{"id":"https://openalex.org/W4396833747","doi":"https://doi.org/10.1145/3613904.3642443","title":"TutoAI: a cross-domain framework for AI-assisted mixed-media tutorial creation on physical tasks","display_name":"TutoAI: a cross-domain framework for AI-assisted mixed-media tutorial creation on physical tasks","publication_year":2024,"publication_date":"2024-05-11","ids":{"openalex":"https://openalex.org/W4396833747","doi":"https://doi.org/10.1145/3613904.3642443"},"language":"en","primary_location":{"id":"doi:10.1145/3613904.3642443","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642443","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642443","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642443","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067131063","display_name":"Yuexi Chen","orcid":"https://orcid.org/0000-0001-8720-5516"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuexi Chen","raw_affiliation_strings":["University of Maryland, United States"],"raw_orcid":"https://orcid.org/0000-0001-8720-5516","affiliations":[{"raw_affiliation_string":"University of Maryland, United States","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038267072","display_name":"Vlad I. Morariu","orcid":"https://orcid.org/0000-0001-7937-7748"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vlad I Morariu","raw_affiliation_strings":["Adobe Research, United States"],"raw_orcid":"https://orcid.org/0000-0001-7937-7748","affiliations":[{"raw_affiliation_string":"Adobe Research, United States","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097660143","display_name":"Anh Truong","orcid":"https://orcid.org/0009-0005-5409-7287"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anh Truong","raw_affiliation_strings":["Adobe Research, United States"],"raw_orcid":"https://orcid.org/0009-0005-5409-7287","affiliations":[{"raw_affiliation_string":"Adobe Research, United States","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100745766","display_name":"Zhicheng Liu","orcid":"https://orcid.org/0000-0002-1015-2759"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhicheng Liu","raw_affiliation_strings":["University of Maryland, United States"],"raw_orcid":"https://orcid.org/0000-0002-1015-2759","affiliations":[{"raw_affiliation_string":"University of Maryland, United States","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2809,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.931806,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9919999837875366,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9919000267982483,"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":0.8409782648086548},{"id":"https://openalex.org/keywords/timeline","display_name":"Timeline","score":0.8100757598876953},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6628859639167786},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.6359259486198425},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5275121331214905},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4632810950279236},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4545816481113434},{"id":"https://openalex.org/keywords/end-user-development","display_name":"End-user development","score":0.4401651620864868},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3529731035232544},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3401340842247009},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.1957157850265503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8409782648086548},{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.8100757598876953},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6628859639167786},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6359259486198425},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5275121331214905},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4632810950279236},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4545816481113434},{"id":"https://openalex.org/C2776867947","wikidata":"https://www.wikidata.org/wiki/Q500467","display_name":"End-user development","level":3,"score":0.4401651620864868},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3529731035232544},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3401340842247009},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.1957157850265503},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3613904.3642443","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642443","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642443","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3613904.3642443","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642443","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642443","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8500000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396833747.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1603598191","https://openalex.org/W1631063262","https://openalex.org/W1861492603","https://openalex.org/W1988366361","https://openalex.org/W2029044878","https://openalex.org/W2035818959","https://openalex.org/W2051277183","https://openalex.org/W2059216172","https://openalex.org/W2060666149","https://openalex.org/W2110693578","https://openalex.org/W2206440038","https://openalex.org/W2277195237","https://openalex.org/W2794125445","https://openalex.org/W2795818739","https://openalex.org/W2796171214","https://openalex.org/W2916904544","https://openalex.org/W2918341242","https://openalex.org/W2940666954","https://openalex.org/W2952132648","https://openalex.org/W2962869524","https://openalex.org/W2963351113","https://openalex.org/W2963758027","https://openalex.org/W2964089981","https://openalex.org/W3029354791","https://openalex.org/W3030590228","https://openalex.org/W3031000691","https://openalex.org/W3107128832","https://openalex.org/W3120889656","https://openalex.org/W3122206733","https://openalex.org/W3125649296","https://openalex.org/W3159619744","https://openalex.org/W3162594825","https://openalex.org/W3163245619","https://openalex.org/W3170778815","https://openalex.org/W3173181308","https://openalex.org/W3203321135","https://openalex.org/W3206079177","https://openalex.org/W4214663214","https://openalex.org/W4236965008","https://openalex.org/W4284880452","https://openalex.org/W4287107550","https://openalex.org/W4288359814","https://openalex.org/W4292760860","https://openalex.org/W4312956471","https://openalex.org/W4390873401","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W1858249912","https://openalex.org/W2114034199","https://openalex.org/W4391249598","https://openalex.org/W2317428717","https://openalex.org/W2734259032","https://openalex.org/W3094038556","https://openalex.org/W2014772881","https://openalex.org/W4254228154","https://openalex.org/W3049477255","https://openalex.org/W4296345146"],"abstract_inverted_index":{"Mixed-media":[0],"tutorials,":[1],"which":[2],"integrate":[3],"videos,":[4],"images,":[5],"text,":[6],"and":[7,27,57,95],"diagrams":[8],"to":[9,34,47,92,130],"teach":[10],"procedural":[11],"skills,":[12],"offer":[13],"more":[14],"browsable":[15],"alternatives":[16],"than":[17],"timeline-based":[18],"videos.":[19],"However,":[20],"manually":[21],"creating":[22],"such":[23],"tutorials":[24],"is":[25,44],"tedious,":[26],"existing":[28,85],"automated":[29],"solutions":[30],"are":[31],"often":[32],"restricted":[33],"a":[35,66,131],"particular":[36],"domain.":[37],"While":[38],"AI":[39,97],"models":[40,98],"hold":[41],"promise,":[42],"it":[43],"unclear":[45],"how":[46],"effectively":[48],"harness":[49],"their":[50],"powers,":[51],"given":[52],"the":[53,58],"multi-modal":[54],"data":[55],"involved":[56],"vast":[59],"landscape":[60],"of":[61],"models.":[62],"We":[63,119],"present":[64,89],"TutoAI,":[65],"cross-domain":[67],"framework":[68],"for":[69,99,106],"AI-assisted":[70],"mixed-media":[71],"tutorial":[72,81,113],"creation":[73,114],"on":[74,116],"physical":[75],"tasks.":[76],"First,":[77],"we":[78,88,103],"distill":[79],"common":[80],"components":[82],"by":[83],"surveying":[84],"work;":[86],"then,":[87],"an":[90],"approach":[91],"identify,":[93],"assemble,":[94],"evaluate":[96],"component":[100],"extraction;":[101],"finally,":[102],"propose":[104],"guidelines":[105],"designing":[107],"user":[108,136],"interfaces":[109],"(UI)":[110],"that":[111,121],"support":[112],"based":[115],"AI-generated":[117],"components.":[118],"show":[120],"TutoAI":[122],"has":[123],"achieved":[124],"higher":[125],"or":[126],"similar":[127],"quality":[128],"compared":[129],"baseline":[132],"model":[133],"in":[134],"preliminary":[135],"studies.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}