{"id":"https://openalex.org/W4387969594","doi":"https://doi.org/10.1145/3581783.3613798","title":"OccluBEV: Occlusion Aware Spatiotemporal Modeling for Multi-view 3D Object Detection","display_name":"OccluBEV: Occlusion Aware Spatiotemporal Modeling for Multi-view 3D Object Detection","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969594","doi":"https://doi.org/10.1145/3581783.3613798"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3613798","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3613798","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3613798","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3613798","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070344296","display_name":"Ziteng Wen","orcid":"https://orcid.org/0009-0003-8331-184X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ziteng Wen","raw_affiliation_strings":["iFLYTEK Research, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-8331-184X","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075074351","display_name":"Hai Cheng Xu","orcid":"https://orcid.org/0000-0003-4581-8394"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hai Xu","raw_affiliation_strings":["iFLYTEK Research, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4581-8394","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731343","display_name":"Chenyu Liu","orcid":"https://orcid.org/0009-0006-6682-2877"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenyu Liu","raw_affiliation_strings":["iFLYTEK Research, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0006-6682-2877","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002604327","display_name":"Tao Guo","orcid":"https://orcid.org/0009-0007-0733-8310"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Guo","raw_affiliation_strings":["iFLYTEK Research, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-0733-8310","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050645517","display_name":"Jinshui Hu","orcid":"https://orcid.org/0009-0001-3017-973X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinshui Hu","raw_affiliation_strings":["iFLYTEK Research, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0001-3017-973X","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015970030","display_name":"Xuming He","orcid":"https://orcid.org/0000-0003-2150-1237"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuming He","raw_affiliation_strings":["ShanghaiTech University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2150-1237","affiliations":[{"raw_affiliation_string":"ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081281454","display_name":"Fengren Wang","orcid":"https://orcid.org/0009-0007-4539-3361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fengren Wang","raw_affiliation_strings":["iFLYTEK Research, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-4539-3361","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057409004","display_name":"Shun Lou","orcid":"https://orcid.org/0009-0001-1979-0562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shun Lou","raw_affiliation_strings":["iFLYTEK Research, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0001-1979-0562","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103212783","display_name":"Haibo Fan","orcid":"https://orcid.org/0009-0009-3181-8546"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haibo Fan","raw_affiliation_strings":["iFLYTEK Research, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0009-3181-8546","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5070344296"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2355,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53300619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4074","last_page":"4083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9994999766349792,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9994999766349792,"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":0.9994000196456909,"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":0.9993000030517578,"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":0.767204761505127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7593740224838257},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6705377101898193},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5145018100738525},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5019922256469727},{"id":"https://openalex.org/keywords/voxel","display_name":"Voxel","score":0.5005970001220703},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4917447865009308},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.46631771326065063},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.44521456956863403},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.41202062368392944},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41127827763557434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39207950234413147},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.13115322589874268},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10857832431793213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767204761505127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7593740224838257},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6705377101898193},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5145018100738525},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5019922256469727},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.5005970001220703},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4917447865009308},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.46631771326065063},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.44521456956863403},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.41202062368392944},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41127827763557434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39207950234413147},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13115322589874268},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10857832431793213},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3613798","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3613798","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3613798","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3613798","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3613798","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3613798","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387969594.pdf","grobid_xml":"https://content.openalex.org/works/W4387969594.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2216192774","https://openalex.org/W2555618208","https://openalex.org/W2601564443","https://openalex.org/W2949708697","https://openalex.org/W2954174912","https://openalex.org/W2963727135","https://openalex.org/W2964062501","https://openalex.org/W2964166085","https://openalex.org/W2968296999","https://openalex.org/W2970987838","https://openalex.org/W2986519121","https://openalex.org/W2997790735","https://openalex.org/W2998633559","https://openalex.org/W2999947750","https://openalex.org/W3008105217","https://openalex.org/W3034295100","https://openalex.org/W3034479628","https://openalex.org/W3035574168","https://openalex.org/W3096609285","https://openalex.org/W3109395584","https://openalex.org/W3167095230","https://openalex.org/W3167732492","https://openalex.org/W3171032126","https://openalex.org/W3173668541","https://openalex.org/W3176319743","https://openalex.org/W3215100485","https://openalex.org/W4214530037","https://openalex.org/W4386072002","https://openalex.org/W6600175266","https://openalex.org/W6600339963","https://openalex.org/W6610578020","https://openalex.org/W6717243457"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W4221142204"],"abstract_inverted_index":{"Bird's-Eye-View":[0],"(BEV)":[1],"based":[2],"3D":[3,38,136,148],"visual":[4],"perception,":[5],"which":[6,176,215],"formulates":[7],"a":[8,47,65,130,167,172,183,201],"unified":[9,184],"space":[10],"for":[11,25,97],"multi-view":[12,123],"representation,":[13],"has":[14],"received":[15],"wide":[16],"attention":[17],"in":[18,31,42,58,81,89,135,146,162,182],"autonomous":[19],"driving":[20],"due":[21],"to":[22,103,157,218],"its":[23],"scalability":[24],"downstream":[26],"tasks.":[27],"However,":[28],"view":[29,60],"transform":[30,61],"transformer-based":[32,67],"BEV":[33,49,86,137,149,163,185],"methods":[34],"is":[35,116,151,193,216],"agnostic":[36],"of":[37,189,205],"occlusion":[39,56,74],"relationships,":[40],"resulting":[41],"model":[43],"degradation.":[44],"To":[45],"construct":[46],"higher-quality":[48],"space,":[50,92],"this":[51,127],"paper":[52,128],"analyzes":[53],"the":[54,59,73,83,90,147,159,190,197,208],"mutual":[55],"problems":[57],"process":[62],"and":[63,85,100,124],"proposes":[64],"new":[66],"method":[68,192],"named":[69],"OccluBEV.":[70],"OccluBEV":[71],"alleviates":[72],"issue":[75],"via":[76],"point":[77],"cloud":[78],"information":[79,120],"distillation":[80],"both":[82],"image":[84,91,105,115],"space.":[87,138,186],"Specifically,":[88],"we":[93,170],"perform":[94],"depth":[95,111],"estimation":[96],"each":[98,144],"pixel":[99],"utilize":[101],"it":[102],"guide":[104],"feature":[106,164],"mapping.":[107],"Further,":[108],"since":[109],"predicting":[110],"directly":[112],"from":[113],"monocular":[114],"ill-posed,":[117],"ignoring":[118],"stereo":[119],"such":[121],"as":[122],"temporal":[125],"cues,":[126],"introduces":[129],"voxel":[131,145],"visibility":[132],"segmentation":[133],"task":[134,140],"The":[139,187],"explicitly":[141],"predicts":[142],"whether":[143],"grid":[150],"occupied":[152],"or":[153],"not.":[154],"In":[155],"addition,":[156],"alleviate":[158],"overfitting":[160],"problem":[161],"learning":[165,174],"under":[166],"single":[168],"task,":[169],"design":[171],"multi-head":[173],"framework":[175],"jointly":[177],"models":[178],"multiple":[179],"strongly-correlated":[180],"tasks":[181],"effectiveness":[188],"proposed":[191],"fully":[194],"validated":[195],"on":[196,207],"nuScenes":[198,209],"dataset,":[199],"achieving":[200],"competetive":[202],"NDS/mAP":[203],"score":[204],"57.5/47.9":[206],"test":[210],"leaderboard":[211],"using":[212],"ResNet101":[213],"backbone,":[214],"superior":[217],"state-of-the-art":[219],"camera-based":[220],"solutions.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}