{"id":"https://openalex.org/W2896233503","doi":"https://doi.org/10.1109/bigmm.2018.8499172","title":"Enhanced Text-Guided Attention Model for Image Captioning","display_name":"Enhanced Text-Guided Attention Model for Image Captioning","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2896233503","doi":"https://doi.org/10.1109/bigmm.2018.8499172","mag":"2896233503"},"language":"en","primary_location":{"id":"doi:10.1109/bigmm.2018.8499172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigmm.2018.8499172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM)","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/A5025436570","display_name":"Yuanen Zhou","orcid":"https://orcid.org/0000-0002-4986-3611"},"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":"Yuanen Zhou","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/A5019101619","display_name":"Ye Zhac","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":false,"raw_author_name":"Ye Zhac","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/A5101993173","display_name":"Xueliang Liu","orcid":"https://orcid.org/0000-0003-0077-9715"},"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":"Xueliang Liu","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":5,"corresponding_author_ids":["https://openalex.org/A5025436570"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.4178,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67500091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"14","issue":null,"first_page":"1","last_page":"5"},"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":0.9955999851226807,"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":0.9914000034332275,"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":0.9750878810882568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8473556041717529},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.7006044387817383},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6381416320800781},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6178326606750488},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5995522141456604},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5939938426017761},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5901385545730591},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5750569701194763},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.5657561421394348},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.49525371193885803},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.49342218041419983},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.45336630940437317},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.419575959444046},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3348565697669983},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33056068420410156}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9750878810882568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8473556041717529},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.7006044387817383},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6381416320800781},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6178326606750488},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5995522141456604},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5939938426017761},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5901385545730591},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5750569701194763},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5657561421394348},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.49525371193885803},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49342218041419983},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.45336630940437317},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.419575959444046},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3348565697669983},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33056068420410156},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigmm.2018.8499172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigmm.2018.8499172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W825973156","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1706899115","https://openalex.org/W1785460851","https://openalex.org/W1811254738","https://openalex.org/W1858383477","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2119717200","https://openalex.org/W2131179926","https://openalex.org/W2133459682","https://openalex.org/W2133564696","https://openalex.org/W2149172860","https://openalex.org/W2176091656","https://openalex.org/W2194775991","https://openalex.org/W2254252455","https://openalex.org/W2302086703","https://openalex.org/W2404394533","https://openalex.org/W2552161745","https://openalex.org/W2565165987","https://openalex.org/W2604729005","https://openalex.org/W2613718673","https://openalex.org/W2734241621","https://openalex.org/W2737766105","https://openalex.org/W2953022248","https://openalex.org/W2953106684","https://openalex.org/W2962706528","https://openalex.org/W2962935746","https://openalex.org/W2962982762","https://openalex.org/W2963084599","https://openalex.org/W2963758027","https://openalex.org/W2964018924","https://openalex.org/W2964308564","https://openalex.org/W4230563027","https://openalex.org/W4293501525"],"related_works":["https://openalex.org/W2368824897","https://openalex.org/W2221419418","https://openalex.org/W1508050556","https://openalex.org/W1910862367","https://openalex.org/W2379365082","https://openalex.org/W2370747590","https://openalex.org/W4283822356","https://openalex.org/W2030109976","https://openalex.org/W1950940422","https://openalex.org/W2369260257"],"abstract_inverted_index":{"Attention":[0],"mechanism":[1,103],"plays":[2],"an":[3],"important":[4],"role":[5],"in":[6,13,36],"understanding":[7],"images":[8],"and":[9,59,105,131,156],"demonstrates":[10],"its":[11],"effectiveness":[12],"generating":[14],"natural":[15],"language":[16],"descriptions":[17],"of":[18,26,127],"images.":[19,71],"In":[20],"recent":[21],"years,":[22],"with":[23,107],"the":[24,37,43,64,73,83,87,101,138,167],"advance":[25],"deep":[27],"neural":[28,39],"networks,":[29],"visual":[30,76],"attention":[31,77,97,102,112,117,134,142,159,172],"has":[32,78],"been":[33,79],"well":[34,80],"exploited":[35,81],"encoder-decoder":[38],"network-based":[40],"framework.":[41],"On":[42,72],"one":[44],"hand,":[45,75],"existing":[46],"study":[47],"shows":[48],"that":[49],"guidance":[50],"captions":[51],"can":[52],"help":[53],"attend":[54],"to":[55,110,143,152],"relevant":[56],"image":[57,65,122,148,175],"regions":[58],"suppress":[60],"unimportant":[61],"ones":[62],"during":[63,82],"encoding":[66],"stage,":[67],"especially":[68],"for":[69,174],"cluttered":[70],"other":[74],"decoding":[84],"stage.":[85],"Observing":[86],"naturally":[88],"complementary":[89],"property":[90],"between":[91],"them,":[92],"we":[93],"propose":[94],"a":[95,108],"two-side":[96],"model":[98,118,173],"which":[99,124,150],"combines":[100],"seamlessly":[104],"associated":[106],"coarse":[109],"fine":[111],"mechanism.":[113],"The":[114],"original":[115],"text-guided":[116,171],"operates":[119],"on":[120,163,170],"region-level":[121],"feature,":[123,149],"is":[125],"lack":[126],"definite":[128],"semantic":[129],"information":[130],"causes":[132],"unsatisfied":[133],"visualization.":[135,160],"We":[136],"alleviate":[137],"problem":[139],"by":[140],"enabling":[141],"be":[144],"calculated":[145],"at":[146],"object-level":[147],"helps":[151],"obtain":[153],"performance":[154],"improvement":[155,169],"more":[157],"interpretable":[158],"Experiments":[161],"conducted":[162],"MSCOCO":[164],"datasets":[165],"demonstrate":[166],"consistent":[168],"captioning.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}