{"id":"https://openalex.org/W3004164135","doi":"https://doi.org/10.1109/iros40897.2019.8967621","title":"An Object Attribute Guided Framework for Robot Learning Manipulations from Human Demonstration Videos","display_name":"An Object Attribute Guided Framework for Robot Learning Manipulations from Human Demonstration Videos","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3004164135","doi":"https://doi.org/10.1109/iros40897.2019.8967621","mag":"3004164135"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8967621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967621","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":"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/A5100763740","display_name":"Qixiang Zhang","orcid":"https://orcid.org/0000-0001-8537-8974"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qixiang Zhang","raw_affiliation_strings":["Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006","Cobot Vision Lab at the School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]},{"raw_affiliation_string":"Cobot Vision Lab at the School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749483","display_name":"Junhong Chen","orcid":"https://orcid.org/0000-0002-8313-8317"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhong Chen","raw_affiliation_strings":["Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006","Cobot Vision Lab at the School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]},{"raw_affiliation_string":"Cobot Vision Lab at the School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063912447","display_name":"Dayong Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dayong Liang","raw_affiliation_strings":["Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006","Cobot Vision Lab at the School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]},{"raw_affiliation_string":"Cobot Vision Lab at the School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041101317","display_name":"Huaping Liu","orcid":"https://orcid.org/0000-0002-4042-6044"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaping Liu","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110675449","display_name":"Xiaojing Zhou","orcid":"https://orcid.org/0000-0002-6412-2133"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojing Zhou","raw_affiliation_strings":["Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006","Cobot Vision Lab at the School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]},{"raw_affiliation_string":"Cobot Vision Lab at the School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033991278","display_name":"Zihan Ye","orcid":"https://orcid.org/0000-0001-6462-6799"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Ye","raw_affiliation_strings":["Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006","Cobot Vision Lab at the School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]},{"raw_affiliation_string":"Cobot Vision Lab at the School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073720799","display_name":"Wenyin Liu","orcid":"https://orcid.org/0000-0002-6237-6607"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyin Liu","raw_affiliation_strings":["Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006","Cobot Vision Lab at the School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,Cobot Vision Lab at the School of Computer Science and Technology,Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]},{"raw_affiliation_string":"Cobot Vision Lab at the School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100763740"],"corresponding_institution_ids":["https://openalex.org/I139024713"],"apc_list":null,"apc_paid":null,"fwci":0.2024,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56488403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6113","last_page":"6119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10653","display_name":"Robot Manipulation and Learning","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.8577593564987183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7134996652603149},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6864067912101746},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6653774380683899},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.645050048828125},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.5293322801589966},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4964461922645569},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4754233658313751},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.44401779770851135},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3840872347354889},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.32491132616996765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8577593564987183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7134996652603149},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6864067912101746},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6653774380683899},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.645050048828125},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.5293322801589966},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4964461922645569},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4754233658313751},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.44401779770851135},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3840872347354889},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32491132616996765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros40897.2019.8967621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967621","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1613163714","https://openalex.org/W1836465849","https://openalex.org/W1861492603","https://openalex.org/W1986014385","https://openalex.org/W2016053056","https://openalex.org/W2045225768","https://openalex.org/W2081034428","https://openalex.org/W2112913186","https://openalex.org/W2132076832","https://openalex.org/W2156798932","https://openalex.org/W2235034809","https://openalex.org/W2295598076","https://openalex.org/W2309561466","https://openalex.org/W2342662179","https://openalex.org/W2462996230","https://openalex.org/W2526639894","https://openalex.org/W2558383949","https://openalex.org/W2566057350","https://openalex.org/W2605973302","https://openalex.org/W2606212668","https://openalex.org/W2736334449","https://openalex.org/W2746726611","https://openalex.org/W2755546070","https://openalex.org/W2775357942","https://openalex.org/W2776217220","https://openalex.org/W2788945907","https://openalex.org/W2799002257","https://openalex.org/W2898525034","https://openalex.org/W2902905147","https://openalex.org/W2950568498","https://openalex.org/W2962871243","https://openalex.org/W2963150697","https://openalex.org/W2963703448","https://openalex.org/W2963854515","https://openalex.org/W2963860638","https://openalex.org/W2964094092","https://openalex.org/W6638667902","https://openalex.org/W6639102338","https://openalex.org/W6679681992","https://openalex.org/W6744181227","https://openalex.org/W6748516343","https://openalex.org/W6748831540","https://openalex.org/W6755748847"],"related_works":["https://openalex.org/W2975200075","https://openalex.org/W2979649235","https://openalex.org/W2007544051","https://openalex.org/W2540925674","https://openalex.org/W2392565008","https://openalex.org/W1837097281","https://openalex.org/W1966410754","https://openalex.org/W2363840281","https://openalex.org/W2061090284","https://openalex.org/W1561942766"],"abstract_inverted_index":{"Learning":[0],"manipulations":[1],"from":[2,145,167],"videos":[3,31,111,133,147],"is":[4,106,139],"an":[5],"inspiriting":[6],"way":[7],"for":[8,117],"robots":[9],"to":[10,82,95,108,141,162],"acquire":[11],"new":[12],"skills.":[13],"In":[14,99],"this":[15],"paper,":[16],"we":[17,153],"propose":[18],"a":[19,44,49,72,103,125,158],"framework":[20,42,156],"that":[21,136],"can":[22],"generate":[23,113],"robotic":[24],"manipulation":[25,143,165],"plans":[26,144],"by":[27,70],"observing":[28],"human":[29],"demonstration":[30,146,168],"without":[32],"special":[33],"marks":[34],"or":[35],"unnatural":[36],"demonstrated":[37],"behaviors.":[38],"More":[39],"specifically,":[40],"the":[41,57,67,85,96,100,110,114,164,173],"contains":[43],"video":[45,128],"parsing":[46],"module":[47,55],"and":[48,65,90,112,134],"robot":[50,118,160],"execution":[51],"module.":[52],"The":[53],"first":[54],"recognizes":[56],"demonstrator's":[58,97],"actions":[59],"using":[60],"two-stream":[61],"convolution":[62],"neural":[63],"networks,":[64],"classifies":[66],"operated":[68],"objects":[69,86],"adopting":[71],"Mask":[73],"R-CNN.":[74],"After":[75],"that,":[76],"two":[77],"XGBoost":[78],"classifiers":[79],"are":[80,122],"applied":[81],"further":[83],"classify":[84],"into":[87],"subject":[88],"object":[89,92],"patient":[91],"respectively,":[93],"according":[94],"actions.":[98],"second":[101],"module,":[102],"grammar-based":[104],"parser":[105],"used":[107],"summarize":[109],"common":[115],"instructions":[116],"execution.":[119],"Extensive":[120],"experiments":[121],"conducted":[123],"on":[124],"publicly":[126],"available":[127],"datasets":[129],"consisting":[130],"of":[131,175],"273":[132],"manifest":[135],"our":[137,155,176],"approach":[138],"able":[140],"learn":[142],"with":[148,157],"high":[149],"accuracy":[150],"(73.36%).":[151],"Furthermore,":[152],"integrate":[154],"humanoid":[159],"Baxter":[161],"perform":[163],"learning":[166],"videos,":[169],"which":[170],"effectively":[171],"verifies":[172],"performance":[174],"framework.":[177]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}