{"id":"https://openalex.org/W2766445549","doi":"https://doi.org/10.1145/3123266.3123300","title":"RGB-D Scene Recognition with Object-to-Object Relation","display_name":"RGB-D Scene Recognition with Object-to-Object Relation","publication_year":2017,"publication_date":"2017-10-19","ids":{"openalex":"https://openalex.org/W2766445549","doi":"https://doi.org/10.1145/3123266.3123300","mag":"2766445549"},"language":"en","primary_location":{"id":"doi:10.1145/3123266.3123300","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","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/A5055504013","display_name":"Xinhang Song","orcid":"https://orcid.org/0000-0002-0895-1076"},"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/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhang Song","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011528604","display_name":"Chengpeng Chen","orcid":"https://orcid.org/0000-0001-7754-344X"},"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/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengpeng Chen","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085719285","display_name":"Shuqiang Jiang","orcid":"https://orcid.org/0000-0002-1596-4326"},"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/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqiang Jiang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"600","last_page":"608"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10036","display_name":"Advanced Neural Network 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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9959999918937683,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.8153597116470337},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.746056079864502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7446619272232056},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6684513092041016},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5644040107727051},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4997289180755615},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49003541469573975},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4741089940071106},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.47378870844841003},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4520260989665985},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4375150799751282},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.4116177558898926},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.07528477907180786}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8153597116470337},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.746056079864502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7446619272232056},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6684513092041016},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5644040107727051},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4997289180755615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49003541469573975},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4741089940071106},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.47378870844841003},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4520260989665985},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4375150799751282},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.4116177558898926},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.07528477907180786},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3123266.3123300","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G8709429149","display_name":null,"funder_award_id":"61532018, 61322212","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W639708223","https://openalex.org/W753847829","https://openalex.org/W1524680991","https://openalex.org/W1536680647","https://openalex.org/W1565402342","https://openalex.org/W1589362500","https://openalex.org/W1849277567","https://openalex.org/W1919033285","https://openalex.org/W1923184257","https://openalex.org/W1924160326","https://openalex.org/W1956595878","https://openalex.org/W1969366022","https://openalex.org/W2027668556","https://openalex.org/W2027922120","https://openalex.org/W2032699694","https://openalex.org/W2033832873","https://openalex.org/W2086971086","https://openalex.org/W2088049833","https://openalex.org/W2097018403","https://openalex.org/W2098411764","https://openalex.org/W2102605133","https://openalex.org/W2103658758","https://openalex.org/W2107034620","https://openalex.org/W2109992539","https://openalex.org/W2118585731","https://openalex.org/W2125556102","https://openalex.org/W2133576408","https://openalex.org/W2146022472","https://openalex.org/W2159328468","https://openalex.org/W2168356304","https://openalex.org/W2304737248","https://openalex.org/W2444163375","https://openalex.org/W2465570449","https://openalex.org/W2508549879","https://openalex.org/W2520761760","https://openalex.org/W2963277399"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W4400595174","https://openalex.org/W2349635380","https://openalex.org/W4353089801","https://openalex.org/W2353819554","https://openalex.org/W2359488321","https://openalex.org/W2389866386"],"abstract_inverted_index":{"A":[0],"scene":[1,70,173],"is":[2,18,105],"usually":[3],"abstract":[4,10,34],"that":[5],"consists":[6],"of":[7,55,130,187],"several":[8],"less":[9],"entities":[11],"such":[12],"as":[13],"objects":[14,56],"or":[15,57],"themes.":[16,58],"It":[17],"very":[19],"difficult":[20],"to":[21,28,67,79,96,107,167,169],"reason":[22],"scenes":[23,35,44,64],"from":[24],"visual":[25,38],"features":[26,157,164],"due":[27],"the":[29,33,60,99,102,111,127,143,170,185,188],"semantic":[30,148],"gap":[31],"between":[32,63],"and":[36,122,151,181],"low-level":[37],"features.":[39],"Some":[40],"alternative":[41],"works":[42],"recognize":[43],"with":[45,52,82,86,135],"a":[46,77,136],"two-step":[47],"framework":[48,78],"by":[49,159],"representing":[50],"images":[51,81,124],"intermediate":[53,83],"representations":[54,85],"However,":[59],"object":[61,117],"co-occurrences":[62],"may":[65],"lead":[66],"ambiguity":[68],"for":[69,172],"recognition.":[71,174],"In":[72,94,110],"this":[73],"paper,":[74],"we":[75,114,146],"propose":[76],"represent":[80],"(object)":[84],"spatial":[87,100],"layout,":[88],"i.e.,":[89],"object-to-object":[90],"relation":[91],"(OOR)":[92],"representation.":[93],"order":[95],"better":[97],"capture":[98],"information,":[101],"proposed":[103,112,189],"OOR":[104,150],"adapted":[106],"RGB-D":[108,137,180],"data.":[109],"framework,":[113],"first":[115],"apply":[116],"detection":[118],"technique":[119],"on":[120,142,178],"RGB":[121],"depth":[123],"separately.":[125],"Then":[126],"detected":[128,144],"results":[129,177],"both":[131],"modalities":[132],"are":[133,165],"combined":[134],"proposal":[138],"fusion":[139],"process.":[140],"Based":[141],"results,":[145],"extract":[147],"feature":[149],"regional":[152],"convolutional":[153],"neural":[154],"network":[155],"(CNN)":[156],"located":[158],"bounding":[160],"boxes.":[161],"Finally,":[162],"different":[163],"concatenated":[166],"feed":[168],"classifier":[171],"The":[175],"experimental":[176],"SUN":[179],"NYUD2":[182],"datasets":[183],"illustrate":[184],"efficiency":[186],"method.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}