{"id":"https://openalex.org/W4293731196","doi":"https://doi.org/10.1109/tmm.2022.3202690","title":"Image Captioning With Novel Topics Guidance and Retrieval-Based Topics Re-Weighting","display_name":"Image Captioning With Novel Topics Guidance and Retrieval-Based Topics Re-Weighting","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4293731196","doi":"https://doi.org/10.1109/tmm.2022.3202690"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3202690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3202690","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067972997","display_name":"Majjed Al-Qatf","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Majjed Al-Qatf","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1796-344X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100742230","display_name":"Xingfu Wang","orcid":"https://orcid.org/0000-0002-1301-3535"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingfu Wang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1301-3535","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089032960","display_name":"Ammar Hawbani","orcid":"https://orcid.org/0000-0002-1069-3993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ammar Hawbani","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1069-3993","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057083285","display_name":"Amr Abdussalam","orcid":"https://orcid.org/0000-0001-9426-3415"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Amr Abdussalam","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9426-3415","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012786887","display_name":"Saeed Hamood Alsamhi","orcid":"https://orcid.org/0000-0003-2857-6979"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]},{"id":"https://openalex.org/I78137547","display_name":"Ibb University","ror":"https://ror.org/00fhcxc56","country_code":"YE","type":"education","lineage":["https://openalex.org/I78137547"]}],"countries":["IE","YE"],"is_corresponding":false,"raw_author_name":"Saeed Hammod Alsamhi","raw_affiliation_strings":["Insight Centre for Data Analytics, National University of Ireland, Galway, Ireland","IBB University, Ibb, Yemen"],"raw_orcid":"https://orcid.org/0000-0003-2857-6979","affiliations":[{"raw_affiliation_string":"Insight Centre for Data Analytics, National University of Ireland, Galway, Ireland","institution_ids":["https://openalex.org/I188760350"]},{"raw_affiliation_string":"IBB University, Ibb, Yemen","institution_ids":["https://openalex.org/I78137547"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0555,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.88200528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"5984","last_page":"5999"},"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/T10028","display_name":"Topic Modeling","score":0.9936000108718872,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9926999807357788,"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":0.9877452254295349},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.844154953956604},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7664341926574707},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5957093834877014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5671339631080627},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5535611510276794},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5103389620780945},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4949890971183777},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4901634156703949},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48897016048431396},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4548112452030182},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4419749975204468},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42468133568763733},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37324604392051697}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9877452254295349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.844154953956604},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7664341926574707},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5957093834877014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5671339631080627},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5535611510276794},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5103389620780945},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4949890971183777},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4901634156703949},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48897016048431396},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4548112452030182},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4419749975204468},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42468133568763733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37324604392051697},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3202690