":[196],"under":[197],"W8A8":[198],"achieves":[199],"near-floating-point":[200],"(":[202]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}