{"id":"https://openalex.org/W2219747066","doi":"https://doi.org/10.1109/icra.2016.7487381","title":"Understand scene categories by objects: A semantic regularized scene classifier using Convolutional Neural Networks","display_name":"Understand scene categories by objects: A semantic regularized scene classifier using Convolutional Neural Networks","publication_year":2016,"publication_date":"2016-05-01","ids":{"openalex":"https://openalex.org/W2219747066","doi":"https://doi.org/10.1109/icra.2016.7487381","mag":"2219747066"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2016.7487381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2016.7487381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Robotics and Automation (ICRA)","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/A5018811297","display_name":"Yiyi Liao","orcid":"https://orcid.org/0000-0001-6662-3022"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiyi Liao","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Zhejiang University, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Zhejiang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053565868","display_name":"Sarath Kodagoda","orcid":"https://orcid.org/0000-0001-5175-9138"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sarath Kodagoda","raw_affiliation_strings":["Sarath Kodagoda and Lei Shi are with the Centre for Autonomous Systems (CAS), The University of Technology, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sarath Kodagoda and Lei Shi are with the Centre for Autonomous Systems (CAS), The University of Technology, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371992","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0002-0981-935X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Zhejiang University, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Zhejiang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100666184","display_name":"Lei Shi","orcid":"https://orcid.org/0000-0002-5215-025X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Shi","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Zhejiang University, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Zhejiang, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100724297","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0003-4822-8939"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Zhejiang University, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Zhejiang, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.529,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":{"value":0.97114199,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2318","last_page":"2325"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9940000176429749,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.8507567644119263},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8036016225814819},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7099526524543762},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6096038222312927},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5905373096466064},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5698009729385376},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5500341057777405},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.49852466583251953},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4907184839248657},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4662697911262512},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.44978439807891846},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.41847944259643555},{"id":"https://openalex.org/keywords/scene-statistics","display_name":"Scene statistics","score":0.415807843208313},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3898393511772156},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.2789067029953003}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8507567644119263},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8036016225814819},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7099526524543762},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6096038222312927},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5905373096466064},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5698009729385376},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5500341057777405},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.49852466583251953},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4907184839248657},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4662697911262512},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.44978439807891846},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.41847944259643555},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.415807843208313},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3898393511772156},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2789067029953003},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2016.7487381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2016.7487381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1565402342","https://openalex.org/W1566135517","https://openalex.org/W1899185266","https://openalex.org/W1903029394","https://openalex.org/W1923184257","https://openalex.org/W1966385142","https://openalex.org/W2062118960","https://openalex.org/W2066813062","https://openalex.org/W2067506101","https://openalex.org/W2106624428","https://openalex.org/W2107672745","https://openalex.org/W2123099218","https://openalex.org/W2125849446","https://openalex.org/W2134670479","https://openalex.org/W2137881638","https://openalex.org/W2147880316","https://openalex.org/W2152571752","https://openalex.org/W2155541015","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2169177311","https://openalex.org/W2963038646","https://openalex.org/W2963996492","https://openalex.org/W4294375521","https://openalex.org/W6629098493","https://openalex.org/W6639927594","https://openalex.org/W6640054144","https://openalex.org/W6666899075","https://openalex.org/W6676415162","https://openalex.org/W6679792166","https://openalex.org/W6680357304","https://openalex.org/W6682082992","https://openalex.org/W6682778277","https://openalex.org/W6684191040","https://openalex.org/W6684872329"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Scene":[0],"classification":[1,83,123],"is":[2,51,94],"a":[3,97,129,145,166,175],"fundamental":[4],"perception":[5],"task":[6],"for":[7,54],"environmental":[8],"understanding":[9,72],"in":[10,36,171],"today's":[11],"robotics.":[12],"In":[13,135],"this":[14],"paper,":[15],"we":[16,77,114,156],"have":[17,42],"attempted":[18],"to":[19,31,58,89,110,125,165],"exploit":[20],"the":[21,46,79,116,126,141,179,183],"use":[22],"of":[23,28,81,99,138,168,182],"popular":[24],"machine":[25],"learning":[26,30,56],"technique":[27],"deep":[29,55,86,118],"enhance":[32],"scene":[33,40,63,71,82,122,153],"understanding,":[34],"particularly":[35],"robotics":[37],"applications.":[38],"As":[39],"images":[41,64,169],"larger":[43],"diversity":[44],"than":[45],"iconic":[47],"object":[48,75],"images,":[49,107,113],"it":[50],"more":[52],"challenging":[53],"methods":[57],"automatically":[59],"learn":[60],"features":[61],"from":[62,151],"with":[65,96,148],"less":[66],"samples.":[67],"Inspired":[68],"by":[69,84],"human":[70],"based":[73],"on":[74,128,161],"knowledge,":[76],"address":[78],"problem":[80],"encouraging":[85],"neural":[87],"networks":[88],"incorporate":[90],"object-level":[91],"information.":[92],"This":[93],"implemented":[95],"regularization":[98],"semantic":[100,139],"segmentation.":[101],"With":[102],"only":[103],"5":[104],"thousand":[105],"training":[106],"as":[108],"opposed":[109],"2.5":[111],"million":[112],"show":[115],"proposed":[117,184],"architecture":[119],"achieves":[120],"superior":[121],"results":[124],"state-of-the-art":[127],"publicly":[130],"available":[131],"SUN":[132,162],"RGB-D":[133,163],"dataset.":[134],"addition,":[136],"performance":[137],"segmentation,":[140],"regularizer,":[142],"also":[143],"reaches":[144],"new":[146],"record":[147],"refinement":[149],"derived":[150],"predicted":[152],"labels.":[154],"Finally,":[155],"apply":[157],"our":[158,172],"model":[159],"trained":[160],"dataset":[164],"set":[167],"captured":[170],"university":[173],"using":[174],"mobile":[176],"robot,":[177],"demonstrating":[178],"generalization":[180],"ability":[181],"algorithm.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}