{"id":"https://openalex.org/W3118205815","doi":"https://doi.org/10.18653/v1/2020.coling-main.176","title":"Image Caption Generation for News Articles","display_name":"Image Caption Generation for News Articles","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3118205815","doi":"https://doi.org/10.18653/v1/2020.coling-main.176","mag":"3118205815"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.coling-main.176","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.176","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.176.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/2020.coling-main.176.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062273504","display_name":"Zhishen Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Zhishen Yang","raw_affiliation_strings":["Tokyo Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066940046","display_name":"Naoaki Okazaki","orcid":"https://orcid.org/0000-0001-7635-6175"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoaki Okazaki","raw_affiliation_strings":["Tokyo Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5062273504"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.4907,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.67450382,"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":"1941","last_page":"1951"},"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":0.9966999888420105,"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":0.9962000250816345,"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":0.9813651442527771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8404310941696167},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5897167921066284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.540721595287323},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5317275524139404},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.531489372253418},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5010185241699219},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42954084277153015},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3327496647834778},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33039379119873047}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9813651442527771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8404310941696167},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5897167921066284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.540721595287323},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5317275524139404},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.531489372253418},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5010185241699219},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42954084277153015},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3327496647834778},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33039379119873047},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2020.coling-main.176","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.176","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.176.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0004678960","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100835576","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 28th International Conference on Computational Linguistics (COLING2020)","raw_type":"conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.coling-main.176","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.176","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.176.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320335839","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3118205815.pdf","grobid_xml":"https://content.openalex.org/works/W3118205815.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2095705004","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2133459682","https://openalex.org/W2156830856","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2308864855","https://openalex.org/W2506483933","https://openalex.org/W2555042572","https://openalex.org/W2604729005","https://openalex.org/W2732026016","https://openalex.org/W2752172973","https://openalex.org/W2806887946","https://openalex.org/W2933138175","https://openalex.org/W2941599692","https://openalex.org/W2945260553","https://openalex.org/W2963250244","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2970971581","https://openalex.org/W2971246534","https://openalex.org/W2971274815","https://openalex.org/W2982573303","https://openalex.org/W4295312788","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757"],"abstract_inverted_index":{"In":[0,105],"this":[1],"paper,":[2],"we":[3,107],"address":[4],"the":[5,18,32,98,102,116],"task":[6,27],"of":[7,14,42,118],"news-image":[8,88,119],"captioning,":[9,35],"which":[10],"generates":[11],"a":[12,39,48,67],"description":[13],"an":[15,80],"image":[16,19,34,43,55],"given":[17],"and":[20,44,54,57,75],"its":[21],"article":[22,81],"body":[23],"as":[24],"input.":[25],"This":[26],"is":[28],"more":[29],"challenging":[30],"than":[31],"conventional":[33],"because":[36],"it":[37],"requires":[38],"joint":[40],"understanding":[41],"text.":[45],"We":[46],"present":[47],"Transformer":[49],"model":[50,100],"that":[51,79,97,110],"integrates":[52],"text":[53,82],"modalities":[56],"attends":[58],"to":[59,86,114],"textual":[60],"features":[61,64,112],"from":[62],"visual":[63,111],"in":[65],"generating":[66],"caption.":[68],"Experiments":[69],"based":[70],"on":[71],"automatic":[72],"evaluation":[73,77],"metrics":[74],"human":[76],"show":[78],"provides":[83],"primary":[84],"information":[85],"reproduce":[87],"captions":[89],"written":[90],"by":[91],"journalists.":[92],"The":[93],"results":[94],"also":[95,108],"demonstrate":[96],"proposed":[99],"outperforms":[101],"state-of-the-art":[103],"model.":[104],"addition,":[106],"confirm":[109],"contribute":[113],"improving":[115],"quality":[117],"captions.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
