{"id":"https://openalex.org/W4417409739","doi":"https://doi.org/10.63317/2cbr6347bzzu","title":"ProMQA-Assembly: Multimodal Procedural QA Dataset on Assembly","display_name":"ProMQA-Assembly: Multimodal Procedural QA Dataset on Assembly","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W4417409739","doi":"https://doi.org/10.63317/2cbr6347bzzu"},"language":"en","primary_location":{"id":"doi:10.63317/2cbr6347bzzu","is_oa":false,"landing_page_url":"https://doi.org/10.63317/2cbr6347bzzu","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.02949","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067638128","display_name":"Kimihiro Hasegawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kimihiro Hasegawa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032018733","display_name":"Wiradee Imrattanatrai","orcid":"https://orcid.org/0000-0002-8461-8611"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wiradee Imrattanatrai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045914141","display_name":"Masaki Asada","orcid":"https://orcid.org/0000-0002-7117-5962"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masaki Asada","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004726092","display_name":"Susan Holm","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Susan E. Holm","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049728192","display_name":"Yuran Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuran Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120826610","display_name":"Vincent Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuanang Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045602197","display_name":"Ken Fukuda","orcid":"https://orcid.org/0000-0003-4990-6308"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ken Fukuda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052956256","display_name":"Teruko Mitamura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Teruko Mitamura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00922968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9082","last_page":"9104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.42160001397132874,"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":0.42160001397132874,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07649999856948853,"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/T13197","display_name":"Spreadsheets and End-User Computing","score":0.02410000003874302,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/benchmarking","display_name":"Benchmarking","score":0.8432999849319458},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.729200005531311},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6901000142097473},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5774000287055969},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5177000164985657},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.39480000734329224}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8432999849319458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7947999835014343},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.729200005531311},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6901000142097473},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5774000287055969},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47589999437332153},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4528999924659729},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.399399995803833},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.36239999532699585},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3531000018119812},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2694999873638153}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/2cbr6347bzzu","is_oa":false,"landing_page_url":"https://doi.org/10.63317/2cbr6347bzzu","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.02949","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.02949","pdf_url":"https://arxiv.org/pdf/2509.02949","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.02949","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.02949","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.02949","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.02949","pdf_url":"https://arxiv.org/pdf/2509.02949","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Assistants":[0],"on":[1,41],"assembly":[2,25,42,116],"tasks":[3,15],"show":[4],"great":[5],"potential":[6],"to":[7,16,102,170],"benefit":[8],"humans":[9,89],"ranging":[10],"from":[11],"helping":[12],"with":[13],"everyday":[14],"interacting":[17],"in":[18,24,64,71,125,132],"industrial":[19],"settings.":[20],"However,":[21],"evaluation":[22,39,167],"resources":[23],"activities":[26],"are":[27,123],"underexplored.":[28],"To":[29],"foster":[30],"system":[31],"development,":[32],"we":[33,75,107,141],"propose":[34],"a":[35,77],"new":[36,166],"multimodal":[37,54,147,155],"QA":[38,50,79,86,95],"dataset":[40,168],"activities.":[43],"Our":[44],"dataset,":[45,140],"ProMQA-Assembly,":[46],"consists":[47],"of":[48,56,174],"646":[49],"pairs":[51,87],"that":[52,151],"require":[53],"understanding":[55],"human":[57,135],"activity":[58],"videos":[59],"and":[60,88],"their":[61],"instruction":[62,110],"manuals":[63],"an":[65],"online-style":[66],"manner.":[67],"For":[68],"cost":[69],"effectiveness":[70],"the":[72,134,171],"data":[73],"creation,":[74],"adopt":[76],"semi-automated":[78],"annotation":[80],"approach,":[81],"where":[82,157],"LLMs":[83],"generate":[84],"candidate":[85],"verify":[90],"them.":[91],"We":[92,149,163],"further":[93,172],"improve":[94],"generation":[96],"by":[97],"integrating":[98],"fine-grained":[99],"action":[100],"labels":[101],"diversify":[103],"question":[104],"types.":[105],"Additionally,":[106],"create":[108],"81":[109],"task":[111,121],"graphs":[112,122],"for":[113],"our":[114,126,139,165],"target":[115],"tasks.":[117],"These":[118],"newly":[119],"created":[120],"used":[124],"benchmarking":[127],"experiment,":[128],"as":[129,131],"well":[130],"facilitating":[133],"verification":[136],"process.":[137],"With":[138],"benchmark":[142],"models,":[143],"including":[144],"competitive":[145],"proprietary":[146],"models.":[148],"find":[150],"ProMQA-Assembly":[152],"contains":[153],"challenging":[154],"questions,":[156],"reasoning":[158],"models":[159],"showcase":[160],"promising":[161],"results.":[162],"believe":[164],"contributes":[169],"development":[173],"procedural-activity":[175],"assistants.":[176]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}