{"id":"https://openalex.org/W2938245606","doi":"https://doi.org/10.1109/iros40897.2019.8968510","title":"Learning to Generate Unambiguous Spatial Referring Expressions for Real-World Environments","display_name":"Learning to Generate Unambiguous Spatial Referring Expressions for Real-World Environments","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2938245606","doi":"https://doi.org/10.1109/iros40897.2019.8968510","mag":"2938245606"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8968510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.07165","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Fethiye Irmak Do\u011fan","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Fethiye Irmak Do\u011fan","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning from the School of Electrical Engineering and Computer Science,Stockholm,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning from the School of Electrical Engineering and Computer Science,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sinan Kalkan","orcid":null},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Sinan Kalkan","raw_affiliation_strings":["Middle East Technical University,KOVAN Research Lab,Ankara,Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Middle East Technical University,KOVAN Research Lab,Ankara,Turkey","institution_ids":["https://openalex.org/I201799495"]}]},{"author_position":"last","author":{"id":null,"display_name":"Iolanda Leite","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Iolanda Leite","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning from the School of Electrical Engineering and Computer Science,Stockholm,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning from the School of Electrical Engineering and Computer Science,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.915,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.82813321,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4992","last_page":"4999"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9983000159263611,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9932000041007996,"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/object","display_name":"Object (grammar)","score":0.6567999720573425},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4251999855041504},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4097999930381775},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.38839998841285706},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.3781000077724457},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.3723999857902527},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.33970001339912415},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.33399999141693115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7103000283241272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6797999739646912},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6567999720573425},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4251999855041504},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3630000054836273},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2533000111579895}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iros40897.2019.8968510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.07165","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.07165","pdf_url":"https://arxiv.org/pdf/1904.07165","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:open.metu.edu.tr:11511/49001","is_oa":false,"landing_page_url":"https://hdl.handle.net/11511/49001","pdf_url":null,"source":{"id":"https://openalex.org/S4306402495","display_name":"OpenMETU (Middle East Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I201799495","host_organization_name":"Middle East Technical University","host_organization_lineage":["https://openalex.org/I201799495"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.07165","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.07165","pdf_url":"https://arxiv.org/pdf/1904.07165","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1923184257","https://openalex.org/W2006354339","https://openalex.org/W2017814585","https://openalex.org/W2024271606","https://openalex.org/W2040145958","https://openalex.org/W2107537133","https://openalex.org/W2142315290","https://openalex.org/W2165504147","https://openalex.org/W2226467950","https://openalex.org/W2277195237","https://openalex.org/W2557728737","https://openalex.org/W2785990151","https://openalex.org/W2788810331","https://openalex.org/W2951281980","https://openalex.org/W2962716343","https://openalex.org/W2963109634","https://openalex.org/W2963244312","https://openalex.org/W2963640828","https://openalex.org/W6604707697","https://openalex.org/W6638035631","https://openalex.org/W6678621652","https://openalex.org/W6731766730","https://openalex.org/W6741457941","https://openalex.org/W6756945690"],"related_works":[],"abstract_inverted_index":{"Referring":[0],"to":[1,35,55,70,101,110],"objects":[2,86],"in":[3,77],"a":[4,43,63],"natural":[5],"and":[6,60,107],"unambiguous":[7],"manner":[8],"is":[9,31],"crucial":[10],"for":[11,51],"effective":[12],"human-robot":[13],"interaction.":[14],"Previous":[15],"research":[16],"on":[17,24,48],"learning-based":[18],"referring":[19,29,64,96],"expressions":[20,30,97],"has":[21],"focused":[22],"primarily":[23],"comprehension":[25],"tasks,":[26],"while":[27],"generating":[28],"still":[32],"mostly":[33],"limited":[34],"rule-based":[36],"methods.":[37],"In":[38],"this":[39],"work,":[40],"we":[41],"propose":[42],"two-stage":[44],"approach":[45],"that":[46,82,92,98],"relies":[47],"deep":[49],"learning":[50],"estimating":[52],"spatial":[53],"relations":[54],"describe":[56],"an":[57],"object":[58],"naturally":[59],"unambiguously":[61],"with":[62,87],"expression.":[65],"We":[66,90],"compare":[67],"our":[68,93],"method":[69,94],"the":[71,74],"state":[72],"of":[73],"art":[75],"algorithm":[76],"ambiguous":[78],"environments":[79,81],"(e.g.,":[80],"include":[83],"very":[84],"similar":[85,88],"relationships).":[89],"show":[91],"generates":[95],"people":[99],"find":[100],"be":[102],"more":[103,113],"accurate":[104],"(~30%":[105],"better)":[106],"would":[108],"prefer":[109],"use":[111],"(~32%":[112],"often).":[114]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2019-04-25T00:00:00"}