{"id":"https://openalex.org/W4285235844","doi":"https://doi.org/10.1109/tcsvt.2022.3171781","title":"Image Understanding With Reinforcement Learning: Auto-Tuning Image Attributes and Model Parameters for Object Detection and Segmentation","display_name":"Image Understanding With Reinforcement Learning: Auto-Tuning Image Attributes and Model Parameters for Object Detection and Segmentation","publication_year":2022,"publication_date":"2022-05-02","ids":{"openalex":"https://openalex.org/W4285235844","doi":"https://doi.org/10.1109/tcsvt.2022.3171781"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3171781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3171781","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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/A5030374805","display_name":"Fen Fang","orcid":"https://orcid.org/0000-0002-3834-4795"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fen Fang","raw_affiliation_strings":["Department of Visual Intelligence, Institute for Infocomm Research, A*STAR, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-3834-4795","affiliations":[{"raw_affiliation_string":"Department of Visual Intelligence, Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052143634","display_name":"Qianli Xu","orcid":"https://orcid.org/0000-0003-0105-5903"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qianli Xu","raw_affiliation_strings":["Department of Visual Intelligence, Institute for Infocomm Research, A*STAR, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-0105-5903","affiliations":[{"raw_affiliation_string":"Department of Visual Intelligence, Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001675146","display_name":"Yi Cheng","orcid":"https://orcid.org/0000-0002-5940-0581"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yi Cheng","raw_affiliation_strings":["Department of Visual Intelligence, Institute for Infocomm Research, A*STAR, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5940-0581","affiliations":[{"raw_affiliation_string":"Department of Visual Intelligence, Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100649794","display_name":"Ying Sun","orcid":"https://orcid.org/0000-0002-7224-6726"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ying Sun","raw_affiliation_strings":["Department of Visual Intelligence, Institute for Infocomm Research, A*STAR, Singapore","Centre for Frontier AI Research, A*STAR, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7224-6726","affiliations":[{"raw_affiliation_string":"Department of Visual Intelligence, Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Centre for Frontier AI Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077258552","display_name":"Joo\u2010Hwee Lim","orcid":"https://orcid.org/0000-0002-4103-3824"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Joo-Hwee Lim","raw_affiliation_strings":["Department of Visual Intelligence, Institute for Infocomm Research, A*STAR, Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4103-3824","affiliations":[{"raw_affiliation_string":"Department of Visual Intelligence, Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8122,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75988486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"32","issue":"10","first_page":"6671","last_page":"6685"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9966999888420105,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9966999888420105,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9955000281333923,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9944000244140625,"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":0.7585842609405518},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7522911429405212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6914955377578735},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.6585103273391724},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5828845500946045},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5630854368209839},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5427958369255066},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5328035354614258},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4819583594799042},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4489724040031433},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.430311918258667},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.40345093607902527},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34092628955841064}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7585842609405518},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7522911429405212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6914955377578735},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.6585103273391724},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5828845500946045},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5630854368209839},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5427958369255066},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5328035354