{"id":"https://openalex.org/W3133424709","doi":"https://doi.org/10.1109/iros45743.2020.9340905","title":"Understanding Contexts Inside Robot and Human Manipulation Tasks through Vision-Language Model and Ontology System in Video Streams","display_name":"Understanding Contexts Inside Robot and Human Manipulation Tasks through Vision-Language Model and Ontology System in Video Streams","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3133424709","doi":"https://doi.org/10.1109/iros45743.2020.9340905","mag":"3133424709"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9340905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9340905","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":"conference-paper","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/A5100612957","display_name":"Chen Jiang","orcid":"https://orcid.org/0009-0003-7616-8926"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chen Jiang","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006157212","display_name":"Masood Dehghan","orcid":"https://orcid.org/0000-0003-2293-6101"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Masood Dehghan","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030948380","display_name":"Martin J\u00e4gersand","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Martin Jagersand","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.2563,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.60289227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8366","last_page":"8372"},"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/T10812","display_name":"Human Pose and Action Recognition","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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7800740003585815},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.7237541675567627},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.689988374710083},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.661129355430603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5816050171852112},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5700476169586182},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5237424373626709},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5003652572631836},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.42230337858200073},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3506975769996643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7800740003585815},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.7237541675567627},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.689988374710083},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.661129355430603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5816050171852112},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5700476169586182},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5237424373626709},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5003652572631836},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.42230337858200073},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3506975769996643},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros45743.2020.9340905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9340905","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1613163714","https://openalex.org/W1889081078","https://openalex.org/W2079252443","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2139501017","https://openalex.org/W2184048809","https://openalex.org/W2261812172","https://openalex.org/W2563296158","https://openalex.org/W2749087070","https://openalex.org/W2776212699","https://openalex.org/W2783894900","https://openalex.org/W2796136333","https://openalex.org/W2885914489","https://openalex.org/W2895299763","https://openalex.org/W2902709482","https://openalex.org/W2916811071","https://openalex.org/W2924113821","https://openalex.org/W2950019618","https://openalex.org/W2962716343","https://openalex.org/W2963244312","https://openalex.org/W2963245631","https://openalex.org/W2963860638","https://openalex.org/W2964242760","https://openalex.org/W2964308564","https://openalex.org/W2965310593","https://openalex.org/W2967180672","https://openalex.org/W2967199722","https://openalex.org/W2967857025","https://openalex.org/W2967901646","https://openalex.org/W2973266032","https://openalex.org/W2990161439","https://openalex.org/W2996856264","https://openalex.org/W3004164135","https://openalex.org/W3004280398","https://openalex.org/W3004383953","https://openalex.org/W3100516791","https://openalex.org/W4289740432","https://openalex.org/W6630875275","https://openalex.org/W6639432524","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6686628513","https://openalex.org/W6745096383","https://openalex.org/W6749916090","https://openalex.org/W6753924131","https://openalex.org/W6755626774","https://openalex.org/W6756688856","https://openalex.org/W6759801421","https://openalex.org/W6760721115","https://openalex.org/W6770619867","https://openalex.org/W6785737802"],"related_works":["https://openalex.org/W2003333417","https://openalex.org/W1975289146","https://openalex.org/W2378862226","https://openalex.org/W118236634","https://openalex.org/W2355326633","https://openalex.org/W2804669904","https://openalex.org/W2149777447","https://openalex.org/W2347456287","https://openalex.org/W2122871747","https://openalex.org/W3114279067"],"abstract_inverted_index":{"Manipulation":[0],"tasks":[1],"in":[2,86,178],"daily":[3],"life,":[4],"such":[5],"as":[6],"pouring":[7],"water,":[8],"unfold":[9],"through":[10],"human":[11,73],"intentions.":[12],"Being":[13],"able":[14],"to":[15,41,51,95,158,169],"process":[16],"contextual":[17],"knowledge":[18,67,105],"from":[19],"these":[20],"Activities":[21],"of":[22,56,99,141],"Daily":[23],"Living":[24],"(ADLs)":[25],"over":[26],"time":[27],"can":[28,136],"help":[29],"us":[30],"understand":[31],"manipulation":[32,46,76,145],"intentions,":[33],"which":[34],"are":[35,80],"essential":[36],"for":[37,69,147,174],"an":[38,83,103,120,142],"intelligent":[39],"robot":[40,71,157,176],"transition":[42],"smoothly":[43],"between":[44],"various":[45],"actions.":[47],"In":[48],"this":[49,171],"paper,":[50],"model":[52,123],"the":[53,125,133,139,156],"intended":[54,143],"concepts":[55,77],"manipulation,":[57],"we":[58,91],"present":[59],"a":[60,64,87,93,97],"vision":[61],"dataset":[62],"under":[63],"strictly":[65],"constrained":[66],"domain":[68],"both":[70,148],"and":[72,78,102,118,150],"manipulations,":[74],"where":[75],"relations":[79],"stored":[81],"by":[82,163],"ontology":[84,126],"system":[85],"taxonomic":[88],"manner.":[89],"Furthermore,":[90],"propose":[92],"scheme":[94,112,135,154,172],"generate":[96],"combination":[98],"visual":[100],"attentions":[101],"evolving":[104],"graph":[106],"filled":[107],"with":[108,114,124],"commonsense":[109],"knowledge.":[110],"Our":[111],"works":[113],"real-world":[115,175],"camera":[116],"streams":[117],"fuses":[119],"attention-based":[121],"Vision-Language":[122],"system.":[127],"The":[128,152],"experimental":[129],"results":[130],"demonstrate":[131],"that":[132],"proposed":[134,153],"successfully":[137],"represent":[138],"evolution":[140],"object":[144],"procedure":[146],"robots":[149],"humans.":[151],"allows":[155],"mimic":[159],"human-like":[160],"intentional":[161],"behaviors":[162],"watching":[164],"real-time":[165],"videos.":[166],"We":[167],"aim":[168],"develop":[170],"further":[173],"intelligence":[177],"Human-Robot":[179],"Interaction.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}