{"id":"https://openalex.org/W2952003359","doi":"https://doi.org/10.18653/v1/p19-1650","title":"Informative Image Captioning with External Sources of Information","display_name":"Informative Image Captioning with External Sources of Information","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2952003359","doi":"https://doi.org/10.18653/v1/p19-1650","mag":"2952003359"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1650","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1650","pdf_url":null,"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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/p19-1650","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031618209","display_name":"Sanqiang Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanqiang Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100679058","display_name":"Piyush Sharma","orcid":"https://orcid.org/0009-0003-0372-4303"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piyush Sharma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037105118","display_name":"Tomer Levinboim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomer Levinboim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089152779","display_name":"Radu Soricut","orcid":"https://orcid.org/0000-0003-1565-3365"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Radu Soricut","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6485","last_page":"6494"},"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":0.9973999857902527,"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/T10028","display_name":"Topic Modeling","score":0.9904999732971191,"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":0.9263252019882202},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8347076177597046},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6313028931617737},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.552140474319458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5288432836532593},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5162551403045654},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.48701363801956177},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3950648903846741},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3676905632019043},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35891157388687134}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9263252019882202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8347076177597046},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6313028931617737},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.552140474319458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5288432836532593},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5162551403045654},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48701363801956177},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3950648903846741},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3676905632019043},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35891157388687134},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1650","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1650","pdf_url":null,"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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1650","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1650","pdf_url":null,"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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1514535095","https://openalex.org/W1527575280","https://openalex.org/W1821462560","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2130942839","https://openalex.org/W2146502635","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2552161745","https://openalex.org/W2558533273","https://openalex.org/W2737766105","https://openalex.org/W2886641317","https://openalex.org/W2962753250","https://openalex.org/W2962784628","https://openalex.org/W2963138277","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964049455","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W4323777661","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3122720459"],"abstract_inverted_index":{"An":[0],"image":[1,56,76,95],"caption":[2,72],"should":[3],"fluently":[4],"present":[5,51],"the":[6,19,75,111,118],"essential":[7],"information":[8,57],"in":[9,21,77,117,121],"a":[10,52,71,78,85],"given":[11],"image,":[12],"including":[13],"informative,":[14],"fine-grained":[15,60],"entity":[16,101,115],"mentions":[17],"and":[18,80,97,127],"manner":[20],"which":[22],"these":[23,114],"entities":[24],"interact.":[25],"However,":[26],"current":[27],"captioning":[28],"models":[29],"are":[30,124],"usually":[31],"trained":[32],"to":[33,63,109],"generate":[34],"captions":[35,122],"that":[36,73,92,105,123],"only":[37],"contain":[38],"common":[39],"object":[40],"names,":[41],"thus":[42],"falling":[43],"short":[44],"on":[45,90],"an":[46],"important":[47],"\u201cinformativeness\u201d":[48],"dimension.":[49],"We":[50,83,103],"mechanism":[53],"for":[54],"integrating":[55],"together":[58],"with":[59],"labels":[61,116],"(assumed":[62],"be":[64],"generated":[65],"by":[66],"some":[67],"upstream":[68],"models)":[69],"into":[70],"describes":[74],"fluent":[79,126],"informative":[81],"manner.":[82],"introduce":[84],"multimodal,":[86],"multi-encoder":[87],"model":[88],"based":[89],"Transformer":[91],"ingests":[93],"both":[94,125],"features":[96],"multiple":[98],"sources":[99],"of":[100,113],"labels.":[102],"demonstrate":[104],"we":[106],"can":[107],"learn":[108],"control":[110],"appearance":[112],"output,":[119],"resulting":[120],"informative.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":13}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}