{"id":"https://openalex.org/W4401018288","doi":"https://doi.org/10.1109/ur61395.2024.10597493","title":"Action2Code: Transforming Video Demonstrations into Sequential Robotic Instructions","display_name":"Action2Code: Transforming Video Demonstrations into Sequential Robotic Instructions","publication_year":2024,"publication_date":"2024-06-24","ids":{"openalex":"https://openalex.org/W4401018288","doi":"https://doi.org/10.1109/ur61395.2024.10597493"},"language":"en","primary_location":{"id":"doi:10.1109/ur61395.2024.10597493","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ur61395.2024.10597493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 21st International Conference on Ubiquitous Robots (UR)","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/A5101882843","display_name":"Abhinav Upadhyay","orcid":"https://orcid.org/0000-0001-8201-5959"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Abhinav Upadhyay","raw_affiliation_strings":["Accenture Labs,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Accenture Labs,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006577584","display_name":"Gautam Reddy","orcid":null},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gautam Reddy","raw_affiliation_strings":["Indraprastha Institute of Information Technology Delhi,Department of Computer Science,New Delhi,India"],"affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology Delhi,Department of Computer Science,New Delhi,India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016780429","display_name":"Alpana Dubey","orcid":"https://orcid.org/0000-0001-8217-8707"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alpana Dubey","raw_affiliation_strings":["Accenture Labs,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Accenture Labs,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040421942","display_name":"Shubham Saurav","orcid":"https://orcid.org/0009-0006-2003-0014"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shubham Saurav","raw_affiliation_strings":["Accenture Labs,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Accenture Labs,Bangalore,India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100748443","display_name":"Shubhashis Sengupta","orcid":"https://orcid.org/0009-0003-8298-0216"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shubhashis Sengupta","raw_affiliation_strings":["Accenture Labs,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Accenture Labs,Bangalore,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101882843"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09480593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"92","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9894999861717224,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9894999861717224,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.98580002784729,"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":0.96670001745224,"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":0.7261831164360046},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4108657240867615},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3979007303714752},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3876717686653137},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3680533766746521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3314966857433319}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261831164360046},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4108657240867615},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3979007303714752},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3876717686653137},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3680533766746521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3314966857433319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ur61395.2024.10597493","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ur61395.2024.10597493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 21st International Conference on Ubiquitous Robots (UR)","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":35,"referenced_works":["https://openalex.org/W2990152177","https://openalex.org/W3089307846","https://openalex.org/W3098605233","https://openalex.org/W3120335880","https://openalex.org/W3126721948","https://openalex.org/W3198685994","https://openalex.org/W4214612132","https://openalex.org/W4224912544","https://openalex.org/W4226485558","https://openalex.org/W4283211057","https://openalex.org/W4312560592","https://openalex.org/W4312971267","https://openalex.org/W4322616306","https://openalex.org/W4322718191","https://openalex.org/W4383097638","https://openalex.org/W4383108296","https://openalex.org/W4383108457","https://openalex.org/W4383109144","https://openalex.org/W4385562549","https://openalex.org/W4387802732","https://openalex.org/W4389519352","https://openalex.org/W4389524484","https://openalex.org/W4390722831","https://openalex.org/W4394828156","https://openalex.org/W4401415042","https://openalex.org/W4401905821","https://openalex.org/W6783958930","https://openalex.org/W6810874553","https://openalex.org/W6838959477","https://openalex.org/W6839459284","https://openalex.org/W6843759960","https://openalex.org/W6850343319","https://openalex.org/W6850625674","https://openalex.org/W6854555012","https://openalex.org/W6857758392"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"The":[0],"time-consuming":[1],"nature":[2],"of":[3,134,142,156],"programming":[4],"robotic":[5,66,106],"motion":[6],"and":[7,49,102,117,136,144,148],"manipulation":[8],"to":[9,23,31,42,46,55,79,87,105,125],"achieve":[10],"specific":[11,34],"tasks":[12,25],"is":[13],"a":[14,76,92,131,140],"key":[15],"reason":[16],"that":[17,95],"robots":[18,81],"have":[19],"generally":[20],"been":[21],"restricted":[22],"repetitive":[24],"with":[26,139],"little":[27],"variation.":[28],"Developers":[29],"need":[30],"manually":[32],"write":[33],"code":[35,45,63,127,161],"for":[36,64,146],"each":[37],"task,":[38],"making":[39],"it":[40,104],"challenging":[41],"adapt":[43],"the":[44,88,154,157],"different":[47],"environments":[48],"assembly":[50],"scenarios.":[51],"This":[52],"inefficiency":[53],"leads":[54],"significant":[56],"time":[57],"being":[58],"spent":[59],"on":[60,112],"creating":[61],"redundant":[62],"similar":[65],"actions":[67],"in":[68,159],"various":[69],"assemblies.":[70],"To":[71],"address":[72],"this,":[73],"we":[74],"develop":[75],"generative":[77],"network":[78],"program":[80],"through":[82],"demonstration,":[83],"bringing":[84],"more":[85],"agility":[86],"process.":[89],"We":[90,108,129],"propose":[91],"network,":[93],"Action2Code,":[94],"takes":[96],"video":[97,163],"demonstration":[98],"as":[99],"an":[100],"input":[101],"translates":[103],"instructions.":[107],"evaluate":[109],"our":[110],"approach":[111],"two":[113],"datasets,":[114],"namely":[115],"RH20T":[116,147],"ASMCode,":[118,149],"using":[119],"quantitative":[120],"analysis":[121],"across":[122],"four":[123],"metrics":[124],"assess":[126],"generation.":[128],"observe":[130],"CodeBLEU":[132],"score":[133],"0.69":[135],"0.65,":[137],"along":[138],"CodeBERTScore":[141],"0.78":[143],"0.73":[145],"respectively.":[150],"Our":[151],"results":[152],"demonstrate":[153],"effectiveness":[155],"model":[158],"generating":[160],"from":[162],"demonstrations.":[164]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}