{"id":"https://openalex.org/W4403792289","doi":"https://doi.org/10.1145/3664647.3681293","title":"FusionOcc: Multi-Modal Fusion for 3D Occupancy Prediction","display_name":"FusionOcc: Multi-Modal Fusion for 3D Occupancy Prediction","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792289","doi":"https://doi.org/10.1145/3664647.3681293"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681293","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681293","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/A5100450399","display_name":"Shuo Zhang","orcid":"https://orcid.org/0000-0003-1032-5151"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuo Zhang","raw_affiliation_strings":["Zhejiang Lab, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108314655","display_name":"Y. C. Zhai","orcid":"https://orcid.org/0009-0002-9576-1429"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupeng Zhai","raw_affiliation_strings":["Zhejiang Lab, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064630457","display_name":"Jilin Mei","orcid":"https://orcid.org/0000-0002-3326-1632"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jilin Mei","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100721270","display_name":"Yu Hu","orcid":"https://orcid.org/0000-0001-8818-4075"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Hu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100450399"],"corresponding_institution_ids":["https://openalex.org/I4210123185"],"apc_list":null,"apc_paid":null,"fwci":0.7716,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6860471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"787","last_page":"796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9926999807357788,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9919000267982483,"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/occupancy","display_name":"Occupancy","score":0.7890312075614929},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6452987194061279},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.6065508127212524},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5902112126350403},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10684776306152344},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.060428231954574585},{"id":"https://openalex.org/keywords/architectural-engineering","display_name":"Architectural engineering","score":0.04213899374008179}],"concepts":[{"id":"https://openalex.org/C160331591","wikidata":"https://www.wikidata.org/wiki/Q7075743","display_name":"Occupancy","level":2,"score":0.7890312075614929},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6452987194061279},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6065508127212524},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5902112126350403},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10684776306152344},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.060428231954574585},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.04213899374008179},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681293","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681293","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":30,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2557465155","https://openalex.org/W2594519801","https://openalex.org/W2752782242","https://openalex.org/W2963926543","https://openalex.org/W2991216808","https://openalex.org/W3035172746","https://openalex.org/W3035574168","https://openalex.org/W3117804044","https://openalex.org/W3138516171","https://openalex.org/W3174692508","https://openalex.org/W3177330511","https://openalex.org/W3179351458","https://openalex.org/W3179909833","https://openalex.org/W3198790326","https://openalex.org/W3203597819","https://openalex.org/W3215584334","https://openalex.org/W4212774754","https://openalex.org/W4312414163","https://openalex.org/W4312559648","https://openalex.org/W4312707458","https://openalex.org/W4312894406","https://openalex.org/W4383066393","https://openalex.org/W4386076253","https://openalex.org/W4386083035","https://openalex.org/W4390873564","https://openalex.org/W4390873604","https://openalex.org/W4390874087","https://openalex.org/W4390874575","https://openalex.org/W4402713134"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4282043467","https://openalex.org/W2105697914","https://openalex.org/W3093197249","https://openalex.org/W1968324288","https://openalex.org/W1540010871","https://openalex.org/W3023979140","https://openalex.org/W3177545769"],"abstract_inverted_index":{"3D":[0,33,65,91,129,150,205],"occupancy":[1,11,66,206],"prediction":[2,67],"(OCC)":[3],"aims":[4],"to":[5,108,187],"estimate":[6],"and":[7,23,75,90,120,140,175],"predict":[8,109],"the":[9,14,26,96,157,161,188],"semantic":[10],"state":[12,159],"of":[13,71,84,124,134,160,170,184],"surrounding":[15],"environment,":[16],"which":[17],"is":[18,43,106],"crucial":[19],"for":[20,32,64,198,204],"scene":[21],"understanding":[22],"reconstruction":[24],"in":[25,46,88,149,201],"real":[27],"world.":[28],"However,":[29],"existing":[30],"methods":[31],"OCC":[34],"mainly":[35],"rely":[36],"on":[37,163],"surround-view":[38,76],"camera":[39],"images,":[40,77],"whose":[41],"performance":[42],"still":[44],"insufficient":[45],"some":[47],"challenging":[48],"scenarios,":[49],"such":[50],"as":[51],"low-light":[52],"conditions.":[53],"To":[54],"this":[55],"end,":[56],"we":[57],"propose":[58],"a":[59,102,110,121,147,167,195],"new":[60,158,196],"multi-modal":[61,202],"fusion":[62,104,203],"network":[63],"by":[68,146],"fusing":[69],"features":[70,83,127,133,144],"LiDAR":[72],"point":[73,100,136],"clouds":[74,137],"called":[78],"FusionOcc.":[79],"Our":[80,192],"model":[81],"fuses":[82],"these":[85],"two":[86],"modals":[87],"2D":[89,111,125],"space,":[92],"respectively.":[93],"By":[94],"integrating":[95],"depth":[97,113,118],"information":[98],"from":[99],"clouds,":[101],"cross-modal":[103],"module":[105],"designed":[107],"dense":[112],"map,":[114],"enabling":[115],"an":[116,181],"accurate":[117],"estimation":[119],"better":[122],"transition":[123],"image":[126,143],"into":[128],"space.":[130,151],"In":[131],"addition,":[132],"voxelized":[135],"are":[138],"aligned":[139],"merged":[141],"with":[142],"converted":[145],"view-transformer":[148],"Experiments":[152],"show":[153],"that":[154],"FusionOcc":[155],"establishes":[156],"art":[162],"Occ3D-nuScenes":[164],"dataset,":[165],"achieving":[166],"mIoU":[168],"score":[169],"35.94%":[171],"(without":[172],"visibility":[173,178],"mask)":[174],"56.62%":[176],"(with":[177],"mask),":[179],"showing":[180],"average":[182],"improvement":[183],"3.42%":[185],"compared":[186],"best":[189],"previous":[190],"method.":[191],"work":[193],"provides":[194],"baseline":[197],"further":[199],"research":[200],"prediction.":[207],"Codes":[208],"will":[209],"be":[210],"made":[211],"publicly":[212],"at":[213],"https://github.com/ShuoZhang-code/FusionOcc.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}