{"id":"https://openalex.org/W3089780482","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206644","title":"Improving Diversity and Reducing Redundancy in Paragraph Captions","display_name":"Improving Diversity and Reducing Redundancy in Paragraph Captions","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3089780482","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206644","mag":"3089780482"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9206644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/A5063184018","display_name":"Chandresh S. Kanani","orcid":null},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chandresh S. Kanani","raw_affiliation_strings":["Department of CSE, Indian Institute of Technology, Patna, Patna, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CSE, Indian Institute of Technology, Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060797340","display_name":"Sriparna Saha","orcid":"https://orcid.org/0000-0001-5458-9381"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriparna Saha","raw_affiliation_strings":["Department of CSE, Indian Institute of Technology, Patna, Patna, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CSE, Indian Institute of Technology, Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065100828","display_name":"Pushpak Bhattacharyya","orcid":"https://orcid.org/0000-0001-5319-5508"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pushpak Bhattacharyya","raw_affiliation_strings":["Department of CSE, Indian Institute of Technology, Patna, Patna, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CSE, Indian Institute of Technology, Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I132153292"],"apc_list":null,"apc_paid":null,"fwci":0.2937,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.57371217,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.991599977016449,"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/T10028","display_name":"Topic Modeling","score":0.9747999906539917,"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":0.9729981422424316},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.8400297164916992},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.826675295829773},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.627449095249176},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6182459592819214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5910487174987793},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5623764991760254},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5556636452674866},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5254494547843933},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5108737349510193},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47310781478881836},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.429551362991333},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18611007928848267}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9729981422424316},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.8400297164916992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.826675295829773},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.627449095249176},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6182459592819214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5910487174987793},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5623764991760254},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5556636452674866},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5254494547843933},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5108737349510193},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47310781478881836},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.429551362991333},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18611007928848267},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9206644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7400000095367432,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W658020064","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2125101937","https://openalex.org/W2154652894","https://openalex.org/W2163380389","https://openalex.org/W2176263492","https://openalex.org/W2441124914","https://openalex.org/W2539033431","https://openalex.org/W2549599535","https://openalex.org/W2605045867","https://openalex.org/W2737766105","https://openalex.org/W2890781596","https://openalex.org/W2951684117","https://openalex.org/W2963084599","https://openalex.org/W2963248296","https://openalex.org/W6621906925","https://openalex.org/W6678262379","https://openalex.org/W6685322675","https://openalex.org/W6740863234","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W2366944513"],"abstract_inverted_index":{"The":[0,32,47,71],"purpose":[1],"of":[2,13,64],"an":[3,93],"image":[4,29,49,76],"paragraph":[5,18,57],"captioning":[6,19,30,50,58,77],"model":[7,122],"is":[8,34,42],"to":[9,26,61,134],"produce":[10,52],"detailed":[11],"descriptions":[12],"the":[14,27,40,56,62,67,100,129,137],"source":[15],"images.":[16],"Generally,":[17],"models":[20,51,78],"use":[21],"encoder-decoder":[22],"based":[23,37],"architectures":[24],"similar":[25],"standard":[28,48,75],"models.":[31],"encoder":[33],"a":[35,43,120],"CNN":[36],"model,":[38],"and":[39,83,104],"decoder":[41],"LSTM":[44],"or":[45],"GRU.":[46],"unsatisfactory":[53],"results":[54],"for":[55,98,112,136],"task":[59],"due":[60],"lack":[63,79],"diversity":[65,82,101],"in":[66,80,102],"generated":[68,73],"outputs":[69],"[9].":[70],"paragraphs":[72],"from":[74,132],"language":[81,96],"contain":[84],"redundant":[85,114],"information.":[86,115],"In":[87],"this":[88,117],"work,":[89],"we":[90,126],"have":[91,127],"proposed":[92],"approach":[94,118],"with":[95,119],"discriminator":[97],"increasing":[99],"language,":[103],"dissimilarity":[105],"score":[106,131],"using":[107],"word":[108],"mover's":[109],"distance":[110],"[4]":[111],"reducing":[113],"Using":[116],"state-of-the-art":[121],"at":[123],"testing":[124],"time,":[125],"improved":[128],"METEOR":[130],"13.63":[133],"19.01":[135],"Visual":[138],"Genome":[139],"dataset.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}