{"id":"https://openalex.org/W3197292052","doi":"https://doi.org/10.1145/3460426.3463603","title":"RGB-D Scene Recognition based on Object-Scene Relation and Semantics-Preserving Attention","display_name":"RGB-D Scene Recognition based on Object-Scene Relation and Semantics-Preserving Attention","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3197292052","doi":"https://doi.org/10.1145/3460426.3463603","mag":"3197292052"},"language":"en","primary_location":{"id":"doi:10.1145/3460426.3463603","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","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":true,"raw_author_name":"Yuhui Guo","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","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, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005891143"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54735737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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"}},{"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":0.9997000098228455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7826720476150513},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7493783831596375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7212167978286743},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.7117737531661987},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6466271281242371},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5997026562690735},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.571118950843811},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5365880131721497},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5027036666870117},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4927351772785187},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48009708523750305},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4710395634174347},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4701274335384369},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46288228034973145},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4474841058254242},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4318031966686249},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.228046715259552},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07567670941352844},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.067755788564682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7826720476150513},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7493783831596375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7212167978286743},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7117737531661987},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6466271281242371},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5997026562690735},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.571118950843811},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5365880131721497},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5027036666870117},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4927351772785187},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48009708523750305},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4710395634174347},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4701274335384369},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46288228034973145},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4474841058254242},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4318031966686249},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.228046715259552},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07567670941352844},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.067755788564682},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3460426.3463603","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1919033285","https://openalex.org/W1923184257","https://openalex.org/W1924160326","https://openalex.org/W2032699694","https://openalex.org/W2110628941","https://openalex.org/W2128532956","https://openalex.org/W2146022472","https://openalex.org/W2157331557","https://openalex.org/W2444163375","https://openalex.org/W2465570449","https://openalex.org/W2552002300","https://openalex.org/W2604627275","https://openalex.org/W2732026016","https://openalex.org/W2741601747","https://openalex.org/W2766445549","https://openalex.org/W2884561390","https://openalex.org/W2963758027","https://openalex.org/W2968004941","https://openalex.org/W2981510929","https://openalex.org/W3104752576"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W3208297503","https://openalex.org/W3119773509","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353","https://openalex.org/W4390871823","https://openalex.org/W4311555960"],"abstract_inverted_index":{"Scene":[0],"recognition":[1,117],"is":[2,79],"challenging":[3],"due":[4],"to":[5,57,75,82],"intra-class":[6],"diversity":[7],"and":[8,88,96,121],"inter-class":[9],"similarity.":[10],"Previous":[11],"works":[12],"recognize":[13],"scenes":[14],"either":[15],"with":[16,20],"global":[17],"representations":[18,22],"or":[19],"intermediate":[21],"of":[23,33,53,62,114],"objects.":[24],"By":[25],"contrast,":[26],"we":[27,41,71,109],"investigate":[28],"more":[29,80],"discriminative":[30],"sequential":[31],"representation":[32],"object-to-scene":[34],"relations":[35],"(SOSRs)":[36],"for":[37],"scene":[38,97,116],"recognition.":[39],"Particularly,":[40],"develop":[42],"an":[43],"Attention-Preserving":[44],"Memory-Learning":[45],"(APML)":[46],"model,":[47],"which":[48,78],"enforces":[49],"the":[50,54,59,63,67,84,90,105,111],"Memory":[51],"Network":[52,61],"semantic":[55],"domain":[56,65],"guide":[58],"Learning":[60],"appearance":[64],"in":[66],"learning":[68],"procedure.":[69],"Accordingly,":[70],"allocate":[72],"semantics-preserving":[73],"attention":[74],"different":[76],"objects,":[77],"effective":[81],"seek":[83],"key":[85],"encoded":[86,92],"SOSR":[87,93],"discard":[89],"misleading":[91],"between":[94],"objects":[95],"without":[98],"requiring":[99],"extra":[100],"labeled":[101],"data.":[102],"Based":[103],"on":[104,118],"proposed":[106],"APML":[107],"networks,":[108],"obtain":[110],"state-of-the-art":[112],"results":[113],"RGB-D":[115,120],"SUN":[119],"NYUD2":[122],"datasets.":[123]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}