{"id":"https://openalex.org/W4413158305","doi":"https://doi.org/10.1109/cvpr52734.2025.01322","title":"DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering","display_name":"DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413158305","doi":"https://doi.org/10.1109/cvpr52734.2025.01322"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01322","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/A5101697281","display_name":"Jingzhou Luo","orcid":"https://orcid.org/0009-0001-7731-6746"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingzhou Luo","raw_affiliation_strings":["Sun Yat-sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051943832","display_name":"Y. Liu","orcid":"https://orcid.org/0000-0003-3615-2332"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Sun Yat-sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070234760","display_name":"Weixing Chen","orcid":"https://orcid.org/0000-0002-8081-1289"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixing Chen","raw_affiliation_strings":["Sun Yat-sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332655","display_name":"Zhen Li","orcid":"https://orcid.org/0000-0003-1166-9482"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073082132","display_name":"Yaowei Wang","orcid":"https://orcid.org/0000-0002-6110-4036"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowei Wang","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101691639","display_name":"Guanbin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanbin Li","raw_affiliation_strings":["Sun Yat-sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091957369","display_name":"Liang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["Sun Yat-sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2409,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94757633,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"14169","last_page":"14178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/dual","display_name":"Dual (grammatical number)","score":0.7761273384094238},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.758746862411499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6725890040397644},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6149792671203613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.601748526096344},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6014262437820435},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13645580410957336},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.08764714002609253}],"concepts":[{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7761273384094238},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.758746862411499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6725890040397644},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6149792671203613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.601748526096344},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6014262437820435},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13645580410957336},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.08764714002609253},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01322","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"}],"best_oa_location":null,"sustainable_development_goals":[],"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":31,"referenced_works":["https://openalex.org/W2555618208","https://openalex.org/W2594519801","https://openalex.org/W2752782242","https://openalex.org/W2795014656","https://openalex.org/W2963800628","https://openalex.org/W2964935470","https://openalex.org/W2966683369","https://openalex.org/W2970641574","https://openalex.org/W2988715931","https://openalex.org/W3009928773","https://openalex.org/W3017930107","https://openalex.org/W3035461736","https://openalex.org/W3035574168","https://openalex.org/W3095974555","https://openalex.org/W3107521863","https://openalex.org/W3117804044","https://openalex.org/W3138516171","https://openalex.org/W3167599226","https://openalex.org/W3168640669","https://openalex.org/W3170030651","https://openalex.org/W3203949114","https://openalex.org/W4226376247","https://openalex.org/W4312385518","https://openalex.org/W4385809408","https://openalex.org/W4386075854","https://openalex.org/W4390872495","https://openalex.org/W4393148430","https://openalex.org/W4395083692","https://openalex.org/W4402733575","https://openalex.org/W4403791922","https://openalex.org/W4412722243"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","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":{"3D":[0,13,43,82,111,150],"Question":[1],"Answering":[2],"(3D":[3],"QA)":[4],"requires":[5],"the":[6,17,48,61,125,129,143,180],"model":[7],"to":[8,60,99,107],"comprehensively":[9,100],"understand":[10],"its":[11,22],"situated":[12],"scene":[14,39,151],"described":[15],"by":[16,163],"text,":[18],"then":[19],"reason":[20],"about":[21],"surrounding":[23],"environment":[24],"and":[25,46,67,75,103,169,176],"answer":[26],"a":[27,93],"question":[28],"under":[29],"that":[30,122],"situation.":[31],"However,":[32],"existing":[33],"methods":[34],"usually":[35],"rely":[36],"on":[37,174],"global":[38],"perception":[40],"from":[41,55],"pure":[42],"point":[44,83,104,138],"clouds":[45],"overlook":[47],"importance":[49],"of":[50,128,182],"rich":[51],"local":[52],"texture":[53],"details":[54],"multi-view":[56,86,102,135],"images.":[57,87],"Moreover,":[58],"due":[59],"inherent":[62],"noise":[63],"in":[64,110],"camera":[65],"poses":[66],"complex":[68],"occlusions,":[69],"there":[70],"exists":[71],"significant":[72],"feature":[73,77],"degradation":[74],"reduced":[76],"robustness":[78,109],"problems":[79],"when":[80],"aligning":[81],"cloud":[84,105,139],"with":[85,137],"In":[88],"this":[89],"paper,":[90],"we":[91,141],"propose":[92],"Dual-vision":[94,145],"Scene":[95],"Perception":[96,146],"Network":[97],"(DSPNet),":[98],"integrate":[101],"features":[106],"improve":[108],"QA.":[112],"Our":[113],"Text-guided":[114],"Multi-view":[115],"Fusion":[116],"(TGMF)":[117],"module":[118,159],"prioritizes":[119],"image":[120],"views":[121],"closely":[123],"match":[124],"semantic":[126],"content":[127],"text.":[130],"To":[131],"adaptively":[132],"fuse":[133],"back-projected":[134],"images":[136],"features,":[140],"design":[142],"Adaptive":[144],"(ADVP)":[147],"module,":[148],"enhancing":[149],"comprehension.":[152],"Additionally,":[153],"our":[154,183],"Multimodal":[155],"Context-guided":[156],"Reasoning":[157],"(MCGR)":[158],"facilitates":[160],"robust":[161],"reasoning":[162],"integrating":[164],"contextual":[165],"information":[166],"across":[167],"visual":[168],"linguistic":[170],"modalities.":[171],"Experimental":[172],"results":[173],"SQA3D":[175],"ScanQA":[177],"datasets":[178],"demonstrate":[179],"superiority":[181],"DSPNet.":[184],"Codes":[185],"will":[186],"be":[187],"available":[188],"at":[189],"https://github.com/LZ-CH/DSPNet.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}