{"id":"https://openalex.org/W2891054863","doi":"https://doi.org/10.1109/tip.2018.2872629","title":"Learning Effective RGB-D Representations for Scene Recognition","display_name":"Learning Effective RGB-D Representations for Scene Recognition","publication_year":2018,"publication_date":"2018-09-28","ids":{"openalex":"https://openalex.org/W2891054863","doi":"https://doi.org/10.1109/tip.2018.2872629","mag":"2891054863","pmid":"https://pubmed.ncbi.nlm.nih.gov/30281448"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2018.2872629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2018.2872629","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1809.06269","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xinhang Song","orcid":"https://orcid.org/0000-0002-0895-1076"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhang Song","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences, Beijing, CN"],"raw_orcid":"https://orcid.org/0000-0002-0895-1076","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences, Beijing, CN","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuqiang Jiang","orcid":"https://orcid.org/0000-0002-1596-4326"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqiang Jiang","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences, Beijing, CN"],"raw_orcid":"https://orcid.org/0000-0002-1596-4326","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences, Beijing, CN","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Luis Herranz","orcid":null},"institutions":[{"id":"https://openalex.org/I123044942","display_name":"Universitat Aut\u00f2noma de Barcelona","ror":"https://ror.org/052g8jq94","country_code":"ES","type":"education","lineage":["https://openalex.org/I123044942"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luis Herranz","raw_affiliation_strings":["Universitat Autonoma de Barcelona, Barcelona, Catalunya, ES"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Autonoma de Barcelona, Barcelona, Catalunya, ES","institution_ids":["https://openalex.org/I123044942"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chengpeng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengpeng Chen","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences, Beijing, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences, Beijing, CN","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0508,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.92369173,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"28","issue":"2","first_page":"980","last_page":"993"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.3610999882221222,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.3610999882221222,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.20000000298023224,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.07909999787807465,"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/rgb-color-model","display_name":"RGB color model","score":0.7235999703407288},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7164999842643738},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5547000169754028},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4171999990940094},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3952000141143799},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3707999885082245},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3497999906539917},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.33489999175071716},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"Activity recognition","score":0.3269999921321869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8356999754905701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.808899998664856},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.7235999703407288},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7164999842643738},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6281999945640564},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5547000169754028},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3707999885082245},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.3167000114917755},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C132900626","wikidata":"https://www.wikidata.org/wiki/Q7534733","display_name":"Sketch recognition","level":4,"score":0.2793999910354614},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25279998779296875}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tip.2018.2872629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2018.2872629","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:30281448","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30281448","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:arXiv.org:1809.06269","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.06269","pdf_url":"https://arxiv.org/pdf/1809.06269","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:ddd.uab.cat:304014","is_oa":true,"landing_page_url":"https://ddd.uab.cat/record/304014","pdf_url":null,"source":{"id":"https://openalex.org/S4306400380","display_name":"Dip\u00f2sit Digital de Documents de la UAB (Universitat Aut\u00f2noma de