{"id":"https://openalex.org/W1938708284","doi":"https://doi.org/10.18653/v1/w15-2807","title":"Image Representations and New Domains in Neural Image Captioning","display_name":"Image Representations and New Domains in Neural Image Captioning","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W1938708284","doi":"https://doi.org/10.18653/v1/w15-2807","mag":"1938708284"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-2807","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-2807","pdf_url":"https://www.aclweb.org/anthology/W15-2807.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 Fourth Workshop on Vision and Language","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-2807.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043614405","display_name":"Jack Hessel","orcid":"https://orcid.org/0000-0002-4012-8979"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Jack Hessel","raw_affiliation_strings":["Computer Science Dept Cornell University","Cornell University, Ithaca, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept Cornell University","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4210156583"]},{"raw_affiliation_string":"Cornell University, Ithaca, United States","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035473513","display_name":"Nicolas Savva","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Nicolas Savva","raw_affiliation_strings":["Computer Science Dept Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept Cornell University","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4210156583"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026971189","display_name":"Michael J. Wilber","orcid":"https://orcid.org/0000-0001-7040-0251"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4405261073","display_name":"Cornell Tech","ror":"https://ror.org/04qscbg47","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Wilber","raw_affiliation_strings":["Cornell Tech Cornell University","Cornell University, Ithaca, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell Tech Cornell University","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]},{"raw_affiliation_string":"Cornell University, Ithaca, United States","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"39"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9941999912261963,"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":0.992900013923645,"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":0.9841998219490051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7750883102416992},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.7440135478973389},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6449995636940002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5869413614273071},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5691121816635132},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5658144950866699},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.495355486869812},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4786744713783264},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4347417950630188},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.4187540113925934},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08843794465065002}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9841998219490051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7750883102416992},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.7440135478973389},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6449995636940002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5869413614273071},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5691121816635132},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5658144950866699},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.495355486869812},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4786744713783264},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4347417950630188},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.4187540113925934},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08843794465065002},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w15-2807","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-2807","pdf_url":"https://www.aclweb.org/anthology/W15-2807.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 Fourth Workshop on Vision and Language","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1508.02091","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1508.02091","pdf_url":"https://arxiv.org/pdf/1508.02091","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:1938708284","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1508.02091.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1508.02091","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1508.02091","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-2807","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-2807","pdf_url":"https://www.aclweb.org/anthology/W15-2807.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 Fourth Workshop on Vision and Language","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1938708284.pdf","grobid_xml":"https://content.openalex.org/works/W1938708284.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W68733909","https://openalex.org/W196214544","https://openalex.org/W1527575280","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1897761818","https://openalex.org/W1963321737","https://openalex.org/W1969616664","https://openalex.org/W2044905690","https://openalex.org/W2055527244","https://openalex.org/W2096761622","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2109586012","https://openalex.org/W2120826678","https://openalex.org/W2133459682","https://openalex.org/W2159243025","https://openalex.org/W2185175083","https://openalex.org/W2295582178","https://openalex.org/W2949667497","https://openalex.org/W2949769367","https://openalex.org/W2950179405","https://openalex.org/W2951183276","https://openalex.org/W2951805548","https://openalex.org/W2952574180"],"related_works":["https://openalex.org/W2962685035","https://openalex.org/W2785567709","https://openalex.org/W2891658588","https://openalex.org/W2889720786","https://openalex.org/W2913090763","https://openalex.org/W2767577934","https://openalex.org/W3200264219","https://openalex.org/W2890769421","https://openalex.org/W3184581815","https://openalex.org/W2952342379","https://openalex.org/W3102877762","https://openalex.org/W2946574595","https://openalex.org/W3195250027","https://openalex.org/W3086385316","https://openalex.org/W3199014515","https://openalex.org/W2885822952","https://openalex.org/W3195966176","https://openalex.org/W3010982166","https://openalex.org/W2951570118","https://openalex.org/W568317867"],"abstract_inverted_index":{"We":[0,51,69],"examine":[1],"the":[2,75],"possibility":[3],"that":[4,31,84],"recent":[5],"promising":[6],"results":[7],"in":[8,55],"automatic":[9,80],"caption":[10],"generation":[11],"are":[12],"due":[13],"primarily":[14],"to":[15,39],"language":[16],"models.":[17],"By":[18],"varying":[19],"image":[20,49,89],"representation":[21],"quality":[22,41],"produced":[23],"by":[24],"a":[25,32,56],"convolutional":[26],"neural":[27,34],"network,":[28],"we":[29],"find":[30,83],"state-of-theart":[33],"captioning":[35,61],"algorithm":[36],"is":[37,90],"able":[38],"produce":[40],"captions":[42,87],"even":[43],"when":[44],"provided":[45],"with":[46],"surprisingly":[47],"poor":[48],"representations.":[50],"replicate":[52],"this":[53],"result":[54],"new,":[57],"fine-grained,":[58],"transfer":[59],"learned":[60],"domain,":[62],"consisting":[63],"of":[64,77],"66K":[65],"recipe":[66],"image/title":[67],"pairs.":[68],"also":[70],"provide":[71],"some":[72],"experiments":[73],"regarding":[74],"appropriateness":[76],"datasets":[78],"for":[79],"captioning,":[81],"and":[82],"having":[85],"multiple":[86],"per":[88],"beneficial,":[91],"but":[92],"not":[93],"an":[94],"absolute":[95],"requirement.":[96]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}