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3202690","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1902027874","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W2024932032","https://openalex.org/W2101105183","https://openalex.org/W2101234009","https://openalex.org/W2133459682","https://openalex.org/W2154652894","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2555042572","https://openalex.org/W2558834163","https://openalex.org/W2568262903","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2754689878","https://openalex.org/W2774267535","https://openalex.org/W2808663243","https://openalex.org/W2883900035","https://openalex.org/W2884561390","https://openalex.org/W2887272576","https://openalex.org/W2893724244","https://openalex.org/W2908056713","https://openalex.org/W2932399282","https://openalex.org/W2938260698","https://openalex.org/W2950212751","https://openalex.org/W2962861647","https://openalex.org/W2962938439","https://openalex.org/W2963084599","https://openalex.org/W2965922392","https://openalex.org/W2969136062","https://openalex.org/W2974212192","https://openalex.org/W2985626746","https://openalex.org/W2990349092","https://openalex.org/W3003478339","https://openalex.org/W3009270862","https://openalex.org/W3038593179","https://openalex.org/W3039115681","https://openalex.org/W3045147787","https://openalex.org/W3080813890","https://openalex.org/W3082436432","https://openalex.org/W3093660915","https://openalex.org/W3100183449","https://openalex.org/W3106925514","https://openalex.org/W3136792391","https://openalex.org/W3188805207","https://openalex.org/W3201187808","https://openalex.org/W3211865849","https://openalex.org/W4299801216","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6638145986","https://openalex.org/W6675354045","https://openalex.org/W6682631176","https://openalex.org/W6685183736","https://openalex.org/W6747225742","https://openalex.org/W6765766786"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W3088136942","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Topic":[0],"modelling":[1],"(TM)":[2],"has":[3],"shown":[4,24],"significant":[5],"progress":[6],"in":[7,14,25,48,128,167,224,259],"boosting":[8,213],"the":[9,15,37,40,44,56,60,66,72,80,134,149,152,168,173,182,191,194,199,214,218,221,231,242,248,262],"effectiveness":[10],"of":[11,39,51,101,137,193,216,261],"image":[12,28,87,97,153,195,244,256],"captioning":[13,29,68,81,98,257],"last":[16],"few":[17],"years.":[18],"Although":[19],"important":[20],"improvements":[21],"have":[22],"been":[23],"previous":[26],"topic-guided":[27],"models,":[30,202],"some":[31],"challenges":[32],"remain":[33],"unsolved,":[34],"such":[35],"as":[36],"independence":[38],"topic":[41,62,105,114,159,249],"predictors":[42],"and":[43,117,123,155,210,233,247,252],"sentence":[45],"generators,":[46],"resulting":[47],"ineffective":[49],"exploitation":[50],"semantic":[52],"information.":[53],"Also,":[54],"all":[55],"predicted":[57,175],"topics":[58,109,138,142,150,174,187,219],"or":[59],"top-one":[61],"are":[63,126],"used":[64],"throughout":[65],"whole":[67],"task":[69],"without":[70],"considering":[71],"current":[73],"time":[74,145,180,226],"step's":[75],"linguistic":[76],"context,":[77],"which":[78],"deviates":[79],"network":[82],"to":[83,132,189],"focus":[84],"on":[85,230],"inaccurate":[86],"objects.":[88],"To":[89],"tackle":[90],"these":[91],"challenges,":[92],"we":[93],"propose":[94],"a":[95],"novel":[96],"method":[99,240],"consisting":[100],"four":[102],"modules:":[103],"enhanced":[104,157],"predictor":[106,115],"(ETP),":[107],"retrieval-based":[108],"re-weighting":[110,172],"module":[111],"(RTR),":[112],"subsequent":[113],"(STP),":[116],"caption":[118],"generation":[119,124],"module.":[120],"The":[121,162],"prediction":[122,250],"modules":[125],"trained":[127],"an":[129],"end-to-end":[130],"manner":[131],"promote":[133],"efficient":[135],"use":[136],"by":[139,176],"predicting":[140],"suitable":[141],"at":[143],"each":[144,179,225],"step.":[146,227],"ETP":[147],"predicts":[148,185],"using":[151],"features,":[154],"is":[156,164],"with":[158,198],"embedding":[160],"(TE).":[161],"RTR":[163],"only":[165],"applied":[166],"testing":[169],"stage":[170],"for":[171],"ETP.":[177],"In":[178],"step,":[181],"STP":[183],"automatically":[184,206],"concise":[186],"subsets":[188],"alleviate":[190],"diversity":[192],"topics.":[196],"Compared":[197],"existing":[200],"topic-based":[201],"our":[203,239],"model":[204],"can":[205],"generate":[207],"more":[208],"accurate":[209],"diverse":[211],"captions,":[212],"explainability":[215],"how":[217],"influence":[220],"generated":[222],"word":[223],"Extensive":[228],"experiments":[229],"MS-COCO":[232],"Flickr30K":[234],"benchmark":[235],"datasets":[236],"show":[237],"that":[238],"enhances":[241],"overall":[243],"captioning's":[245],"performance":[246],"task,":[251],"outperforms":[253],"many":[254],"recent":[255],"approaches":[258],"terms":[260],"evaluation":[263],"metrics.":[264]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}