{"id":"https://openalex.org/W2906314281","doi":"https://doi.org/10.1109/tmm.2018.2888822","title":"High-Quality Image Captioning With Fine-Grained and Semantic-Guided Visual Attention","display_name":"High-Quality Image Captioning With Fine-Grained and Semantic-Guided Visual Attention","publication_year":2018,"publication_date":"2018-12-20","ids":{"openalex":"https://openalex.org/W2906314281","doi":"https://doi.org/10.1109/tmm.2018.2888822","mag":"2906314281"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2018.2888822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2018.2888822","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10453/132536","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060113731","display_name":"Zongjian Zhang","orcid":"https://orcid.org/0000-0001-9309-1826"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zongjian Zhang","raw_affiliation_strings":["Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9309-1826","affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063629854","display_name":"Qiang Wu","orcid":"https://orcid.org/0000-0001-5641-2483"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiang Wu","raw_affiliation_strings":["Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714578","display_name":"Yang Wang","orcid":"https://orcid.org/0000-0002-6815-0879"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["Data61, Commonwealth Scientific and Industrial Research Organisation, Eveleigh, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data61, Commonwealth Scientific and Industrial Research Organisation, Eveleigh, NSW, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100400043","display_name":"Fang Chen","orcid":"https://orcid.org/0000-0003-4971-8729"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Fang Chen","raw_affiliation_strings":["Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7444,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":0.95752601,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"21","issue":"7","first_page":"1681","last_page":"1693"},"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":0.9983000159263611,"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":0.9912999868392944,"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":0.9049489498138428},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8157837390899658},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6560385227203369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6218990683555603},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5944222807884216},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5778748393058777},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5749290585517883},{"id":"https://openalex.org/keywords/semantic-grid","display_name":"Semantic grid","score":0.5632637143135071},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5410827994346619},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4408940076828003},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4345618188381195},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4010744094848633},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.28213363885879517},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.11452481150627136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9049489498138428},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8157837390899658},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6560385227203369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6218990683555603},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5944222807884216},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5778748393058777},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5749290585517883},{"id":"https://openalex.org/C103692084","wikidata":"https://www.wikidata.org/wiki/Q1765824","display_name":"Semantic grid","level":3,"score":0.5632637143135071},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5410827994346619},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4408940076828003},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4345618188381195},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4010744094848633},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28213363885879517},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.11452481150627136},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2018.2888822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2018.2888822","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/132536","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/132536","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:opus.lib.uts.edu.au:10453/132536","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/132536","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6499999761581421,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1895989618","https://openalex.org/W1905882502","https://openalex.org/W1923211482","https://openalex.org/W1930223417","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W1992841082","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2133564696","https://openalex.org