{"id":"https://openalex.org/W1905882502","doi":"https://doi.org/10.1109/cvpr.2015.7298932","title":"Deep visual-semantic alignments for generating image descriptions","display_name":"Deep visual-semantic alignments for generating image descriptions","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W1905882502","doi":"https://doi.org/10.1109/cvpr.2015.7298932","mag":"1905882502"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2015.7298932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2015.7298932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5009290031","display_name":"Andrej Karpathy","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrej Karpathy","raw_affiliation_strings":["Department of Computer Science, Stanford University, USA","Dept of Computer Science, Stanford University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Dept of Computer Science, Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100450462","display_name":"Li Fei-Fei","orcid":"https://orcid.org/0000-0002-7481-0810"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Fei-Fei","raw_affiliation_strings":["Department of Computer Science, Stanford University, USA","Dept of Computer Science, Stanford University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Dept of Computer Science, Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009290031"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":303.2904,"has_fulltext":false,"cited_by_count":4944,"citation_normalized_percentile":{"value":0.99986868,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3128","last_page":"3137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.993399977684021,"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":0.993399977684021,"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":0.0006000000284984708,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0006000000284984708,"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/computer-science","display_name":"Computer science","score":0.8539552092552185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7175669074058533},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6420209407806396},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5648754239082336},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5092698335647583},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5027420520782471},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4907172918319702},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4706296920776367},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4704011380672455},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4131418466567993},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3159247636795044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8539552092552185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7175669074058533},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6420209407806396},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5648754239082336},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5092698335647583},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5027420520782471},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4907172918319702},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4706296920776367},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4704011380672455},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4131418466567993},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3159247636795044},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cvpr.2015.7298932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2015.7298932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.838.7368","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.838.7368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Karpathy_Deep_Visual-Semantic_Alignments_2015_CVPR_paper.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":95,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W62621907","https://openalex.org/W68733909","https://openalex.org/W100623710","https://openalex.org/W179875071","https://openalex.org/W196214544","https://openalex.org/W1527575280","https://openalex.org/W1591801644","https://openalex.org/W1686810756","https://openalex.org/W1687846465","https://openalex.org/W1858383477","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1923162067","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1987835821","https://openalex.org/W2031489346","https://openalex.org/W2048343491","https://openalex.org/W2056621158","https://openalex.org/W2062955551","https://openalex.org/W2064675550","https://openalex.org/W2066134726","https://openalex.org/W2086842362","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2102605133","https://openalex.org/W2106624428","https://openalex.org/W2108598243","https://openalex.org/W2109586012","https://openalex.org/W2110485445","https://openalex.org/W2112796928","https://openalex.org/W2112912048","https://openalex.org/W2115752676","https://openalex.org/W2117539524","https://openalex.org/W2122180654","https://openalex.org/W2123024445","https://openalex.org/W2125436662","https://openalex.org/W2131774270","https://openalex.org/W2133459682","https://openalex.org/W2143449221","https://openalex.org/W2147625498","https://openalex.org/W2149172860","https://openalex.org/W2149536503","https://openalex.org/W2149557440","https://openalex.org/W2153579005","https://openalex.org/W2159243025","https://openalex.org/W2163605009","https://openalex.org/W2171361956","https://openalex.org/W2181691731","https://openalex.org/W2185175083","https://openalex.org/W2250539671","https://openalex.org/W2251583212","https://openalex.org/W2296385829","https://openalex.org/W2536208356","https://openalex.org/W2952574180","https://openalex.org/W2963811219","https://openalex.org/W4239072543","https://openalex.org/W4254816979","https://openalex.org/W4285719527","https://openalex.org/W4294170691","https://openalex.org/W6607974698","https://openalex.org/W6631516269","https://openalex.org/W6635446068","https://openalex.org/W6637306801","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6639118148","https://openalex.org/W6639432524","https://openalex.org/W6639657675","https://openalex.org/W6639694449","https://openalex.org/W6640071036","https://openalex.org/W6640169532","https://openalex.org/W6640617836","https://openalex.org/W6641064462","https://openalex.org/W6674914833","https://openalex.org/W6676297131","https://openalex.org/W6676497082","https://openalex.org/W6676647902","https://openalex.org/W6677533783","https://openalex.org/W6677651945","https://openalex.org/W6677969093","https://openalex.org/W6678470764","https://openalex.org/W6681184217","https://openalex.org/W6682086108","https://openalex.org/W6682691769","https://openalex.org/W6683167905","https://openalex.org/W6683512859","https://openalex.org/W6684191040","https://openalex.org/W6685230081","https://openalex.org/W6898505805","https://openalex.org/W7011438494"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W3017902212","https://openalex.org/W2964335273","https://openalex.org/W2982145560","https://openalex.org/W2597655663"],"abstract_inverted_index":{"We":[0,70,93,114],"present":[1],"a":[2,41,58,67,73,131],"model":[3,37,98],"that":[4,61,79,95,117],"generates":[5],"natural":[6],"language":[7,31],"descriptions":[8,23,89,120],"of":[9,18,44,90,101,134],"images":[10,19,128],"and":[11,20,32,57,111,129],"their":[12,21],"regions.":[13,92],"Our":[14,35],"approach":[15],"leverages":[16],"datasets":[17],"sentence":[22],"to":[24,84,86],"learn":[25,85],"about":[26],"the":[27,63,81,102,118],"inter-modal":[28],"correspondences":[29],"between":[30],"visual":[33],"data.":[34],"alignment":[36,97],"is":[38],"based":[39],"on":[40,108,125,130],"novel":[42,88],"combination":[43],"Convolutional":[45],"Neural":[46,53,76],"Networks":[47,54],"over":[48,55],"image":[49,91],"regions,":[50],"bidirectional":[51],"Recurrent":[52,75],"sentences,":[56],"structured":[59],"objective":[60],"aligns":[62],"two":[64],"modalities":[65],"through":[66],"multimodal":[68],"embedding.":[69],"then":[71,115],"describe":[72],"Multimodal":[74],"Network":[77],"architecture":[78],"uses":[80],"inferred":[82],"alignments":[83],"generate":[87],"demonstrate":[94],"our":[96],"produces":[99],"state":[100],"art":[103],"results":[104],"in":[105],"retrieval":[106,123],"experiments":[107],"Flickr8K,":[109],"Flickr30K":[110],"MSCOCO":[112],"datasets.":[113],"show":[116],"generated":[119],"significantly":[121],"outperform":[122],"baselines":[124],"both":[126],"full":[127],"new":[132],"dataset":[133],"region-level":[135],"annotations.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":39},{"year":2025,"cited_by_count":284},{"year":2024,"cited_by_count":372},{"year":2023,"cited_by_count":429},{"year":2022,"cited_by_count":402},{"year":2021,"cited_by_count":575},{"year":2020,"cited_by_count":552},{"year":2019,"cited_by_count":667},{"year":2018,"cited_by_count":582},{"year":2017,"cited_by_count":508},{"year":2016,"cited_by_count":364},{"year":2015,"cited_by_count":166},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}