{"id":"https://openalex.org/W2887325417","doi":"https://doi.org/10.1109/iros.2018.8593736","title":"In pixels we trust: From Pixel Labeling to Object Localization and Scene Categorization","display_name":"In pixels we trust: From Pixel Labeling to Object Localization and Scene Categorization","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2887325417","doi":"https://doi.org/10.1109/iros.2018.8593736","mag":"2887325417"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8593736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5016968127","display_name":"Carlos Herranz-Perdiguero","orcid":null},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Carlos Herranz-Perdiguero","raw_affiliation_strings":["Department of Signal Theory and Communications, University of Alcal\u00e1, Alcal\u00e1 de Henares, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, University of Alcal\u00e1, Alcal\u00e1 de Henares, Spain","institution_ids":["https://openalex.org/I189268942"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003445562","display_name":"Carolina Redondo-Cabrera","orcid":null},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carolina Redondo-Cabrera","raw_affiliation_strings":["Department of Signal Theory and Communications, University of Alcal\u00e1, Alcal\u00e1 de Henares, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, University of Alcal\u00e1, Alcal\u00e1 de Henares, Spain","institution_ids":["https://openalex.org/I189268942"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042331786","display_name":"Roberto J. L\u00f3pez-Sastre","orcid":"https://orcid.org/0000-0002-2477-0152"},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Roberto J. Lopez-Sastre","raw_affiliation_strings":["Department of Signal Theory and Communications, University of Alcal\u00e1, Alcal\u00e1 de Henares, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, University of Alcal\u00e1, Alcal\u00e1 de Henares, Spain","institution_ids":["https://openalex.org/I189268942"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016968127"],"corresponding_institution_ids":["https://openalex.org/I189268942"],"apc_list":null,"apc_paid":null,"fwci":0.4178,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.66793294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"355","last_page":"361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8434377908706665},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.8159963488578796},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7610913515090942},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7588083148002625},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7548370361328125},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7200077176094055},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.710537314414978},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.626089334487915},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.625820517539978},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6227138638496399},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6185950040817261},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5739662051200867},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5062550902366638},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4834943115711212},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4319917857646942},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2540086507797241}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8434377908706665},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8159963488578796},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7610913515090942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7588083148002625},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7548370361328125},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7200077176094055},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.710537314414978},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.626089334487915},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.625820517539978},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6227138638496399},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6185950040817261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5739662051200867},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5062550902366638},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4834943115711212},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4319917857646942},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2540086507797241},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"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/iros.2018.8593736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1565402342","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W1905829557","https://openalex.org/W1969366022","https://openalex.org/W1994956562","https://openalex.org/W2017814585","https://openalex.org/W2066813062","https://openalex.org/W2067912884","https://openalex.org/W2102605133","https://openalex.org/W2106624428","https://openalex.org/W2109235804","https://openalex.org/W2137881638","https://openalex.org/W2155893237","https://openalex.org/W2186094539","https://openalex.org/W2194775991","https://openalex.org/W2296478878","https://openalex.org/W2412782625","https://openalex.org/W2444163375","https://openalex.org/W2560023338","https://openalex.org/W2570343428","https://openalex.org/W2587989515","https://openalex.org/W2593617942","https://openalex.org/W2604455318","https://openalex.org/W2604627275","https://openalex.org/W2774839435","https://openalex.org/W2950094539","https://openalex.org/W2962835968","https://openalex.org/W2963277399","https://openalex.org/W3099112683","https://openalex.org/W3106250896","https://openalex.org/W6605121731","https://openalex.org/W6633727509","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6639633739","https://openalex.org/W6666899075","https://openalex.org/W6680357304","https://openalex.org/W6733387591","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W2165912799","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4243305035"],"abstract_inverted_index":{"While":[0],"there":[1],"has":[2],"been":[3],"significant":[4,130],"progress":[5],"in":[6,139],"solving":[7],"the":[8,46,52,57,77,87,92,102,113,125,133,137,143,147],"problems":[9,33],"of":[10,45,76,104,136],"image":[11],"pixel":[12,74],"labeling,":[13],"object":[14,152],"detection":[15,153],"and":[16,89,154],"scene":[17,47,148,155],"classification,":[18],"existing":[19],"approaches":[20],"normally":[21],"address":[22],"them":[23],"separately.":[24],"In":[25],"this":[26,140],"paper,":[27],"we":[28,39],"propose":[29],"to":[30,65,70,85,90],"tackle":[31],"these":[32],"from":[34],"a":[35,42,72,108,121,129],"bottom-up":[36],"perspective,":[37],"where":[38],"simply":[40],"need":[41],"semantic":[43,80,150],"segmentation":[44,81],"as":[48],"input.":[49],"We":[50,100],"employ":[51],"DeepLab":[53],"architecture,":[54],"based":[55],"on":[56,112],"ResNet":[58],"deep":[59],"network,":[60],"which":[61],"leverages":[62],"multi-scale":[63],"inputs":[64],"later":[66],"fuse":[67],"their":[68],"responses":[69],"perform":[71],"precise":[73],"labeling":[75],"scene.":[78],"This":[79],"mask":[82],"is":[83],"used":[84],"localize":[86],"objects":[88],"recognize":[91],"scene,":[93],"following":[94],"two":[95],"simple":[96],"yet":[97],"effective":[98],"strategies.":[99],"evaluate":[101],"benefits":[103],"our":[105],"solutions,":[106],"performing":[107],"thorough":[109],"experimental":[110],"evaluation":[111],"NYU":[114],"Depth":[115],"V2":[116],"dataset.":[117],"Our":[118],"approach":[119],"achieves":[120],"performance":[122],"that":[123],"beats":[124],"leading":[126],"results":[127],"by":[128],"margin,":[131],"defining":[132],"new":[134],"state":[135],"art":[138],"benchmark":[141],"for":[142],"three":[144],"tasks":[145],"comprising":[146],"understanding:":[149],"segmentation,":[151],"categorization.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}