{"id":"https://openalex.org/W4400648802","doi":"https://doi.org/10.1109/iv55156.2024.10588449","title":"SF3D: SlowFast Temporal 3D Object Detection","display_name":"SF3D: SlowFast Temporal 3D Object Detection","publication_year":2024,"publication_date":"2024-06-02","ids":{"openalex":"https://openalex.org/W4400648802","doi":"https://doi.org/10.1109/iv55156.2024.10588449"},"language":"en","primary_location":{"id":"doi:10.1109/iv55156.2024.10588449","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iv55156.2024.10588449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Intelligent Vehicles Symposium (IV)","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/A5077503671","display_name":"Renhao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Renhao Wang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054586129","display_name":"Zhiding Yu","orcid":"https://orcid.org/0000-0003-1776-996X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiding Yu","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008361912","display_name":"Shiyi Lan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyi Lan","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041031140","display_name":"Enze Xie","orcid":"https://orcid.org/0000-0001-6890-1049"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Enze Xie","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100649535","display_name":"Ke Chen","orcid":"https://orcid.org/0000-0003-0928-5199"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014498545","display_name":"Anima Anandkumar","orcid":"https://orcid.org/0000-0002-6974-6797"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anima Anandkumar","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068261539","display_name":"Jos\u00e9 Manuel Gonz\u00e1lez y Fern\u00e1ndez Valles","orcid":"https://orcid.org/0000-0003-1093-8644"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jose M. Alvarez","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5077503671"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08031597,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"1280","last_page":"1285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9688000082969666,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9688000082969666,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.957099974155426,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9275000095367432,"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/computer-science","display_name":"Computer science","score":0.6909605860710144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5655438303947449},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5465384125709534},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4762140214443207},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.42170020937919617},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.29775363206863403}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6909605860710144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5655438303947449},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5465384125709534},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4762140214443207},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42170020937919617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29775363206863403}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iv55156.2024.10588449","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iv55156.2024.10588449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2549139847","https://openalex.org/W2601564443","https://openalex.org/W2803876455","https://openalex.org/W2897529137","https://openalex.org/W2955189650","https://openalex.org/W2963155035","https://openalex.org/W2968296999","https://openalex.org/W3008105217","https://openalex.org/W3035172746","https://openalex.org/W3035574168","https://openalex.org/W3036587719","https://openalex.org/W3092462694","https://openalex.org/W3136022415","https://openalex.org/W3167095230","https://openalex.org/W3167732492","https://openalex.org/W3171377125","https://openalex.org/W3175563878","https://openalex.org/W3179351458","https://openalex.org/W3209374680","https://openalex.org/W3213288297","https://openalex.org/W4212774754","https://openalex.org/W4224947594","https://openalex.org/W4310078553","https://openalex.org/W4312307873","https://openalex.org/W4312501532","https://openalex.org/W4312707458","https://openalex.org/W4312894406","https://openalex.org/W4313024968","https://openalex.org/W4320737106","https://openalex.org/W4383066393","https://openalex.org/W4385245566","https://openalex.org/W6751597478","https://openalex.org/W6759579507","https://openalex.org/W6772595511","https://openalex.org/W6779390028","https://openalex.org/W6784094891","https://openalex.org/W6789760779","https://openalex.org/W6803444062","https://openalex.org/W6803556390","https://openalex.org/W6810001583","https://openalex.org/W6849840618"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Leveraging":[0],"inputs":[1],"over":[2,141],"multiple":[3],"consecutive":[4,56],"frames":[5],"has":[6],"been":[7],"shown":[8],"to":[9,83,113,120],"benefit":[10],"3D":[11],"object":[12],"detection.":[13],"However,":[14],"existing":[15],"approaches":[16],"often":[17],"demonstrate":[18],"unsatisfactory":[19],"scaling":[20,119],"with":[21,131],"increasing":[22],"temporal":[23,42],"histories.":[24],"In":[25,87],"this":[26,37],"work,":[27],"we":[28],"propose":[29],"SF3D,":[30],"a":[31,45,89,100],"late":[32],"fusion":[33],"module":[34],"which":[35,61],"addresses":[36],"issue":[38],"by":[39],"better":[40],"modeling":[41],"relationships":[43],"via":[44],"two-stream":[46,109],"factorization.":[47],"Concretely,":[48],"SF3D":[49,112,129],"operates":[50],"on":[51,144],"an":[52],"input":[53],"sequence":[54],"of":[55,93,103],"bird\u2019s-eye":[57],"view":[58],"(BEV)":[59],"features,":[60],"is":[62],"partitioned":[63],"into":[64],"\"short-term\"":[65],"and":[66,77,136,148],"\"long-term\"":[67],"frames.":[68],"A":[69],"more":[70],"heavily":[71],"parameterized":[72],"short-term":[73],"branch":[74,91],"using":[75],"adapters":[76],"deformable":[78],"attention":[79],"aggregates":[80,99],"features":[81],"closer":[82],"the":[84,145],"current":[85],"timestep.":[86],"parallel,":[88],"long-term":[90],"composed":[92],"efficiently":[94,121],"implemented":[95],"global":[96],"convolution":[97],"layers":[98],"larger":[101],"window":[102],"temporally":[104],"distant":[105],"historical":[106,124],"features.":[107],"This":[108],"paradigm":[110],"allows":[111],"effectively":[114],"consume":[115],"near-term":[116],"information,":[117],"while":[118],"leverage":[122],"longer":[123],"windows.":[125],"We":[126],"show":[127],"that":[128],"works":[130],"arbitrary":[132],"upstream":[133],"BEV":[134],"encoders":[135],"downstream":[137],"detectors,":[138],"achieving":[139],"improvements":[140],"recent":[142],"state-of-the-art":[143],"Waymo":[146],"Open":[147],"nuScenes":[149],"benchmarks.":[150]},"counts_by_year":[],"updated_date":"2026-04-16T15:07:20.185449","created_date":"2025-10-10T00:00:00"}