{"id":"https://openalex.org/W4394841762","doi":"https://doi.org/10.1109/tvcg.2024.3388514","title":"Visual Analytics for Efficient Image Exploration and User-Guided Image Captioning","display_name":"Visual Analytics for Efficient Image Exploration and User-Guided Image Captioning","publication_year":2024,"publication_date":"2024-04-16","ids":{"openalex":"https://openalex.org/W4394841762","doi":"https://doi.org/10.1109/tvcg.2024.3388514","pmid":"https://pubmed.ncbi.nlm.nih.gov/38625780"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2024.3388514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2024.3388514","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"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 Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11412260/pdf/nihms-2003834.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100427534","display_name":"Yiran Li","orcid":"https://orcid.org/0000-0001-5204-4935"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yiran Li","raw_affiliation_strings":["University of California, Davis, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669433","display_name":"Junpeng Wang","orcid":"https://orcid.org/0000-0002-1130-9914"},"institutions":[{"id":"https://openalex.org/I4210148469","display_name":"Visa (United States)","ror":"https://ror.org/05t1y0b59","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junpeng Wang","raw_affiliation_strings":["Visa Research, Foster City, CA, USA"],"affiliations":[{"raw_affiliation_string":"Visa Research, Foster City, CA, USA","institution_ids":["https://openalex.org/I4210148469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054968503","display_name":"Prince Aboagye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148469","display_name":"Visa (United States)","ror":"https://ror.org/05t1y0b59","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prince Aboagye","raw_affiliation_strings":["Visa Research, Foster City, CA, USA"],"affiliations":[{"raw_affiliation_string":"Visa Research, Foster City, CA, USA","institution_ids":["https://openalex.org/I4210148469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011045620","display_name":"Chin\u2010Chia Michael Yeh","orcid":"https://orcid.org/0000-0002-9807-2963"},"institutions":[{"id":"https://openalex.org/I4210148469","display_name":"Visa (United States)","ror":"https://ror.org/05t1y0b59","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Chia Michael Yeh","raw_affiliation_strings":["Visa Research, Foster City, CA, USA"],"affiliations":[{"raw_affiliation_string":"Visa Research, Foster City, CA, USA","institution_ids":["https://openalex.org/I4210148469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109988926","display_name":"Yan Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148469","display_name":"Visa (United States)","ror":"https://ror.org/05t1y0b59","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Zheng","raw_affiliation_strings":["Visa Research, Foster City, CA, USA"],"affiliations":[{"raw_affiliation_string":"Visa Research, Foster City, CA, USA","institution_ids":["https://openalex.org/I4210148469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602506","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5224-8647"},"institutions":[{"id":"https://openalex.org/I4210148469","display_name":"Visa (United States)","ror":"https://ror.org/05t1y0b59","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["Visa Research, Foster City, CA, USA"],"affiliations":[{"raw_affiliation_string":"Visa Research, Foster City, CA, USA","institution_ids":["https://openalex.org/I4210148469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100830966","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0003-4020-2259"},"institutions":[{"id":"https://openalex.org/I4210148469","display_name":"Visa (United States)","ror":"https://ror.org/05t1y0b59","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Visa Research, Foster City, CA, USA"],"affiliations":[{"raw_affiliation_string":"Visa Research, Foster City, CA, USA","institution_ids":["https://openalex.org/I4210148469"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037161857","display_name":"Kwan\u2010Liu Ma","orcid":"https://orcid.org/0000-0001-8086-0366"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kwan-Liu Ma","raw_affiliation_strings":["University of California, Davis, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100427534"],"corresponding_institution_ids":["https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":2.9914,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.92224424,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"30","issue":"6","first_page":"2875","last_page":"2887"},"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":0.9901999831199646,"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":0.9891999959945679,"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/closed-captioning","display_name":"Closed captioning","score":0.9120818376541138},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8508849740028381},{"id":"https://openalex.org/keywords/visual-analytics","display_name":"Visual analytics","score":0.6857172250747681},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6778804063796997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4696919918060303},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.46065470576286316},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4568849205970764},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4405042827129364},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.42558401823043823},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4119079113006592},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41060903668403625},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3664858937263489},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36447906494140625},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3517643213272095}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9120818376541138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8508849740028381},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.6857172250747681},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6778804063796997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4696919918060303},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.46065470576286316},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4568849205970764},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4405042827129364},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.42558401823043823},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4119079113006592},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41060903668403625},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3664858937263489},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36447906494140625},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3517643213272095},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tvcg.2024.3388514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2024.3388514","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"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 Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:38625780","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38625780","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":"IEEE transactions on visualization and computer graphics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11412260","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11412260","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11412260/pdf/nihms-2003834.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Trans Vis Comput Graph","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:11412260","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11412260","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11412260/pdf/nihms-2003834.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Trans Vis Comput Graph","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5460739416","display_name":null,"funder_award_id":"P41 EB032840","funder_id":"https://openalex.org/F4320337363","funder_display_name":"National Institute of Biomedical Imaging and Bioengineering"}],"funders":[{"id":"https://openalex.org/F4320337363","display_name":"National Institute of Biomedical Imaging and Bioengineering","ror":"https://ror.org/00372qc85"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394841762.pdf","grobid_xml":"https://content.openalex.org/works/W4394841762.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1508404128","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2117539524","https://openalex.org/W2133564696","https://openalex.org/W2251512949","https://openalex.org/W2282821441","https://openalex.org/W2512274390","https://openalex.org/W2553981914","https://openalex.org/W2751746637","https://openalex.org/W2803808737","https://openalex.org/W2892051885","https://openalex.org/W2896457183","https://openalex.org/W2950784811","https://openalex.org/W2962858109","https://openalex.org/W2963123635","https://openalex.org/W2969224142","https://openalex.org/W2969980980","https://openalex.org/W2973221207","https://openalex.org/W2996005046","https://openalex.org/W3021565519","https://openalex.org/W3025713681","https://openalex.org/W3093452197","https://openalex.org/W3094617751","https://openalex.org/W3108010663","https://openalex.org/W3149637534","https://openalex.org/W3175479236","https://openalex.org/W3186479087","https://openalex.org/W3202452289","https://openalex.org/W3203358361","https://openalex.org/W3204602149","https://openalex.org/W3204925778","https://openalex.org/W4200283487","https://openalex.org/W4205342995","https://openalex.org/W4206706211","https://openalex.org/W4223519356","https://openalex.org/W4225557928","https://openalex.org/W4225792990","https://openalex.org/W4226020779","https://openalex.org/W4226038327","https://openalex.org/W4226253248","https://openalex.org/W4281956361","https://openalex.org/W4297459897","https://openalex.org/W4298326701","https://openalex.org/W4312791030","https://openalex.org/W4360995299","https://openalex.org/W4384918448","https://openalex.org/W4385245566","https://openalex.org/W4385565405","https://openalex.org/W4387801427","https://openalex.org/W4387934929","https://openalex.org/W4387966251","https://openalex.org/W4390874575","https://openalex.org/W4391128914","https://openalex.org/W6620707391","https://openalex.org/W6679434410","https://openalex.org/W6730169232","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6811013733","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W2186032312","https://openalex.org/W2158984754","https://openalex.org/W3149127250","https://openalex.org/W2564956852","https://openalex.org/W4246764483","https://openalex.org/W2126824079","https://openalex.org/W2143428259","https://openalex.org/W4378086562","https://openalex.org/W2112083262","https://openalex.org/W4389880955"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,8,116],"pre-trained":[3,113],"language-image":[4,70,114],"models":[5,71,115],"have":[6,132],"ushered":[7],"a":[9,136],"new":[10],"era":[11],"of":[12,18,29,36,42,50,55,112,145,154],"visual":[13,30,82,103,138,146],"comprehension.":[14],"Leveraging":[15],"the":[16,27,33,48,60,66,81,92,95,100,110,142,152,155],"power":[17],"these":[19],"models,":[20],"this":[21],"article":[22],"tackles":[23],"two":[24,130],"issues":[25],"within":[26,45,91],"realm":[28],"analytics:":[31],"(1)":[32],"efficient":[34],"exploration":[35],"large-scale":[37,165],"image":[38,51,74,166],"datasets":[39],"and":[40,53,105,120,147],"identification":[41],"data":[43,85],"biases":[44,86],"them;":[46],"(2)":[47],"evaluation":[49],"captions":[52,67],"steering":[54],"their":[56,117],"generation":[57],"process.":[58],"On":[59,94],"one":[61],"hand,":[62,97],"by":[63,98],"visually":[64],"examining":[65],"generated":[68],"from":[69],"for":[72],"an":[73,122],"dataset,":[75],"we":[76,108],"gain":[77],"deeper":[78],"insights":[79],"into":[80,135],"contents,":[83],"unearthing":[84],"that":[87],"may":[88],"be":[89],"entrenched":[90],"dataset.":[93],"other":[96],"depicting":[99],"association":[101],"between":[102],"features":[104],"textual":[106,148],"captions,":[107],"expose":[109],"weaknesses":[111],"captioning":[118],"capability":[119],"propose":[121],"interactive":[123],"interface":[124],"to":[125],"steer":[126],"caption":[127],"generation.":[128],"The":[129],"parts":[131],"been":[133],"coalesced":[134],"coordinated":[137],"analytics":[139],"system,":[140],"fostering":[141],"mutual":[143],"enrichment":[144],"contents.":[149],"We":[150],"validate":[151],"effectiveness":[153],"system":[156],"with":[157,164],"domain":[158],"practitioners":[159],"through":[160],"concrete":[161],"case":[162],"studies":[163],"datasets.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}