614258},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4819583594799042},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4489724040031433},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.430311918258667},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.40345093607902527},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34092628955841064},{"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:10.1109/tcsvt.2022.3171781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3171781","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1680797894","https://openalex.org/W1861492603","https://openalex.org/W1979393293","https://openalex.org/W2031489346","https://openalex.org/W2039875163","https://openalex.org/W2093834886","https://openalex.org/W2104095591","https://openalex.org/W2114705035","https://openalex.org/W2116040950","https://openalex.org/W2150856297","https://openalex.org/W2158782408","https://openalex.org/W2179488730","https://openalex.org/W2193145675","https://openalex.org/W2469312016","https://openalex.org/W2570599740","https://openalex.org/W2609701065","https://openalex.org/W2616240092","https://openalex.org/W2769883686","https://openalex.org/W2770898551","https://openalex.org/W2777138218","https://openalex.org/W2786344118","https://openalex.org/W2883872876","https://openalex.org/W2884367402","https://openalex.org/W2921935742","https://openalex.org/W2946469828","https://openalex.org/W2946987243","https://openalex.org/W2949736877","https://openalex.org/W2962793481","https://openalex.org/W2963037989","https://openalex.org/W2963466723","https://openalex.org/W2963677766","https://openalex.org/W2963897760","https://openalex.org/W2963967766","https://openalex.org/W2964053787","https://openalex.org/W2972006294","https://openalex.org/W2996678997","https://openalex.org/W2997189783","https://openalex.org/W3004594394","https://openalex.org/W3009184501","https://openalex.org/W3009447447","https://openalex.org/W3035175896","https://openalex.org/W3043995050","https://openalex.org/W3076143500","https://openalex.org/W3083531979","https://openalex.org/W3095921757","https://openalex.org/W3106250896","https://openalex.org/W3106704289","https://openalex.org/W3112027556","https://openalex.org/W3113769242","https://openalex.org/W3163153368","https://openalex.org/W3176732771","https://openalex.org/W6685444567","https://openalex.org/W6687681856"],"related_works":["https://openalex.org/W2517104666","https://openalex.org/W2613186388","https://openalex.org/W2187221949","https://openalex.org/W2734888972","https://openalex.org/W2536634271","https://openalex.org/W2739874619","https://openalex.org/W1485614034","https://openalex.org/W3112953119","https://openalex.org/W2112454231","https://openalex.org/W2909428641"],"abstract_inverted_index":{"Models":[0],"for":[1,84,116],"image":[2,94,117,136],"semantics":[3],"understanding,":[4],"such":[5,27],"as":[6,79],"deep":[7],"learning":[8,60,75],"(DL)":[9],"models":[10,28,144],"and":[11,87,106,141,159],"mathematical":[12,112],"models,":[13],"are":[14],"often":[15],"trained":[16],"on":[17,29,102,151,171,179,197],"specific":[18,23],"dataset":[19,162],"or":[20,45],"configured":[21],"with":[22,201],"parameters.":[24,51],"When":[25],"deploying":[26],"new":[30],"tasks":[31],"in":[32,126],"a":[33,57,80,121,127,160],"different":[34],"test":[35],"environment,":[36],"it":[37],"requires":[38],"considerable":[39,194],"effort":[40],"to":[41,48,66,70,89,97,131],"re-train":[42],"the":[43,50,111,180],"model":[44,72,113],"extensive":[46],"expertise":[47],"tune":[49,67,133],"In":[52],"this":[53],"paper,":[54],"we":[55,167],"propose":[56],"smart":[58],"reinforcement":[59],"(RL)":[61],"agent":[62,130],"that":[63,190],"could":[64],"learn":[65],"parameters":[68,134],"automatically":[69],"enhance":[71],"performance.":[73],"The":[74],"process":[76],"is":[77],"formulated":[78],"generic":[81],"control":[82],"task":[83],"parameter":[85,108,182],"adjustment,":[86],"applied":[88],"two":[90],"use":[91],"scenarios:":[92],"(1)":[93],"attributes":[95],"tuning":[96,109,183],"improve":[98],"object":[99,139,146,172],"detection":[100,173],"performance":[101,195],"fixed":[103],"DL":[104],"model,":[105],"(2)":[107],"of":[110,135,163,184],"(Level":[114],"Set)":[115],"segmentation.":[118],"We":[119,148,175],"design":[120],"novel":[122],"dynamic":[123],"threshold":[124],"mechanism":[125],"multi-branch":[128],"RL":[129],"effectively":[132],"qualities":[137],"(for":[138,145],"detection)":[140],"Level":[142,185],"Set":[143,186],"segmentation).":[147],"conduct":[149],"experiments":[150,178],"Pascal-VOC":[152],"testing":[153],"set,":[154],"MS":[155],"COCO":[156],"validation":[157],"set":[158],"proprietary":[161],"industrial":[164],"components,":[165],"where":[166],"achieve":[168],"substantial":[169],"improvement":[170,196],"accuracy.":[174],"also":[176],"perform":[177],"automatic":[181],"models.":[187],"Results":[188],"show":[189],"our":[191],"method":[192],"facilitates":[193],"public":[198],"datasets":[199],"compared":[200],"baseline":[202],"method.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}