{"id":"https://openalex.org/W4390548063","doi":"https://doi.org/10.1145/3632410.3632467","title":"GIMNet: Assembly Plan Generation from Graphical Instruction Manual","display_name":"GIMNet: Assembly Plan Generation from Graphical Instruction Manual","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4390548063","doi":"https://doi.org/10.1145/3632410.3632467"},"language":"en","primary_location":{"id":"doi:10.1145/3632410.3632467","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632467","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/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"],"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":"last","author":{"id":"https://openalex.org/A5071482252","display_name":"Suma Mani Kuriakose","orcid":"https://orcid.org/0000-0002-5490-9928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suma Mani Kuriakose","raw_affiliation_strings":["Accenture Labs, Bangalore, India"],"raw_orcid":"https://orcid.org/0000-0002-5490-9928","affiliations":[{"raw_affiliation_string":"Accenture Labs, Bangalore, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101882843"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6661,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69784206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"422","last_page":"429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T11159","display_name":"Manufacturing Process and Optimization","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.993399977684021,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9914000034332275,"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":0.8402431011199951},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.5970546007156372},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.581325113773346},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.574912965297699},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5446937680244446},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5359253883361816},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5268339514732361},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45838066935539246},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.45061129331588745},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4143403172492981},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3860948085784912},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34391647577285767},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3203383684158325},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.20411592721939087},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16799062490463257},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.10222852230072021},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07058137655258179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8402431011199951},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.5970546007156372},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.581325113773346},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.574912965297699},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5446937680244446},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5359253883361816},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5268339514732361},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45838066935539246},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.45061129331588745},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4143403172492981},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3860948085784912},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34391647577285767},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3203383684158325},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.20411592721939087},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16799062490463257},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.10222852230072021},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07058137655258179},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3632410.3632467","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632467","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1668476885","https://openalex.org/W2553710993","https://openalex.org/W2560023338","https://openalex.org/W2561337467","https://openalex.org/W2964309882","https://openalex.org/W2967532292","https://openalex.org/W3035625567","https://openalex.org/W3100255941","https://openalex.org/W3127162144","https://openalex.org/W3138516171","https://openalex.org/W3168238783","https://openalex.org/W4281298696","https://openalex.org/W4319323788","https://openalex.org/W6849909303"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W1976205134","https://openalex.org/W2381570729","https://openalex.org/W4248336175","https://openalex.org/W3009369890","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W4312490297","https://openalex.org/W2062212388"],"abstract_inverted_index":{"Graphical":[0],"instruction":[1,72,90],"manuals":[2,14],"are":[3],"commonly":[4],"employed":[5],"for":[6,65],"assembling":[7],"various":[8],"products,":[9],"particularly":[10],"furniture.":[11],"However,":[12],"these":[13,52],"often":[15],"lack":[16],"detailed":[17],"written":[18],"task":[19],"instructions":[20,45],"and":[21,84,95,155],"rely":[22],"primarily":[23],"on":[24,48,123,158],"a":[25,60,76,110],"series":[26],"of":[27,51,98,128,144],"illustrated":[28,53],"images":[29],"to":[30,42,81,103,114,140],"convey":[31],"the":[32,44,49,89,116,124,142,152,160],"assembly":[33,68,106,117,134],"process.":[34],"Consequently,":[35],"in":[36,88],"many":[37],"cases,":[38],"it":[39],"becomes":[40],"essential":[41],"comprehend":[43],"solely":[46],"based":[47],"sequence":[50],"images.":[54],"In":[55],"this":[56],"work,":[57],"we":[58],"propose":[59],"deep":[61],"neural":[62],"network,":[63],"GIMNet,":[64],"automatically":[66],"generating":[67],"plans":[69],"from":[70],"graphical":[71],"manuals.":[73,135],"We":[74,108,119,136,147],"develop":[75],"hierarchical":[77],"Swin":[78],"Transformer":[79],"model":[80,115],"predict":[82],"actions":[83,94],"segment":[85],"different":[86],"parts":[87,100],"manual.":[91],"The":[92],"predicted":[93],"extracted":[96],"information":[97],"corresponding":[99],"is":[101],"used":[102],"construct":[104],"an":[105],"graph.":[107],"apply":[109],"functional":[111],"object-oriented":[112],"network":[113,122],"plan.":[118],"evaluate":[120,141],"our":[121,145,149],"IKEA-Manual":[125],"dataset":[126],"consisting":[127],"102":[129],"IKEA":[130],"objects":[131],"paired":[132],"with":[133,151],"perform":[137],"quantitative":[138],"analysis":[139],"efficacy":[143],"approach.":[146],"compare":[148],"approach":[150],"existing":[153],"baseline":[154],"significantly":[156],"outperform":[157],"all":[159],"metrics.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}