{"id":"https://openalex.org/W4391620834","doi":"https://doi.org/10.1109/mmul.2024.3363429","title":"Image-Relevant Entities Knowledge-Aware News Image Captioning","display_name":"Image-Relevant Entities Knowledge-Aware News Image Captioning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391620834","doi":"https://doi.org/10.1109/mmul.2024.3363429"},"language":"en","primary_location":{"id":"doi:10.1109/mmul.2024.3363429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2024.3363429","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 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/A5000670218","display_name":"Sonali Ajankar","orcid":"https://orcid.org/0000-0001-9608-7101"},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sonali Ajankar","raw_affiliation_strings":["Indian Institute of Technology, Varanasi, 221005, India"],"raw_orcid":"https://orcid.org/0000-0001-9608-7101","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Varanasi, 221005, India","institution_ids":["https://openalex.org/I56404289"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088215863","display_name":"Tanima Dutta","orcid":"https://orcid.org/0000-0002-2801-0687"},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tanima Dutta","raw_affiliation_strings":["Indian Institute of Technology, Varanasi, 221005, India"],"raw_orcid":"https://orcid.org/0000-0002-2801-0687","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Varanasi, 221005, India","institution_ids":["https://openalex.org/I56404289"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6562,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66432817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"31","issue":"1","first_page":"88","last_page":"98"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9969000220298767,"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":0.9968000054359436,"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":0.952461838722229},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8952046036720276},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6535977125167847},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5985299348831177},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5817391872406006},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5802368521690369},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5729278922080994},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5225909948348999},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4644847512245178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.374409556388855},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.16967415809631348},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12938565015792847},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08210694789886475}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.952461838722229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8952046036720276},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6535977125167847},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5985299348831177},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5817391872406006},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5802368521690369},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5729278922080994},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5225909948348999},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4644847512245178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.374409556388855},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.16967415809631348},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12938565015792847},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08210694789886475},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmul.2024.3363429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2024.3363429","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 MultiMedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2096733369","https://openalex.org/W2308864855","https://openalex.org/W2341528187","https://openalex.org/W2493916176","https://openalex.org/W2783914607","https://openalex.org/W2964029788","https://openalex.org/W2965373594","https://openalex.org/W2982573303","https://openalex.org/W3033767380","https://openalex.org/W3034689697","https://openalex.org/W3101998545","https://openalex.org/W3183226462","https://openalex.org/W3211405508","https://openalex.org/W4205428821","https://openalex.org/W4206675125","https://openalex.org/W4304080167","https://openalex.org/W4309576667","https://openalex.org/W4385245566","https://openalex.org/W4385570224","https://openalex.org/W4385574482","https://openalex.org/W6766673545"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"News":[0,93],"Image":[1,94],"Captioning":[2,95],"(NIC)":[3],"generates":[4],"entity-rich":[5],"captions":[6,151],"for":[7,119],"news":[8,11,42],"images":[9,43],"via":[10],"article":[12,55],"context.":[13],"It":[14],"effectively":[15],"conveys":[16],"information":[17,33,51],"to":[18,61,73,103,174],"a":[19,53,57,153,167],"broad":[20],"audience.":[21],"However,":[22],"it":[23],"inherits":[24],"various":[25],"challenges,":[26],"like":[27],"the":[28,39,45,62,69,83,88,105,108,111,121,126,137,175,178],"presence":[29],"of":[30,107,141,147,169],"abstract":[31],"semantic":[32],"based":[34],"on":[35,177],"named":[36],"entities":[37,133,138,148],"deteriorates":[38],"relation":[40,64],"between":[41,65,77],"and":[44,79,171,180],"article.":[46],"In":[47],"addition,":[48],"finding":[49],"valuable":[50],"in":[52,135,156,163],"lengthy":[54],"is":[56],"critical":[58],"task.":[59],"Due":[60],"ambiguous":[63],"an":[66,161],"image":[67],"article,":[68],"existing":[70],"works":[71],"struggle":[72],"exploit":[74],"multimodal":[75],"clues":[76],"text":[78],"images.":[80],"To":[81],"alleviate":[82],"above-mentioned":[84],"limitations,":[85],"we":[86],"proposed":[87],"Image-relevant":[89,127],"Entities":[90,122,128],"Knowledge":[91,123],"aware":[92],"novel":[96],"framework":[97],"known":[98],"as":[99],"IEK-NIC.":[100],"We":[101],"propose":[102],"tweak":[104],"output":[106],"model":[109],"using":[110],"Time-step-bounded":[112],"Entity":[113],"Constrained":[114],"beam":[115],"search":[116],"(TEC)":[117],"algorithm":[118],"incorporating":[120,136],"produced":[124],"by":[125,166],"Generation":[129],"(IEG)":[130],"method.":[131],"Constraining":[132],"assist":[134],"made":[139],"up":[140],"multiple":[142],"tokens.":[143],"The":[144],"efficient":[145],"usage":[146],"while":[149],"generating":[150],"plays":[152],"crucial":[154],"role":[155],"enhancing":[157],"performance.":[158],"IEK-NIC":[159],"shows":[160],"improvement":[162],"CIDEr":[164],"score":[165],"margin":[168],"1.46":[170],"1.49":[172],"compared":[173],"state-of-the-art":[176],"GoodNews":[179],"NYTimes800K":[181],"datasets,":[182],"respectively.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}