{"id":"https://openalex.org/W3153965221","doi":"https://doi.org/10.1145/3442381.3449923","title":"Generating Accurate Caption Units for Figure Captioning","display_name":"Generating Accurate Caption Units for Figure Captioning","publication_year":2021,"publication_date":"2021-04-19","ids":{"openalex":"https://openalex.org/W3153965221","doi":"https://doi.org/10.1145/3442381.3449923","mag":"3153965221"},"language":"en","primary_location":{"id":"doi:10.1145/3442381.3449923","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449923","pdf_url":null,"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 Web Conference 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3442381.3449923","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101737150","display_name":"Xin Qian","orcid":"https://orcid.org/0000-0001-6436-2690"},"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":"Xin Qian","raw_affiliation_strings":["University of Maryland, College Park, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071007779","display_name":"Eunyee Koh","orcid":"https://orcid.org/0000-0003-2091-5972"},"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":"Eunyee Koh","raw_affiliation_strings":["Adobe Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073516753","display_name":"Fan Du","orcid":"https://orcid.org/0000-0002-4383-8888"},"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":"Fan Du","raw_affiliation_strings":["Adobe Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718934","display_name":"Sungchul Kim","orcid":"https://orcid.org/0000-0003-3580-5290"},"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":"Sungchul Kim","raw_affiliation_strings":["Adobe Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003751225","display_name":"Joel Chan","orcid":"https://orcid.org/0000-0003-3000-4160"},"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":"Joel Chan","raw_affiliation_strings":["University of Maryland, College Park, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009957887","display_name":"Ryan A. Rossi","orcid":"https://orcid.org/0000-0001-9758-0635"},"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":"Ryan A. Rossi","raw_affiliation_strings":["Adobe Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018266351","display_name":"Sana Malik","orcid":"https://orcid.org/0000-0001-8885-186X"},"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":"Sana Malik","raw_affiliation_strings":["Adobe Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069834920","display_name":"Tak Yeon Lee","orcid":"https://orcid.org/0000-0002-9235-9947"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tak Yeon Lee","raw_affiliation_strings":["Department of Industrial Design, KAIST, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Design, KAIST, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2792","last_page":"2804"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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/T11439","display_name":"Video Analysis and Summarization","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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9648154973983765},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8594003915786743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5836719870567322},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5519794225692749},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.551251232624054},{"id":"https://openalex.org/keywords/paraphrase","display_name":"Paraphrase","score":0.5479438900947571},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.439268559217453},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4277181327342987},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41323456168174744},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4075245261192322},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3535419702529907},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17329120635986328},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16885560750961304}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9648154973983765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8594003915786743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5836719870567322},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5519794225692749},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.551251232624054},{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.5479438900947571},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.439268559217453},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4277181327342987},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41323456168174744},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4075245261192322},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3535419702529907},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17329120635986328},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16885560750961304}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3442381.3449923","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449923","pdf_url":null,"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 Web Conference 2021","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3442381.3449923","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449923","pdf_url":null,"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 Web Conference 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W103848519","https://openalex.org/W194369716","https://openalex.org/W1579838312","https://openalex.org/W1587890082","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1948566616","https://openalex.org/W1978722038","https://openalex.org/W2029844001","https://openalex.org/W2053690843","https://openalex.org/W2068985441","https://openalex.org/W2101105183","https://openalex.org/W2121278608","https://openalex.org/W2123301721","https://openalex.org/W2141971526","https://openalex.org/W2251329024","https://openalex.org/W2251707744","https://openalex.org/W2277195237","https://openalex.org/W2304113845","https://openalex.org/W2346371394","https://openalex.org/W2520300089","https://openalex.org/W2549599535","https://openalex.org/W2551940339","https://openalex.org/W2552161745","https://openalex.org/W2606974598","https://openalex.org/W2745461083","https://openalex.org/W2745653947","https://openalex.org/W2748261613","https://openalex.org/W2796032388","https://openalex.org/W2891021031","https://openalex.org/W2901988662","https://openalex.org/W2946635368","https://openalex.org/W2951619830","https://openalex.org/W2963954913","https://openalex.org/W2972897806","https://openalex.org/W2973546605","https://openalex.org/W2976658881","https://openalex.org/W2982573303","https://openalex.org/W3004189960","https://openalex.org/W3014820286","https://openalex.org/W3029025901","https://openalex.org/W3032875465","https://openalex.org/W3093370362","https://openalex.org/W4299670242","https://openalex.org/W6730782440"],"related_works":["https://openalex.org/W3200285530","https://openalex.org/W3009270862","https://openalex.org/W2955859849","https://openalex.org/W2152921782","https://openalex.org/W382594479","https://openalex.org/W3213765460","https://openalex.org/W3034878914","https://openalex.org/W2470045054","https://openalex.org/W2575772232","https://openalex.org/W2151245229"],"abstract_inverted_index":{"Scientific-style":[0],"figures":[1],"are":[2],"commonly":[3],"used":[4],"on":[5,33,91],"the":[6,59,121,148,166],"web":[7],"to":[8,170],"present":[9,30],"numerical":[10],"information.":[11],"Captions":[12],"that":[13,45,86,100,127],"tell":[14],"accurate":[15,54,82,133],"figure":[16,24,35,47,122],"information":[17,107],"and":[18,108,112,158,172],"sound":[19],"natural":[20],"would":[21],"significantly":[22],"improve":[23],"accessibility.":[25],"In":[26],"this":[27,102],"paper,":[28],"we":[29,95],"promising":[31],"results":[32],"machine":[34,46],"captioning.":[36],"A":[37,140],"recent":[38],"corpus":[39],"analysis":[40],"of":[41,85,150],"real-world":[42],"captions":[43,180],"reveals":[44],"captioning":[48,67],"systems":[49],"should":[50],"start":[51],"by":[52,181],"generating":[53],"caption":[55,60,71,83,134,152,176],"units.":[56],"We":[57],"formulate":[58],"unit":[61,72,84],"generation":[62],"problem":[63],"as":[64,74],"a":[65,70,75,78,89,97,109,161],"controlled":[66],"problem.":[68],"Given":[69],"type":[73],"control":[76],"signal,":[77],"model":[79,129],"generates":[80],"an":[81],"type.":[87],"As":[88],"proof-of-concept":[90],"single":[92],"bar":[93],"charts,":[94],"propose":[96],"model,":[98],"FigJAM,":[99],"achieves":[101],"goal":[103],"through":[104],"utilizing":[105],"metadata":[106],"joint":[110],"static":[111],"dynamic":[113],"dictionary.":[114],"Quantitative":[115],"evaluations":[116],"with":[117,143],"two":[118],"datasets":[119],"from":[120,183],"question":[123],"answering":[124],"task":[125],"show":[126],"our":[128],"can":[130],"generate":[131],"more":[132],"units":[135,153,177],"than":[136],"competitive":[137],"baseline":[138],"models.":[139],"user":[141],"study":[142,164],"ten":[144],"human":[145],"experts":[146],"confirms":[147],"value":[149],"machine-generated":[151],"in":[154],"their":[155],"standalone":[156],"accuracy":[157],"naturalness.":[159],"Finally,":[160],"post-editing":[162],"simulation":[163],"demonstrates":[165],"potential":[167],"for":[168],"models":[169],"paraphrase":[171],"stitch":[173],"together":[174],"single-type":[175],"into":[178],"multi-type":[179],"learning":[182],"data.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}