{"id":"https://openalex.org/W3093272873","doi":"https://doi.org/10.1145/3394171.3413753","title":"Multimodal Attention with Image Text Spatial Relationship for OCR-Based Image Captioning","display_name":"Multimodal Attention with Image Text Spatial Relationship for OCR-Based Image Captioning","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093272873","doi":"https://doi.org/10.1145/3394171.3413753","mag":"3093272873"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","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/A5100378733","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0001-9752-6671"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Wang","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035112538","display_name":"Jinhui Tang","orcid":"https://orcid.org/0000-0001-9008-222X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhui Tang","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100378733"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":4.2987,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.95551859,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4337","last_page":"4345"},"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":0.9901999831199646,"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/T10028","display_name":"Topic Modeling","score":0.9883999824523926,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9614806771278381},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8144572973251343},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6510500907897949},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6366840600967407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6012968420982361},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5994399785995483},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5746616721153259},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5307880640029907},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5233120918273926},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38189131021499634},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3437056243419647},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1297002136707306}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9614806771278381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144572973251343},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6510500907897949},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6366840600967407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6012968420982361},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5994399785995483},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5746616721153259},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5307880640029907},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5233120918273926},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38189131021499634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3437056243419647},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1297002136707306},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8799999952316284,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1922126009","https://openalex.org/W1956340063","https://openalex.org/W2001642682","https://openalex.org/W2053317383","https://openalex.org/W2302086703","https://openalex.org/W2343052201","https://openalex.org/W2493916176","https://openalex.org/W2506483933","https://openalex.org/W2519936666","https://openalex.org/W2544271936","https://openalex.org/W2550687635","https://openalex.org/W2593713917","https://openalex.org/W2613052503","https://openalex.org/W2613718673","https://openalex.org/W2809273748","https://openalex.org/W2832876791","https://openalex.org/W2885013662","https://openalex.org/W2890531016","https://openalex.org/W2960655175","https://openalex.org/W2962986948","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2964018263","https://openalex.org/W2964281014","https://openalex.org/W2964296749","https://openalex.org/W2964546107","https://openalex.org/W2965697393","https://openalex.org/W2979382951","https://openalex.org/W2982834534","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W2988326850","https://openalex.org/W2990818246","https://openalex.org/W3004082545","https://openalex.org/W3004268082","https://openalex.org/W3013137071","https://openalex.org/W4236965008"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"OCR-based":[0,127],"image":[1,23,33,128,179],"captioning":[2],"is":[3,27],"the":[4,32,51,55,71,76,131,156,162,166,173,178,183,194,198,201],"task":[5,26],"of":[6,50,133,200],"automatically":[7],"describing":[8],"images":[9],"based":[10,69],"on":[11,70,161,193],"reading":[12],"and":[13,38,62,119,136,151,165],"understanding":[14],"written":[15],"text":[16,36,67,124,134,149,180,188],"contained":[17,53],"in":[18,54,85],"images.":[19],"Compared":[20],"to":[21,46,58,64,214],"conventional":[22],"captioning,":[24],"this":[25,89],"more":[28],"challenging,":[29],"especially":[30],"when":[31],"contains":[34],"multiple":[35],"tokens":[37,125,135,150],"visual":[39],"objects.":[40],"The":[41],"difficulties":[42],"originate":[43],"from":[44,111,172,177,212],"how":[45,63],"make":[47],"full":[48],"use":[49],"knowledge":[52],"textual":[56],"entities":[57],"facilitate":[59],"sentence":[60],"generation":[61],"predict":[65],"a":[66,93,115,141],"token":[68],"limited":[72],"information":[73,110],"provided":[74],"by":[75,181],"image.":[77],"Such":[78],"problems":[79],"are":[80,138,153,170],"not":[81],"yet":[82],"fully":[83],"investigated":[84],"existing":[86],"research.":[87],"In":[88],"paper,":[90],"we":[91],"present":[92],"novel":[94],"design":[95],"-":[96],"Multimodal":[97],"Attention":[98],"Captioner":[99],"with":[100,114],"OCR":[101],"Spatial":[102],"Relationship":[103],"(dubbed":[104],"as":[105],"MMA-SR)":[106],"architecture,":[107],"which":[108],"manages":[109],"different":[112],"modalities":[113],"multimodal":[116,157],"attention":[117,146,158],"network":[118],"explores":[120],"spatial":[121,185],"relationships":[122,186],"between":[123,187],"for":[126,148],"captioning.":[129],"Specifically,":[130],"representations":[132],"objects":[137,152],"fed":[139],"into":[140],"three-layer":[142],"LSTM":[143,167],"captioner.":[144],"Different":[145],"scores":[147],"exploited":[154],"through":[155],"network.":[159],"Based":[160],"attended":[163],"features":[164],"states,":[168],"words":[169],"selected":[171],"common":[174],"vocabulary":[175],"or":[176],"incorporating":[182],"learned":[184],"tokens.":[189],"Extensive":[190],"experiments":[191],"conducted":[192],"TextCaps":[195],"dataset":[196],"verify":[197],"effectiveness":[199],"proposed":[202],"MMA-SR":[203,208],"method.":[204],"More":[205],"remarkably,":[206],"our":[207],"increases":[209],"CIDEr-D":[210],"score":[211],"93.7%":[213],"98.0%.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}