/W2142192571","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2395611524","https://openalex.org/W2412782625","https://openalex.org/W2463565445","https://openalex.org/W2463955103","https://openalex.org/W2528841789","https://openalex.org/W2550553598","https://openalex.org/W2552002300","https://openalex.org/W2552161745","https://openalex.org/W2556951257","https://openalex.org/W2561196672","https://openalex.org/W2563296158","https://openalex.org/W2575842049","https://openalex.org/W2607579284","https://openalex.org/W2739107216","https://openalex.org/W2753232960","https://openalex.org/W2754689878","https://openalex.org/W2802194751","https://openalex.org/W2808711976","https://openalex.org/W2949376505","https://openalex.org/W2962835968","https://openalex.org/W2963088515","https://openalex.org/W2963093690","https://openalex.org/W2963175879","https://openalex.org/W2963201326","https://openalex.org/W2963758027","https://openalex.org/W2963954913","https://openalex.org/W2964018924","https://openalex.org/W2964049455","https://openalex.org/W2964308564","https://openalex.org/W3099884890","https://openalex.org/W3101225052","https://openalex.org/W3103022576","https://openalex.org/W6630875275","https://openalex.org/W6637373629","https://openalex.org/W6638742206","https://openalex.org/W6639102338","https://openalex.org/W6678262379","https://openalex.org/W6679434410","https://openalex.org/W6688674406","https://openalex.org/W6715287400","https://openalex.org/W6719057275","https://openalex.org/W6729046916"],"related_works":["https://openalex.org/W2767651786","https://openalex.org/W2912288872","https://openalex.org/W564581980","https://openalex.org/W3106036237","https://openalex.org/W2886673456","https://openalex.org/W2295021132","https://openalex.org/W2546942002","https://openalex.org/W2970216048","https://openalex.org/W785854688","https://openalex.org/W2770168862"],"abstract_inverted_index":{"The":[0,83],"soft-attention":[1,28],"mechanism":[2,29,226],"is":[3,72,99,162,233],"regarded":[4],"as":[5],"one":[6],"of":[7,66,158,180,227,265,271],"the":[8,16,27,33,45,48,64,69,76,108,113,122,137,155,166,171,177,190,218,239,248],"representative":[9],"methods":[10,58,283],"for":[11,47],"image":[12,46,71],"captioning.":[13],"Based":[14],"on":[15,136],"end-to-end":[17],"convolutional":[18,139],"neural":[19],"network":[20,140],"(CNN)-long":[21],"short":[22],"term":[23],"memory":[24],"(LSTM)":[25],"framework,":[26,142],"attempts":[30],"to":[31,63,75,186,192,194,217],"link":[32,102,238],"semantic":[34,101,175,205,208,245],"representation":[35],"in":[36,44],"text":[37],"(i.e.,":[38,174],"captioning)":[39],"with":[40,243],"relevant":[41,240],"visual":[42,84,156,178,231,241],"information":[43,216,242],"first":[49],"time.":[50],"Motivated":[51],"by":[52,165,251],"this":[53,129,223],"approach,":[54],"several":[55],"state-of-the-art":[56],"attention":[57,147,232],"are":[59,184],"proposed.":[60],"However,":[61],"due":[62],"constraints":[65],"CNN":[67,287],"architecture,":[68],"given":[70],"only":[73,164],"segmented":[74],"fixed-resolution":[77],"grid":[78,89,104,160,182],"at":[79,149],"a":[80,116,132,150,225],"coarse":[81],"level.":[82],"feature":[85,157],"extracted":[86],"from":[87,207],"each":[88,159,187,244],"indiscriminately":[90],"fuses":[91],"all":[92,281],"inside":[93,247],"objects":[94],"and/or":[95],"their":[96],"portions.":[97],"There":[98],"no":[100],"between":[103],"cells.":[105],"In":[106,222],"addition,":[107],"large":[109,195],"area":[110,196],"\u201cstuff\u201d":[111],"(e.g.,":[112],"sky":[114],"or":[115],"beach)":[117],"cannot":[118],"be":[119],"represented":[120],"using":[121],"current":[123],"methods.":[124],"To":[125],"address":[126],"these":[127],"problems,":[128],"paper":[130],"proposes":[131],"new":[133],"model":[134,261,278],"based":[135],"fully":[138],"(FCN)-LSTM":[141],"which":[143,235],"can":[144,200,212,236,262],"generate":[145,263],"an":[146,203],"map":[148],"fine-grained":[151,228],"grid-wise":[152,172],"resolution.":[153],"Moreover,":[154,276],"cell":[161],"contributed":[163],"principal":[167],"object.":[168],"By":[169],"adopting":[170],"labels":[173],"segmentation),":[176],"representations":[179],"different":[181],"cells":[183],"correlated":[185],"other.":[188],"With":[189],"ability":[191],"attend":[193],"\u201cstuff,\u201d":[197],"our":[198,260,277],"method":[199,211],"further":[201],"summarize":[202],"additional":[204],"context":[206,215],"labels.":[209],"This":[210],"provide":[213],"comprehensive":[214],"language":[219],"LSTM":[220],"decoder.":[221],"way,":[224],"and":[229,257,274],"semantic-guided":[230],"created,":[234],"accurately":[237],"meaning":[246],"text.":[249],"Demonstrated":[250],"three":[252],"experiments":[253],"including":[254],"both":[255],"qualitative":[256],"quantitative":[258],"analyses,":[259],"captions":[264],"high":[266,269],"quality,":[267],"specifically":[268],"levels":[270],"accuracy,":[272],"completeness,":[273],"diversity.":[275],"significantly":[279],"outperforms":[280],"other":[282],"that":[284],"use":[285],"VGG-based":[286],"encoders":[288],"without":[289],"fine-tuning.":[290]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}