Barcelona)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123044942","host_organization_name":"Universitat Aut\u00f2noma de Barcelona","host_organization_lineage":["https://openalex.org/I123044942"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1809.06269","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.06269","pdf_url":"https://arxiv.org/pdf/1809.06269","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3605299792","display_name":"\u8de8\u7f51\u4e92\u8054\u89c6\u97f3\u9891\u5173\u8054\u5206\u6790\u4e0e\u641c\u7d22","funder_award_id":"61532018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7706496980","display_name":null,"funder_award_id":"2018M631583","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G7750894348","display_name":null,"funder_award_id":"BX201700255","funder_id":"https://openalex.org/F4320335768","funder_display_name":"National Postdoctoral Program for Innovative Talents"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335768","display_name":"National Postdoctoral Program for Innovative Talents","ror":null},{"id":"https://openalex.org/F4320336648","display_name":"National Program for Support of Top-notch Young Professionals","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W753847829","https://openalex.org/W1565402342","https://openalex.org/W1849277567","https://openalex.org/W1919033285","https://openalex.org/W1922904362","https://openalex.org/W1923184257","https://openalex.org/W1969366022","https://openalex.org/W1985238052","https://openalex.org/W1994488211","https://openalex.org/W2016053056","https://openalex.org/W2017814585","https://openalex.org/W2040999325","https://openalex.org/W2048790245","https://openalex.org/W2071524685","https://openalex.org/W2085411191","https://openalex.org/W2110306668","https://openalex.org/W2152161678","https://openalex.org/W2160921898","https://openalex.org/W2162915993","https://openalex.org/W2179352600","https://openalex.org/W2194775991","https://openalex.org/W2304737248","https://openalex.org/W2342662179","https://openalex.org/W2438305798","https://openalex.org/W2444163375","https://openalex.org/W2465570449","https://openalex.org/W2517292647","https://openalex.org/W2602364336","https://openalex.org/W2741601747","https://openalex.org/W2747141180","https://openalex.org/W2963603913","https://openalex.org/W2963956866","https://openalex.org/W6620707391","https://openalex.org/W6637373629","https://openalex.org/W6641069144","https://openalex.org/W6676766825","https://openalex.org/W6679792166","https://openalex.org/W6682778277","https://openalex.org/W6682864246","https://openalex.org/W6684191040","https://openalex.org/W6736073538"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"convolutional":[1,175],"networks":[2,179],"(CNN)":[3],"can":[4,131],"achieve":[5],"impressive":[6],"results":[7],"on":[8,153,205],"RGB":[9,123],"scene":[10,22,166,216],"recognition":[11,23,167,172],"thanks":[12],"to":[13,30,109,163,191],"large":[14],"datasets":[15],"such":[16],"as":[17,145],"Places.":[18],"In":[19],"contrast,":[20],"RGB-D":[21,34,136,160,165,206],"is":[24,44,100,143],"still":[25],"underdeveloped":[26],"in":[27,38,112,119,184],"comparison,":[28],"due":[29],"two":[31],"limitations":[32],"of":[33,47,104],"data":[35,49,190],"we":[36,63,156],"address":[37,64],"this":[39,65,129,154],"paper.":[40],"The":[41,87],"first":[42],"limitation":[43,66,99,130],"the":[45,101,120,146,150,158],"lack":[46],"depth":[48,105,113,141],"for":[50],"training":[51,74],"deep":[52],"learning":[53],"models.":[54],"Rather":[55],"than":[56],"fine":[57],"tuning":[58],"or":[59],"transferring":[60],"RGB-specific":[61],"features,":[62],"by":[67,134],"proposing":[68],"an":[69],"architecture":[70,173],"and":[71,176,198,209,212],"a":[72],"twostep":[73],"approach":[75,201],"that":[76,122,128,181],"directly":[77],"learns":[78],"effective":[79,193],"depth-specific":[80],"features":[81,194],"using":[82,135],"weak":[83],"supervision":[84],"via":[85],"patches.":[86],"resulting":[88,111],"RGBD":[89],"model":[90],"also":[91],"benefits":[92],"from":[93],"more":[94,139],"complementary":[95],"multimodal":[96],"features.":[97],"Another":[98],"short":[102],"range":[103],"sensors":[106],"(typically":[107],"0.5m":[108],"5.5m),":[110],"images":[114,124],"not":[115],"capturing":[116],"distant":[117],"objects":[118],"scenes":[121],"can.":[125],"We":[126],"show":[127],"be":[132],"addressed":[133],"videos,":[137],"where":[138],"comprehensive":[140],"information":[142],"accumulated":[144],"camera":[147],"travels":[148],"across":[149],"scenes.":[151],"Focusing":[152],"scenario,":[155],"introduce":[157],"ISIA":[159],"video":[161,171,213],"dataset":[162],"evaluate":[164],"with":[168,187],"videos.":[169],"Our":[170,200],"combines":[174],"recurrent":[177],"neural":[178],"(RNNs)":[180],"are":[182],"trained":[183],"three":[185],"steps":[186],"increasingly":[188],"complex":[189],"learn":[192],"(i.e.":[195],"patches,":[196],"frames":[197],"sequences).":[199],"obtains":[202],"state-of-the-art":[203],"performances":[204],"image":[207],"(NYUD2":[208],"SUN":[210],"RGB-D)":[211,215],"(ISIA":[214],"recognition.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2018-09-27T00:00:00"}