{"id":"https://openalex.org/W4372340824","doi":"https://doi.org/10.1109/icassp49357.2023.10095978","title":"Cross-Modal Matching and Adaptive Graph Attention Network for RGB-D Scene Recognition","display_name":"Cross-Modal Matching and Adaptive Graph Attention Network for RGB-D Scene Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372340824","doi":"https://doi.org/10.1109/icassp49357.2023.10095978"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5005891143","display_name":"Yuhui Guo","orcid":"https://orcid.org/0000-0002-4833-7003"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhui Guo","raw_affiliation_strings":["Renmin University of China,School of Information,Department of Computer Science","Department of Computer Science, School of Information, Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China,School of Information,Department of Computer Science","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Department of Computer Science, School of Information, Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020649203","display_name":"Xun Liang","orcid":"https://orcid.org/0000-0002-3431-5954"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Liang","raw_affiliation_strings":["Renmin University of China,School of Information,Department of Computer Science","Department of Computer Science, School of Information, Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China,School of Information,Department of Computer Science","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Department of Computer Science, School of Information, Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070273088","display_name":"James T. Kwok","orcid":"https://orcid.org/0000-0002-4828-8248"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"James T. Kwok","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068664003","display_name":"Xiangping Zheng","orcid":"https://orcid.org/0000-0001-8653-6225"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangping Zheng","raw_affiliation_strings":["Renmin University of China,School of Information,Department of Computer Science","Department of Computer Science, School of Information, Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China,School of Information,Department of Computer Science","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Department of Computer Science, School of Information, Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101978182","display_name":"Bo Wu","orcid":"https://orcid.org/0000-0001-7266-084X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Wu","raw_affiliation_strings":["Renmin University of China,School of Information,Department of Computer Science","Department of Computer Science, School of Information, Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China,School of Information,Department of Computer Science","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Department of Computer Science, School of Information, Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016666403","display_name":"Yuefeng Ma","orcid":"https://orcid.org/0000-0002-5245-8510"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuefeng Ma","raw_affiliation_strings":["Qufu Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qufu Normal University","institution_ids":["https://openalex.org/I202126657"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2246,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48590861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9983999729156494,"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":0.8026230931282043},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7265676856040955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6129883527755737},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6004169583320618},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5716028809547424},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5366209745407104},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5147202610969543},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4828941822052002},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4369966983795166},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4365946054458618},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4308663308620453},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1352452039718628},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06726852059364319}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8026230931282043},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7265676856040955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6129883527755737},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6004169583320618},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5716028809547424},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5366209745407104},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5147202610969543},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4828941822052002},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4369966983795166},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4365946054458618},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4308663308620453},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1352452039718628},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06726852059364319},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-135439","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-135439","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1895577753","https://openalex.org/W1923184257","https://openalex.org/W1924160326","https://openalex.org/W2207044458","https://openalex.org/W2444163375","https://openalex.org/W2475223347","https://openalex.org/W2489780108","https://openalex.org/W2552002300","https://openalex.org/W2604627275","https://openalex.org/W2732026016","https://openalex.org/W2890231609","https://openalex.org/W2905312384","https://openalex.org/W2911247705","https://openalex.org/W2941724331","https://openalex.org/W2963758027","https://openalex.org/W2968004941","https://openalex.org/W3104752576","https://openalex.org/W4297733535","https://openalex.org/W4301002706","https://openalex.org/W6631190155","https://openalex.org/W6745537798"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W2377397762","https://openalex.org/W2793967660","https://openalex.org/W627697492"],"abstract_inverted_index":{"Despite":[0],"the":[1,24,51,65,70,74,104,114,121,133],"significant":[2],"advances":[3],"in":[4,39],"RGB-D":[5],"scene":[6],"recognition,":[7,58],"there":[8],"are":[9,94,111],"several":[10],"major":[11],"limitations":[12],"that":[13],"need":[14],"further":[15],"investigation.":[16],"For":[17],"example,":[18],"simply":[19],"extracting":[20],"modal-specific":[21,57],"features":[22,34,87,93,110],"neglects":[23],"complex":[25],"relationships":[26],"among":[27],"multiple":[28],"modalities":[29],"of":[30,53,73,99],"features.":[31],"Moreover,":[32],"cross-modal":[33,54,66],"have":[35],"not":[36],"been":[37],"considered":[38],"most":[40],"existing":[41],"methods.":[42],"To":[43],"address":[44],"these":[45],"concerns,":[46],"we":[47],"propose":[48],"to":[49,102,138],"integrate":[50],"tasks":[52],"matching":[55,67],"and":[56,107,125],"termed":[59],"as":[60],"Matching-to-Recognition":[61],"Network":[62],"(MRNet).":[63],"Specifically,":[64],"network":[68,76,84],"enhances":[69],"descriptive":[71],"power":[72],"recognition":[75,83,143],"via":[77],"a":[78,89,97,100],"layer-wise":[79],"semantic":[80,105],"loss.":[81],"The":[82],"obtains":[85],"multi-modal":[86],"from":[88],"two-stream":[90],"CNN:":[91],"global":[92],"obtained":[95],"by":[96,113],"higher-layer":[98],"CNN":[101],"preserve":[103],"content,":[106],"local":[108],"layout":[109],"learned":[112],"graph":[115],"attention":[116],"network,":[117],"thus":[118],"better":[119],"capturing":[120],"key":[122],"object":[123],"regions":[124],"modelling":[126],"their":[127],"relationships.":[128],"Extensive":[129],"experiments":[130],"results":[131],"demonstrate":[132],"MRNet":[134],"achieves":[135],"superior":[136],"performance":[137],"state-of-the-art":[139],"methods,":[140],"especially":[141],"for":[142],"solely":[144],"based":[145],"on":[146],"single":[147],"modality.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}