{"id":"https://openalex.org/W2972354974","doi":"https://doi.org/10.1145/3341162.3345601","title":"Neural caption generation over figures","display_name":"Neural caption generation over figures","publication_year":2019,"publication_date":"2019-09-09","ids":{"openalex":"https://openalex.org/W2972354974","doi":"https://doi.org/10.1145/3341162.3345601","mag":"2972354974"},"language":"en","primary_location":{"id":"doi:10.1145/3341162.3345601","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3341162.3345601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers","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/A5071015273","display_name":"Charles Chen","orcid":"https://orcid.org/0000-0002-2203-0433"},"institutions":[{"id":"https://openalex.org/I4210106879","display_name":"Ohio University","ror":"https://ror.org/01jr3y717","country_code":"US","type":"education","lineage":["https://openalex.org/I4210106879"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Charles Chen","raw_affiliation_strings":["Ohio University"],"affiliations":[{"raw_affiliation_string":"Ohio University","institution_ids":["https://openalex.org/I4210106879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424484","display_name":"Ruiyi Zhang","orcid":"https://orcid.org/0000-0002-4776-6762"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruiyi Zhang","raw_affiliation_strings":["Duke University"],"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055156362","display_name":"Scott Cohen","orcid":"https://orcid.org/0000-0002-3459-6899"},"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":"Scott Cohen","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767815","display_name":"Tong Yu","orcid":"https://orcid.org/0000-0001-7998-3326"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Yu","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"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 Rossi","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020435927","display_name":"R\u0103zvan Bunescu","orcid":"https://orcid.org/0000-0003-2919-3566"},"institutions":[{"id":"https://openalex.org/I4210106879","display_name":"Ohio University","ror":"https://ror.org/01jr3y717","country_code":"US","type":"education","lineage":["https://openalex.org/I4210106879"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Razvan Bunescu","raw_affiliation_strings":["Ohio University"],"affiliations":[{"raw_affiliation_string":"Ohio University","institution_ids":["https://openalex.org/I4210106879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5071015273"],"corresponding_institution_ids":["https://openalex.org/I4210106879"],"apc_list":null,"apc_paid":null,"fwci":0.9195,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.79487058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"482","last_page":"485"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9944000244140625,"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":0.9932000041007996,"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":0.95926833152771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8903754949569702},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7553296089172363},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6049872636795044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5887912511825562},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5821067094802856},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5306745171546936},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5174134969711304},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.43642523884773254},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39256399869918823},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15737953782081604},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15204280614852905}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.95926833152771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8903754949569702},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7553296089172363},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6049872636795044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5887912511825562},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5821067094802856},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5306745171546936},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5174134969711304},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.43642523884773254},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39256399869918823},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15737953782081604},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15204280614852905},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3341162.3345601","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3341162.3345601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2520300089","https://openalex.org/W2600463316","https://openalex.org/W2785017694","https://openalex.org/W2963084599"],"related_works":["https://openalex.org/W3009270862","https://openalex.org/W2955859849","https://openalex.org/W2152921782","https://openalex.org/W382594479","https://openalex.org/W2293063786","https://openalex.org/W2470045054","https://openalex.org/W2575772232","https://openalex.org/W2911292476","https://openalex.org/W2151245229","https://openalex.org/W2140902089"],"abstract_inverted_index":{"Figures":[0],"are":[1,102],"human-friendly":[2],"but":[3],"difficult":[4],"for":[5,39],"computers":[6],"to":[7,23,70,76,79,87],"process":[8],"automatically.":[9],"In":[10],"this":[11,71],"work,":[12],"we":[13,51],"investigate":[14],"the":[15,53,65],"problem":[16],"of":[17,30,47,95,98],"figure":[18,40,74],"captioning.":[19],"The":[20],"goal":[21],"is":[22],"automatically":[24],"generate":[25],"a":[26,31,36,88],"natural":[27],"language":[28],"description":[29],"given":[32],"figure.":[33],"We":[34],"create":[35],"new":[37],"dataset":[38],"captioning,":[41],"FigCAP.":[42],"To":[43],"achieve":[44],"accurate":[45],"generation":[46],"labels":[48],"in":[49],"figures,":[50],"propose":[52],"Label":[54],"Maps":[55],"Attention":[56],"Model.":[57],"Extensive":[58],"experiments":[59],"show":[60],"that":[61],"our":[62],"method":[63],"outperforms":[64],"baselines.":[66],"A":[67],"successful":[68],"solution":[69],"task":[72],"allows":[73],"content":[75],"be":[77],"accessible":[78],"those":[80],"with":[81],"visual":[82],"impairment":[83],"by":[84],"providing":[85],"input":[86],"text-to-speech":[89],"system;":[90],"and":[91],"enables":[92],"automatic":[93],"parsing":[94],"vast":[96],"repositories":[97],"documents":[99],"where":[100],"figures":[101],"pervasive.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}