{"id":"https://openalex.org/W4283399970","doi":"https://doi.org/10.1145/3512527.3531431","title":"OCR-oriented Master Object for Text Image Captioning","display_name":"OCR-oriented Master Object for Text Image Captioning","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4283399970","doi":"https://doi.org/10.1145/3512527.3531431"},"language":"en","primary_location":{"id":"doi:10.1145/3512527.3531431","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","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/A5048868707","display_name":"Wenliang Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenliang Tang","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040235604","display_name":"Zhenzhen Hu","orcid":"https://orcid.org/0000-0003-1042-8361"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhen Hu","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025890671","display_name":"Zijie Song","orcid":"https://orcid.org/0000-0002-1262-764X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijie Song","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051332325","display_name":"Richang Hong","orcid":"https://orcid.org/0000-0001-5461-3986"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048868707"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.5033,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.62703368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"43"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9941999912261963,"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":0.9887999892234802,"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":0.8734748959541321},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8332352638244629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6967213749885559},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6626142263412476},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5000314712524414},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.49145233631134033},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4911315143108368},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.451454758644104},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43903133273124695},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.4290265738964081},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42280346155166626},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3669888973236084},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3303501009941101},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3272104859352112},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.22483932971954346},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.10449999570846558}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8734748959541321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8332352638244629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6967213749885559},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6626142263412476},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5000314712524414},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.49145233631134033},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4911315143108368},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.451454758644104},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43903133273124695},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4290265738964081},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42280346155166626},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3669888973236084},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3303501009941101},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3272104859352112},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.22483932971954346},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.10449999570846558},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3512527.3531431","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2822193437","display_name":null,"funder_award_id":"62172138, 61932009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2053317383","https://openalex.org/W2133459682","https://openalex.org/W2277195237","https://openalex.org/W2493916176","https://openalex.org/W2506483933","https://openalex.org/W2745461083","https://openalex.org/W2809273748","https://openalex.org/W2949376505","https://openalex.org/W2963084599","https://openalex.org/W2963758027","https://openalex.org/W2964018263","https://openalex.org/W2979382951","https://openalex.org/W2986670728","https://openalex.org/W3034336960","https://openalex.org/W3034655362","https://openalex.org/W3093272873","https://openalex.org/W3103022576","https://openalex.org/W3106859150","https://openalex.org/W3110661548","https://openalex.org/W3174012740","https://openalex.org/W3177430964","https://openalex.org/W3215633354"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4287661223"],"abstract_inverted_index":{"Text":[0],"image":[1,12,42],"captioning":[2,43],"aims":[3],"to":[4,23,60,87,140],"understand":[5,24],"the":[6,25,28,47,58,62,68,73,77,81,95,99,108,114,120,124,132,137,147,154,157],"scene":[7,49,110],"text":[8,29,41],"in":[9,94],"images":[10],"for":[11,102],"caption":[13],"generation.":[14],"The":[15,54],"key":[16],"issue":[17],"of":[18,156],"this":[19,35],"challenging":[20],"task":[21],"is":[22,57,64,67],"relationship":[26,70],"between":[27,72],"OCR":[30,63,74,89,104,133],"tokens":[31,90,134],"and":[32,76,91,117,135,150],"images.":[33],"In":[34],"paper,":[36],"we":[37,106,130],"propose":[38],"a":[39,85,142],"novel":[40],"method":[44],"by":[45,123],"purifying":[46],"OCR-oriented":[48],"graph":[50,111],"with":[51],"themaster":[52],"object.":[53],"master":[55,82,100,115],"object":[56,59,83,101],"which":[61,66],"attached,":[65],"semantic":[69],"bridge":[71],"token":[75],"image.":[78,96],"We":[79],"consider":[80],"as":[84],"proxy":[86],"connect":[88],"other":[92],"regions":[93],"By":[97],"exploring":[98],"each":[103],"token,":[105],"build":[107],"purified":[109],"based":[112],"on":[113,146],"objects":[116],"then":[118],"enrich":[119],"visual":[121],"embedding":[122],"Graph":[125],"Convolution":[126],"Network":[127],"(GCN).":[128],"Furthermore,":[129],"cluster":[131],"feed":[136],"hierarchical":[138],"information":[139],"provide":[141],"richer":[143],"representation.":[144],"Experiments":[145],"TextCaps":[148],"validation":[149],"test":[151],"dataset":[152],"demonstrate":[153],"effectiveness":[155],"proposed":[158],"method.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}