{"id":"https://openalex.org/W4413157181","doi":"https://doi.org/10.1109/cvpr52734.2025.00355","title":"Beyond Human Perception: Understanding Multi-Object World from Monocular View","display_name":"Beyond Human Perception: Understanding Multi-Object World from Monocular View","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413157181","doi":"https://doi.org/10.1109/cvpr52734.2025.00355"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5111012169","display_name":"Keyu Guo","orcid":"https://orcid.org/0009-0005-0699-3992"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyu Guo","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102665049","display_name":"Yongle Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongle Huang","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103070400","display_name":"Shijie Sun","orcid":"https://orcid.org/0000-0003-4043-8448"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijie Sun","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053270215","display_name":"Xiangyu Song","orcid":"https://orcid.org/0000-0002-5550-6354"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Song","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087490575","display_name":"Mingtao Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingtao Feng","raw_affiliation_strings":["Xidian University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110814983","display_name":"Zedong Liu","orcid":"https://orcid.org/0009-0000-0345-804X"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zedong Liu","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008672520","display_name":"Huansheng Song","orcid":"https://orcid.org/0000-0002-8590-0061"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huansheng Song","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101468201","display_name":"Tiantian Wang","orcid":"https://orcid.org/0000-0003-2358-9893"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiantian Wang","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380471","display_name":"Jianxin Li","orcid":"https://orcid.org/0000-0002-4590-7939"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxin Li","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103837157","display_name":"Naveed Akhtar","orcid":"https://orcid.org/0009-0005-6999-9865"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Naveed Akhtar","raw_affiliation_strings":["The University of Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne,Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089986388","display_name":"Ajmal Mian","orcid":"https://orcid.org/0000-0002-5206-3842"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ajmal Saeed Mian","raw_affiliation_strings":["University of Western Australia,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Western Australia,Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3751","last_page":"3760"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14163","display_name":"Astronomical Observations and Instrumentation","score":0.06030000001192093,"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/T14163","display_name":"Astronomical Observations and Instrumentation","score":0.06030000001192093,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.04490000009536743,"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":0.672409176826477},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6438459753990173},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5941985249519348},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5543615818023682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5468312501907349},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5231691002845764},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3516034483909607},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16850391030311584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.672409176826477},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6438459753990173},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5941985249519348},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5543615818023682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5468312501907349},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5231691002845764},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3516034483909607},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16850391030311584},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/305ab6d0-3616-4ab1-8f63-0a827bb31428","is_oa":false,"landing_page_url":"https://admin.research-repository.uwa.edu.au/en/publications/305ab6d0-3616-4ab1-8f63-0a827bb31428","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1964291102","https://openalex.org/W1965480313","https://openalex.org/W1989689139","https://openalex.org/W2062860282","https://openalex.org/W2074859404","https://openalex.org/W2100345559","https://openalex.org/W2112575618","https://openalex.org/W2121292693","https://openalex.org/W2488042550","https://openalex.org/W2619383789","https://openalex.org/W2765433083","https://openalex.org/W2970414448","https://openalex.org/W3008115128","https://openalex.org/W3041953040","https://openalex.org/W3095974555","https://openalex.org/W3102927640","https://openalex.org/W3107521863","https://openalex.org/W3133833192","https://openalex.org/W3179868941","https://openalex.org/W3187295906","https://openalex.org/W3203949114","https://openalex.org/W4213019189","https://openalex.org/W4214684415","https://openalex.org/W4230858411","https://openalex.org/W4231598665","https://openalex.org/W4312309370","https://openalex.org/W4312385518","https://openalex.org/W4312713480","https://openalex.org/W4367595583","https://openalex.org/W4384561707","https://openalex.org/W4390874439","https://openalex.org/W4393156227","https://openalex.org/W4402754162","https://openalex.org/W4402754253","https://openalex.org/W4402961736","https://openalex.org/W4403003250","https://openalex.org/W4409366009","https://openalex.org/W4411403346"],"related_works":["https://openalex.org/W200819717","https://openalex.org/W2032269556","https://openalex.org/W1991834176","https://openalex.org/W2944448661","https://openalex.org/W2064421702","https://openalex.org/W4253756925","https://openalex.org/W2805523177","https://openalex.org/W2131956013","https://openalex.org/W2036566443","https://openalex.org/W2081241816"],"abstract_inverted_index":{"Language":[0],"and":[1,47,91,107,133,140,164],"binocular":[2],"vision":[3],"play":[4],"a":[5,58,70,102,109,114,121],"crucial":[6],"role":[7],"in":[8,15,42],"human":[9],"understanding":[10,56],"of":[11],"the":[12,94,159],"world.":[13,96],"Advancements":[14],"artificial":[16],"intelligence":[17],"have":[18],"also":[19],"made":[20],"it":[21],"possible":[22],"for":[23,31,145],"machines":[24,51,87],"to":[25,45,52,88,127,137],"develop":[26],"3D":[27,55,77,95],"perception":[28],"capabilities":[29],"essential":[30],"high-level":[32],"scene":[33],"understanding.":[34],"However,":[35],"only":[36],"monocular":[37,59,83],"cameras":[38],"are":[39,166],"often":[40],"available":[41,167],"practice":[43],"due":[44],"cost":[46],"space":[48],"constraints.":[49],"Enabling":[50],"achieve":[53,128],"accurate":[54],"from":[57],"view":[60],"is":[61],"practical":[62],"but":[63],"presents":[64],"significant":[65],"challenges.":[66],"We":[67],"introduce":[68],"MonoMulti-3DVG,":[69],"novel":[71],"task":[72],"aimed":[73],"at":[74,168],"achieving":[75],"multi-object":[76],"Visual":[78,116],"Grounding":[79],"(3DVG)":[80],"based":[81],"on":[82,158],"RGB":[84],"images,":[85],"allowing":[86],"better":[89],"understand":[90],"interact":[92],"with":[93,120],"To":[97],"this":[98],"end,":[99],"we":[100],"construct":[101],"large-scale":[103],"benchmark":[104],"dataset,":[105],"MonoMulti3D-ROPE,":[106],"propose":[108],"model,":[110],"CyclopsNet":[111],"that":[112,151],"integrates":[113],"State-Prompt":[115],"Encoder":[117],"(SPVE)":[118],"module":[119,126],"Denoising":[122],"Alignment":[123],"Fusion":[124],"(DAF)":[125],"robust":[129,141],"multi-modal":[130,142],"semantic":[131],"alignment":[132],"fusion.":[134],"This":[135],"leads":[136],"more":[138],"stable":[139],"joint":[143],"representations":[144],"downstream":[146],"tasks.":[147],"Experimental":[148],"results":[149],"show":[150],"our":[152],"method":[153],"significantly":[154],"outperforms":[155],"existing":[156],"techniques":[157],"MonoMulti3D-ROPE":[160],"dataset.":[161],"Our":[162],"dataset":[163],"code":[165],"https://github.com/JasonHuang516/MonoMulti-3DVG":[169]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}
