{"id":"https://openalex.org/W3186617021","doi":"https://doi.org/10.3390/jimaging7080125","title":"On the Limitations of Visual-Semantic Embedding Networks for Image-to-Text Information Retrieval","display_name":"On the Limitations of Visual-Semantic Embedding Networks for Image-to-Text Information Retrieval","publication_year":2021,"publication_date":"2021-07-26","ids":{"openalex":"https://openalex.org/W3186617021","doi":"https://doi.org/10.3390/jimaging7080125","mag":"3186617021","pmid":"https://pubmed.ncbi.nlm.nih.gov/34460761"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging7080125","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging7080125","pdf_url":"https://www.mdpi.com/2313-433X/7/8/125/pdf?version=1627280360","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2313-433X/7/8/125/pdf?version=1627280360","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074385870","display_name":"Yan Gong","orcid":"https://orcid.org/0000-0003-2853-2108"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yan Gong","raw_affiliation_strings":["Department of Computer Science, School of Science, Loughborough University, Loughborough LE11 3TT, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Science, Loughborough University, Loughborough LE11 3TT, UK","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022173527","display_name":"Georgina Cosma","orcid":"https://orcid.org/0000-0002-4663-6907"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Georgina Cosma","raw_affiliation_strings":["Department of Computer Science, School of Science, Loughborough University, Loughborough LE11 3TT, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Science, Loughborough University, Loughborough LE11 3TT, UK","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046565976","display_name":"Hui Fang","orcid":"https://orcid.org/0000-0001-9365-7420"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hui Fang","raw_affiliation_strings":["Department of Computer Science, School of Science, Loughborough University, Loughborough LE11 3TT, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Science, Loughborough University, Loughborough LE11 3TT, UK","institution_ids":["https://openalex.org/I143804889"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022173527","https://openalex.org/A5074385870"],"corresponding_institution_ids":["https://openalex.org/I143804889"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":1.1652,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.80688318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"7","issue":"8","first_page":"125","last_page":"125"},"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":0.9977999925613403,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9927999973297119,"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/computer-science","display_name":"Computer science","score":0.8513999581336975},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6868077516555786},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.655290961265564},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5996248126029968},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5892589688301086},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5227327942848206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5195796489715576},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.5012862682342529},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4459291398525238},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4425819218158722},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4356456995010376},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.42980819940567017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8513999581336975},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6868077516555786},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.655290961265564},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5996248126029968},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5892589688301086},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5227327942848206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5195796489715576},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.5012862682342529},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4459291398525238},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4425819218158722},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4356456995010376},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.42980819940567017},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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":7,"locations":[{"id":"doi:10.3390/jimaging7080125","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging7080125","pdf_url":"https://www.mdpi.com/2313-433X/7/8/125/pdf?version=1627280360","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:34460761","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34460761","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of imaging","raw_type":null},{"id":"pmh:oai:eprints.bournemouth.ac.uk:40888","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400187","display_name":"Bournemouth University Research Online (Bournemouth University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9300472","host_organization_name":"Bournemouth University","host_organization_lineage":["https://openalex.org/I9300472"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:doaj.org/article:d970e3f10d5e4e3eacc6f610ae8c8bb5","is_oa":true,"landing_page_url":"https://doaj.org/article/d970e3f10d5e4e3eacc6f610ae8c8bb5","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 7, Iss 8, p 125 (2021)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:7439008","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC8404943","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"Text"},{"id":"pmh:oai:figshare.com:article/15059793","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/On_the_limitations_of_visual-semantic_embedding_networks_for_image-to-text_information_retrieval/15059793","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8404943","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8404943","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Imaging","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/jimaging7080125","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging7080125","pdf_url":"https://www.mdpi.com/2313-433X/7/8/125/pdf?version=1627280360","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3186617021.pdf","grobid_xml":"https://content.openalex.org/works/W3186617021.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W2109586012","https://openalex.org/W2157331557","https://openalex.org/W2163605009","https://openalex.org/W2185175083","https://openalex.org/W2186222003","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2317486713","https://openalex.org/W2519887557","https://openalex.org/W2560730294","https://openalex.org/W2618530766","https://openalex.org/W2774267535","https://openalex.org/W2803259101","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2962964995","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W3088460296","https://openalex.org/W3090449556","https://openalex.org/W4213009331","https://openalex.org/W6676497082","https://openalex.org/W6684191040","https://openalex.org/W6699544537","https://openalex.org/W6766970537"],"related_works":["https://openalex.org/W2123147980","https://openalex.org/W2066590080","https://openalex.org/W2076842684","https://openalex.org/W1539573266","https://openalex.org/W4387423606","https://openalex.org/W2513891871","https://openalex.org/W2187873862","https://openalex.org/W2918350319","https://openalex.org/W3101846449","https://openalex.org/W2396850383"],"abstract_inverted_index":{"Visual-semantic":[0],"embedding":[1,16],"(VSE)":[2],"networks":[3,39,54,184,195],"create":[4],"joint":[5],"image-text":[6,26,126],"representations":[7],"to":[8,18,69,141,185],"map":[9],"images":[10],"and":[11,30,44,61,63,67,105,110,153,169,180],"texts":[12],"in":[13],"a":[14,135],"shared":[15],"space":[17],"enable":[19],"various":[20],"information":[21,198],"retrieval-related":[22],"tasks,":[23],"such":[24],"as":[25],"retrieval,":[27],"image":[28,163,165,167],"captioning,":[29],"visual":[31],"question":[32],"answering.":[33],"The":[34,76,100],"most":[35],"recent":[36],"state-of-the-art":[37],"VSE-based":[38],"are:":[40],"VSE++,":[41,106],"SCAN,":[42,104],"VSRN,":[43,103],"UNITER.":[45,154],"This":[46,175],"study":[47],"evaluates":[48],"the":[49,56,74,83,93,117,129,138,143,146,149,160,178,190],"performance":[50,147],"of":[51,58,95,137,145,148,162,172,182,192],"those":[52],"VSE":[53,183,194],"for":[55,92,116,196],"task":[57,94],"image-to-text":[59],"retrieval":[60,199],"identifies":[62],"analyses":[64],"their":[65],"strengths":[66,179],"limitations":[68,144,156,181],"guide":[70,186],"future":[71],"research":[72,188],"on":[73,79,89,112,125],"topic.":[75],"experimental":[77],"results":[78],"Flickr30K":[80],"revealed":[81],"that":[82],"pre-trained":[84],"network,":[85],"UNITER,":[86],"achieved":[87,107],"61.5%":[88],"average":[90,113],"Recall@5":[91],"retrieving":[96],"all":[97],"relevant":[98],"descriptions.":[99],"traditional":[101],"networks,":[102],"50.3%,":[108],"47.1%,":[109],"29.4%":[111],"Recall@5,":[114],"respectively,":[115],"same":[118],"task.":[119],"An":[120],"additional":[121],"analysis":[122],"was":[123],"performed":[124],"pairs":[127],"from":[128,159],"top":[130],"25":[131],"worst-performing":[132],"classes":[133],"using":[134,193],"subset":[136],"Flickr30K-based":[139],"dataset":[140],"identify":[142],"best-performing":[150],"models,":[151],"VSRN":[152],"These":[155],"are":[157],"discussed":[158],"perspective":[161],"scenes,":[164],"objects,":[166],"semantics,":[168],"basic":[170],"functions":[171],"neural":[173],"networks.":[174],"paper":[176],"discusses":[177],"further":[187],"into":[189],"topic":[191],"cross-modal":[197],"tasks.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
