{"id":"https://openalex.org/W2251955524","doi":"https://doi.org/10.3115/v1/w14-1602","title":"Domain-Specific Image Captioning","display_name":"Domain-Specific Image Captioning","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251955524","doi":"https://doi.org/10.3115/v1/w14-1602","mag":"2251955524"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-1602","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-1602","pdf_url":"https://aclanthology.org/W14-1602.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 Eighteenth Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-1602.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027550394","display_name":"Rebecca Mason","orcid":"https://orcid.org/0000-0001-9156-8782"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rebecca Mason","raw_affiliation_strings":["Brown Laboratory for Linguistic Information Processing (BLLIP) Brown University, Providence, RI 02912"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown Laboratory for Linguistic Information Processing (BLLIP) Brown University, Providence, RI 02912","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005380528","display_name":"Eugene Charniak","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Charniak","raw_affiliation_strings":["Brown Laboratory for Linguistic Information Processing (BLLIP) Brown University, Providence, RI 02912"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown Laboratory for Linguistic Information Processing (BLLIP) Brown University, Providence, RI 02912","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5027550394"],"corresponding_institution_ids":["https://openalex.org/I27804330"],"apc_list":null,"apc_paid":null,"fwci":0.1798,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.50020702,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9476090669631958},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.8449743986129761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8433829545974731},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.654370129108429},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6102828979492188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5921648144721985},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.527572512626648},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5157952308654785},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5138676166534424},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4991614818572998},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4600408673286438},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4188898205757141},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3617614805698395},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32857805490493774},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07863408327102661}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9476090669631958},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.8449743986129761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8433829545974731},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.654370129108429},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6102828979492188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5921648144721985},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.527572512626648},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5157952308654785},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5138676166534424},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4991614818572998},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4600408673286438},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4188898205757141},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3617614805698395},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32857805490493774},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07863408327102661},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/w14-1602","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-1602","pdf_url":"https://aclanthology.org/W14-1602.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 Eighteenth Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.672.770","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.672.770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://anthology.aclweb.org/W/W14/W14-1602.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-1602","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-1602","pdf_url":"https://aclanthology.org/W14-1602.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 Eighteenth Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251955524.pdf","grobid_xml":"https://content.openalex.org/works/W2251955524.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W1484228140","https://openalex.org/W1528802670","https://openalex.org/W1566135517","https://openalex.org/W1750831471","https://openalex.org/W1858383477","https://openalex.org/W1897761818","https://openalex.org/W2001135856","https://openalex.org/W2020842694","https://openalex.org/W2033593667","https://openalex.org/W2066134726","https://openalex.org/W2092654472","https://openalex.org/W2097321121","https://openalex.org/W2097606805","https://openalex.org/W2101105183","https://openalex.org/W2109586012","https://openalex.org/W2114449787","https://openalex.org/W2115322217","https://openalex.org/W2118681326","https://openalex.org/W2124386111","https://openalex.org/W2126384256","https://openalex.org/W2128808215","https://openalex.org/W2133182690","https://openalex.org/W2136985729","https://openalex.org/W2144715671","https://openalex.org/W2149172860","https://openalex.org/W2154652894","https://openalex.org/W2161969291","https://openalex.org/W2168356304","https://openalex.org/W2251620981","https://openalex.org/W4248892431"],"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/W3217195652","https://openalex.org/W3009270862"],"abstract_inverted_index":{"We":[0,21,42,71],"present":[1],"a":[2,47,57,76,109],"data-driven":[3],"framework":[4],"for":[5],"image":[6,27],"caption":[7],"generation":[8],"which":[9],"incorporates":[10],"visual":[11,32,59],"and":[12,49,60,84,91],"textual":[13,61],"features":[14],"with":[15],"varying":[16],"degrees":[17],"of":[18,25,68,80,112],"spatial":[19],"structure.":[20],"propose":[22],"the":[23,66,115],"task":[24],"domain-specific":[26],"captioning,":[28],"where":[29],"many":[30],"relevant":[31],"details":[33],"cannot":[34],"be":[35],"captured":[36],"by":[37],"off-the-shelf":[38],"general-domain":[39],"entity":[40],"detectors.":[41],"extract":[43],"previously-written":[44],"descriptions":[45,87],"from":[46,104],"database":[48],"adapt":[50],"them":[51],"to":[52,64],"new":[53],"query":[54],"images,":[55],"using":[56,75],"joint":[58],"bag-of-words":[62],"model":[63,74],"determine":[65],"correctness":[67],"individual":[69],"words.":[70],"implement":[72],"our":[73,97],"large,":[77],"unlabeled":[78],"dataset":[79],"women's":[81],"shoes":[82],"images":[83],"natural":[85],"language":[86],"Using":[88],"both":[89],"automatic":[90],"human":[92],"evaluations,":[93],"we":[94],"show":[95],"that":[96],"captioning":[98],"method":[99],"effectively":[100],"deletes":[101],"inaccurate":[102],"words":[103],"extracted":[105],"captions":[106],"while":[107],"maintaining":[108],"high":[110],"level":[111],"detail":[113],"in":[114],"generated":[116],"output.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}