{"id":"https://openalex.org/W3119206490","doi":"https://doi.org/10.1109/iros45743.2020.9341186","title":"RobotVQA \u2014 A Scene-Graph- and Deep-Learning-based Visual Question Answering System for Robot Manipulation","display_name":"RobotVQA \u2014 A Scene-Graph- and Deep-Learning-based Visual Question Answering System for Robot Manipulation","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3119206490","doi":"https://doi.org/10.1109/iros45743.2020.9341186","mag":"3119206490"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/A5089314280","display_name":"Franklin Kenghagho Kenfack","orcid":null},"institutions":[{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Franklin Kenghagho Kenfack","raw_affiliation_strings":["Institute for Artificial Intelligence (IAI), University of Bremen"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence (IAI), University of Bremen","institution_ids":["https://openalex.org/I180437899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029570887","display_name":"F.A. Siddiky","orcid":null},"institutions":[{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Feroz Ahmed Siddiky","raw_affiliation_strings":["Institute for Artificial Intelligence (IAI), University of Bremen"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence (IAI), University of Bremen","institution_ids":["https://openalex.org/I180437899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072276653","display_name":"Ferenc B\u00e1lint-Bencz\u00e9di","orcid":null},"institutions":[{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ferenc Balint-Benczedi","raw_affiliation_strings":["Institute for Artificial Intelligence (IAI), University of Bremen"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence (IAI), University of Bremen","institution_ids":["https://openalex.org/I180437899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003274224","display_name":"Michael Beetz","orcid":"https://orcid.org/0000-0002-7888-7444"},"institutions":[{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Beetz","raw_affiliation_strings":["Institute for Artificial Intelligence (IAI), University of Bremen"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence (IAI), University of Bremen","institution_ids":["https://openalex.org/I180437899"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089314280"],"corresponding_institution_ids":["https://openalex.org/I180437899"],"apc_list":null,"apc_paid":null,"fwci":1.1724,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.81762116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9667","last_page":"9674"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning 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/T11714","display_name":"Multimodal Machine Learning 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":0.9998999834060669,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9984999895095825,"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":0.7533283233642578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7368494868278503},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7178155779838562},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.5554674863815308},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5475028157234192},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.48664984107017517},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.45466700196266174},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34482598304748535},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.16446375846862793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7533283233642578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7368494868278503},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7178155779838562},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.5554674863815308},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5475028157234192},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.48664984107017517},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.45466700196266174},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34482598304748535},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.16446375846862793},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros45743.2020.9341186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1263488365","https://openalex.org/W1499297823","https://openalex.org/W1548115571","https://openalex.org/W1983927101","https://openalex.org/W2579549467","https://openalex.org/W2794284562","https://openalex.org/W2911005728","https://openalex.org/W2963150697","https://openalex.org/W2963184176","https://openalex.org/W2963907629","https://openalex.org/W6738893770"],"related_works":["https://openalex.org/W2628861693","https://openalex.org/W8302103","https://openalex.org/W3203087560","https://openalex.org/W4361279463","https://openalex.org/W3171631314","https://openalex.org/W2674584172","https://openalex.org/W2967743314","https://openalex.org/W2606825221","https://openalex.org/W2184085865","https://openalex.org/W2064245428"],"abstract_inverted_index":{"Visual":[0,97],"robot":[1,8,45,55,67,121,199],"perception":[2,18,46,204],"has":[3],"been":[4],"challenging":[5],"to":[6,21,31,51,54,66,108,114,163],"successful":[7],"manipulation":[9,70],"in":[10,43,131,135,139,168,187],"noisy,":[11],"cluttered":[12],"and":[13,36,87,110,148,183],"dynamic":[14],"environments.":[15],"While":[16],"some":[17,44],"systems":[19,47,201],"fail":[20,30],"provide":[22],"an":[23,64],"adequate":[24],"semantics":[25],"of":[26,84,105,141,177],"the":[27,74,103,154,178],"scene,":[28],"others":[29],"present":[32],"appropriate":[33],"learning":[34,107],"models":[35],"training":[37,85,184],"data.":[38],"Another":[39],"major":[40],"issue":[41],"encountered":[42],"is":[48,60,196],"their":[49],"inability":[50],"promptly":[52],"respond":[53],"control":[56,200],"programs":[57],"whose":[58],"realtimeness":[59],"crucial.This":[61],"paper":[62,170],"proposes":[63],"architecture":[65,80,101],"vision":[68],"for":[69,95,198],"tasks":[71],"that":[72,202],"addresses":[73],"three":[75],"issues":[76],"mentioned":[77],"above.":[78],"The":[79,100],"encompasses":[81],"a":[82,88,120,165,188,206],"generator":[83],"datasets":[86],"learnable":[89],"scene":[90,166,172],"describer,":[91],"coined":[92],"as":[93,118,171,205],"RobotVQA":[94,116,152,195],"Robot":[96],"Question":[98],"Answering.":[99],"leverages":[102],"power":[104],"deep":[106],"predict":[109],"photo-realistic":[111],"virtual":[112],"worlds":[113],"train.":[115],"takes":[117],"input":[119],"scene's":[122],"RGB":[123],"or":[124,174],"RGBD":[125],"image,":[126],"detects":[127],"all":[128],"relevant":[129],"objects":[130],"it,":[132],"then":[133],"describes":[134],"realtime":[136],"each":[137],"object":[138],"terms":[140],"category,":[142],"color,":[143],"material,":[144],"shape,":[145],"openability,":[146],"6D-pose":[147],"segmentation":[149],"mask.":[150],"Moreover,":[151],"computes":[153],"qualitative":[155],"spatial":[156],"relations":[157],"among":[158],"those":[159],"objects.":[160],"We":[161],"refer":[162],"such":[164],"description":[167],"this":[169],"graph":[173,176],"semantic":[175],"scene.":[179],"In":[180],"RobotVQA,":[181],"prediction":[182],"take":[185],"place":[186],"unified":[189],"manner.":[190],"Finally,":[191],"we":[192],"demonstrate":[193],"how":[194],"suitable":[197],"interpret":[203],"question":[207],"answering":[208],"process.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}