{"id":"https://openalex.org/W2175462310","doi":"https://doi.org/10.1109/iros.2011.6094596","title":"Enhanced visual scene understanding through human-robot dialog","display_name":"Enhanced visual scene understanding through human-robot dialog","publication_year":2011,"publication_date":"2011-09-01","ids":{"openalex":"https://openalex.org/W2175462310","doi":"https://doi.org/10.1109/iros.2011.6094596","mag":"2175462310"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2011.6094596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2011.6094596","pdf_url":null,"source":{"id":"https://openalex.org/S4363608614","display_name":"2011 IEEE/RSJ International Conference on Intelligent Robots and Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE/RSJ International Conference on Intelligent Robots and Systems","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/A5089990642","display_name":"Matthew Johnson\u2010Roberson","orcid":"https://orcid.org/0000-0002-0506-907X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Matthew Johnson-Roberson","raw_affiliation_strings":["Centre of Autonomous Systems, Computational Vision and Active Perception Laboratory, Sweden"],"affiliations":[{"raw_affiliation_string":"Centre of Autonomous Systems, Computational Vision and Active Perception Laboratory, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021676288","display_name":"Jeannette Bohg","orcid":"https://orcid.org/0000-0002-4921-7193"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeannette Bohg","raw_affiliation_strings":["Centre of Autonomous Systems, Computational Vision and Active Perception Laboratory, Sweden"],"affiliations":[{"raw_affiliation_string":"Centre of Autonomous Systems, Computational Vision and Active Perception Laboratory, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091225228","display_name":"Gabriel Skantze","orcid":"https://orcid.org/0000-0002-8579-1790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabriel Skantze","raw_affiliation_strings":["Department for Speech Music and Hearing, Institutes part of School of Computer Science, KTH in Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Department for Speech Music and Hearing, Institutes part of School of Computer Science, KTH in Stockholm, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015417808","display_name":"Joakim Gustafson","orcid":"https://orcid.org/0000-0002-0397-6442"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joakim Gustafson","raw_affiliation_strings":["Department for Speech Music and Hearing, Institutes part of School of Computer Science, KTH in Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Department for Speech Music and Hearing, Institutes part of School of Computer Science, KTH in Stockholm, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111374272","display_name":"Rolf Carlson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rolf Carlson","raw_affiliation_strings":["Department for Speech Music and Hearing, Institutes part of School of Computer Science, KTH in Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Department for Speech Music and Hearing, Institutes part of School of Computer Science, KTH in Stockholm, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042945642","display_name":"Babak Rasolzadeh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Babak Rasolzadeh","raw_affiliation_strings":["Centre of Autonomous Systems, Computational Vision and Active Perception Laboratory, Sweden"],"affiliations":[{"raw_affiliation_string":"Centre of Autonomous Systems, Computational Vision and Active Perception Laboratory, Sweden","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023792180","display_name":"Danica Kragi\u0107","orcid":"https://orcid.org/0000-0003-2965-2953"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danica Kragic","raw_affiliation_strings":["Centre of Autonomous Systems, Computational Vision and Active Perception Laboratory, Sweden"],"affiliations":[{"raw_affiliation_string":"Centre of Autonomous Systems, Computational Vision and Active Perception Laboratory, Sweden","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5089990642"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6746,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.94075305,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3342","last_page":"3348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9998000264167786,"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/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":0.7940345406532288},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7293524742126465},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.7291082143783569},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6798839569091797},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.621043860912323},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5417935848236084},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5032286047935486},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41021788120269775},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.371574342250824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940345406532288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7293524742126465},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7291082143783569},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6798839569091797},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.621043860912323},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5417935848236084},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5032286047935486},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41021788120269775},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.371574342250824},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2011.6094596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2011.6094596","pdf_url":null,"source":{"id":"https://openalex.org/S4363608614","display_name":"2011 IEEE/RSJ International Conference on Intelligent Robots and Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1500409521","https://openalex.org/W1523135049","https://openalex.org/W1532070457","https://openalex.org/W1973933596","https://openalex.org/W1991296666","https://openalex.org/W2002529375","https://openalex.org/W2018994343","https://openalex.org/W2027248184","https://openalex.org/W2041376653","https://openalex.org/W2089630413","https://openalex.org/W2096139825","https://openalex.org/W2101205555","https://openalex.org/W2101309634","https://openalex.org/W2103088500","https://openalex.org/W2106624428","https://openalex.org/W2107019937","https://openalex.org/W2113137767","https://openalex.org/W2124351162","https://openalex.org/W2127514693","https://openalex.org/W2140435402","https://openalex.org/W2143516773","https://openalex.org/W2149173366","https://openalex.org/W2153667689","https://openalex.org/W2153738822","https://openalex.org/W2156206505","https://openalex.org/W2156222070","https://openalex.org/W2165603175","https://openalex.org/W2165830610","https://openalex.org/W3120421331","https://openalex.org/W4234235766","https://openalex.org/W4244914727","https://openalex.org/W6629818233","https://openalex.org/W6680382358","https://openalex.org/W6682287954","https://openalex.org/W6827083027"],"related_works":["https://openalex.org/W2098987383","https://openalex.org/W2417260800","https://openalex.org/W1596203174","https://openalex.org/W2117933979","https://openalex.org/W2283130723","https://openalex.org/W103938586","https://openalex.org/W2104718772","https://openalex.org/W4233992201","https://openalex.org/W2292950558","https://openalex.org/W337810568"],"abstract_inverted_index":{"We":[0,90,128],"propose":[1],"a":[2,61,67],"novel":[3],"human-robot-interaction":[4],"framework":[5],"for":[6,108],"robust":[7],"visual":[8],"scene":[9,34,120],"understanding.":[10],"Without":[11],"any":[12],"a-priori":[13],"knowledge":[14,86],"about":[15,87],"the":[16,18,21,33,39,70,75,83,96,100,106,112,116,119],"objects,":[17],"task":[19],"of":[20,29,46,78],"robot":[22,84,97],"is":[23,58],"to":[24,98,142],"correctly":[25],"enumerate":[26],"how":[27],"many":[28],"them":[30,37],"are":[31],"in":[32,69],"and":[35,104,125],"segment":[36],"from":[38,115],"background.":[40],"Our":[41],"approach":[42],"builds":[43],"on":[44,111,132],"top":[45],"state-of-the-art":[47],"computer":[48],"vision":[49],"methods,":[50],"generating":[51],"object":[52,102],"hypotheses":[53,103],"through":[54],"segmentation.":[55],"This":[56],"process":[57],"combined":[59],"with":[60],"natural":[62,76],"dialog":[63,81],"system,":[64,82],"thus":[65],"including":[66],"`human":[68],"loop'":[71],"where,":[72],"by":[73],"exploiting":[74],"conversation":[77],"an":[79,92,137],"advanced":[80],"gains":[85],"ambiguous":[88],"situations.":[89],"present":[91,129],"entropy-based":[93],"system":[94],"allowing":[95],"detect":[99],"poorest":[101],"query":[105],"user":[107],"arbitration.":[109],"Based":[110],"information":[113],"obtained":[114],"human-robot":[117],"dialog,":[118],"segmentation":[121,139,143],"can":[122],"be":[123],"re-seeded":[124],"thereby":[126],"improved.":[127],"experimental":[130],"results":[131],"real":[133],"data":[134],"that":[135],"show":[136],"improved":[138],"performance":[140],"compared":[141],"without":[144],"interaction.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}