{"id":"https://openalex.org/W4390548185","doi":"https://doi.org/10.1145/3632410.3632482","title":"Act2Code: Generating Sequential Robotic Instructions from Video Demonstration","display_name":"Act2Code: Generating Sequential Robotic Instructions from Video Demonstration","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4390548185","doi":"https://doi.org/10.1145/3632410.3632482"},"language":"en","primary_location":{"id":"doi:10.1145/3632410.3632482","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","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/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"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Gautam Reddy","raw_affiliation_strings":["IIIT-Delhi, India"],"raw_orcid":"https://orcid.org/0009-0009-2479-9762","affiliations":[{"raw_affiliation_string":"IIIT-Delhi, India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101882843","display_name":"Abhinav Upadhyay","orcid":"https://orcid.org/0000-0001-8201-5959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhinav Upadhyay","raw_affiliation_strings":["Accenture Labs, Bangalore, India"],"raw_orcid":"https://orcid.org/0000-0001-8201-5959","affiliations":[{"raw_affiliation_string":"Accenture Labs, Bangalore, India","institution_ids":[]}]},{"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"],"raw_orcid":"https://orcid.org/0000-0001-8217-8707","affiliations":[{"raw_affiliation_string":"Accenture Labs, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","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"],"raw_orcid":"https://orcid.org/0009-0003-8298-0216","affiliations":[{"raw_affiliation_string":"Accenture Labs, Bangalore, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073597647","display_name":"Piyush Goenka","orcid":"https://orcid.org/0009-0006-7474-1655"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piyush Goenka","raw_affiliation_strings":["Accenture Labs, Bangalore, India"],"raw_orcid":"https://orcid.org/0009-0006-7474-1655","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/A5006577584"],"corresponding_institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00183122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"578","last_page":"579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9951000213623047,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9819999933242798,"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":0.8652995824813843},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.7223671674728394},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.6694433689117432},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6255674362182617},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.624018132686615},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6162919402122498},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.563418984413147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5246315598487854},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35684075951576233},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.30504655838012695},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09936565160751343}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8652995824813843},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.7223671674728394},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.6694433689117432},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6255674362182617},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.624018132686615},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6162919402122498},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.563418984413147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246315598487854},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35684075951576233},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30504655838012695},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09936565160751343},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3632410.3632482","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","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":2,"referenced_works":["https://openalex.org/W3120335880","https://openalex.org/W4214612132"],"related_works":["https://openalex.org/W2264067234","https://openalex.org/W3124243301","https://openalex.org/W1571502335","https://openalex.org/W1589409554","https://openalex.org/W2759038785","https://openalex.org/W2172232600","https://openalex.org/W3123876860","https://openalex.org/W3124172198","https://openalex.org/W2110944602","https://openalex.org/W3213722473"],"abstract_inverted_index":{"The":[0],"time-consuming":[1],"nature":[2],"of":[3,131],"programming":[4],"robotic":[5,66,106],"motion":[6],"and":[7,49,102],"manipulation":[8],"to":[9,23,31,42,46,55,79,87,105],"achieve":[10],"specific":[11,34],"tasks":[12,25],"is":[13],"a":[14,76,92,127],"key":[15],"reason":[16],"that":[17,95],"robots":[18,81],"have":[19],"generally":[20],"been":[21],"restricted":[22],"repetitive":[24],"with":[26],"little":[27],"variation.":[28],"Developers":[29],"need":[30],"manually":[32],"write":[33],"code":[35,45,63],"for":[36,64],"each":[37],"task,":[38],"making":[39],"it":[40,104],"challenging":[41],"adapt":[43],"the":[44,88,113,120],"different":[47],"environments":[48],"assembly":[50,115],"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":[68,123],"various":[69],"assemblies.":[70],"To":[71],"address":[72],"this,":[73],"we":[74],"develop":[75],"generative":[77],"network":[78,111],"program":[80],"through":[82],"demonstration,":[83],"bringing":[84],"more":[85],"agility":[86],"process.":[89],"We":[90,108],"propose":[91],"network,":[93],"Act2Code,":[94],"takes":[96],"video":[97],"demonstration":[98],"as":[99],"an":[100],"input":[101],"translates":[103],"instructions.":[107],"evaluate":[109],"our":[110],"real-world":[114],"dataset.":[116],"Our":[117],"results":[118],"demonstrate":[119],"model\u2019s":[121],"effectiveness":[122],"generating":[124],"code,":[125],"achieving":[126],"promising":[128],"BLEU":[129],"score":[130],"0.72.":[132]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}