{"id":"https://openalex.org/W1895989618","doi":"https://doi.org/10.1109/cvpr.2015.7298856","title":"Mind's eye: A recurrent visual representation for image caption generation","display_name":"Mind's eye: A recurrent visual representation for image caption generation","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W1895989618","doi":"https://doi.org/10.1109/cvpr.2015.7298856","mag":"1895989618"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2015.7298856","doi":"https://doi.org/10.1109/cvpr.2015.7298856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2015.7298856","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"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"},"parent_works":[],"lineage":["https://openalex.org/W1895989618"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5016095713","display_name":"Xinlei Chen","orcid":"https://orcid.org/0000-0001-8271-5023","observed_orcids":["https://orcid.org/0000-0001-8271-5023"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinlei Chen","raw_affiliation_strings":["Carnegie Mellon University","Carnegie Mellon Univ (USA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon Univ (USA)","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058450549","display_name":"C. Lawrence Zitnick","orcid":"https://orcid.org/0009-0006-2032-9374","observed_orcids":["https://orcid.org/0009-0006-2032-9374"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lawrence Zitnick","raw_affiliation_strings":["Microsoft Research, Redmond, WA, US","Microsoft Research, , Redmond, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, US","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, , Redmond, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":28.9833,"has_fulltext":false,"cited_by_count":500,"citation_normalized_percentile":{"value":0.99589236,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2422","last_page":"2431"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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":0.9990000128746033,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0008999999845400453,"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":9.999999747378752e-05,"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/image-captioning","display_name":"image captioning","score":0.9380000233650208},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.781000018119812},{"id":"https://openalex.org/keywords/visual-representation","display_name":"visual representation","score":0.6809999942779541},{"id":"https://openalex.org/keywords/visual-long-term-memory","display_name":"visual long-term memory","score":0.6919999718666077},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"image retrieval","score":0.6449999809265137},{"id":"https://openalex.org/keywords/sentence-retrieval","display_name":"sentence retrieval","score":0.9779999852180481},{"id":"https://openalex.org/keywords/sentence-generation","display_name":"sentence generation","score":0.4269999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8451334834098816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7434877157211304},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7418049573898315},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.687143087387085},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6025598049163818},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5815112590789795},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5635062456130981},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4980282783508301},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49181440472602844},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4570891559123993},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.416806161403656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33760392665863037},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr.2015.7298856","doi":"https://doi.org/10.1109/cvpr.2015.7298856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2015.7298856","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"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"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W68733909","https://openalex.org/W92662927","https://openalex.org/W100623710","https://openalex.org/W179875071","https://openalex.org/W196214544","https://openalex.org/W1514535095","https://openalex.org/W1527575280","https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1858383477","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1965154800","https://openalex.org/W1984205520","https://openalex.org/W1987835821","https://openalex.org/W1996418862","https://openalex.org/W1999965501","https://openalex.org/W2014589321","https://openalex.org/W2025768430","https://openalex.org/W2064675550","https://openalex.org/W2066134726","https://openalex.org/W2074551623","https://openalex.org/W2101105183","https://openalex.org/W2102605133","https://openalex.org/W2107878631","https://openalex.org/W2108598243","https://openalex.org/W2110485445","https://openalex.org/W2112912048","https://openalex.org/W2119775030","https://openalex.org/W2122180654","https://openalex.org/W2123024445","https://openalex.org/W2123301721","https://openalex.org/W2126229220","https://openalex.org/W2128856065","https://openalex.org/W2149172860","https://openalex.org/W2149557440","https://openalex.org/W2155893237","https://openalex.org/W2159243025","https://openalex.org/W2163605009","https://openalex.org/W2171361956","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2122180654","https://openalex.org/W7095927401","https://openalex.org/W3195770884","https://openalex.org/W2601380348","https://openalex.org/W1895577753","https://openalex.org/W2962139653","https://openalex.org/W3212753468","https://openalex.org/W1931639407","https://openalex.org/W4409700503","https://openalex.org/W3119789064"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"explore":[4],"the":[5,32,92,118,130],"bi-directional":[6],"mapping":[7],"between":[8],"images":[9],"and":[10,63,84,132],"their":[11],"sentence-based":[12],"descriptions.":[13,98],"Critical":[14],"to":[15,25,46,101,111,126],"our":[16,73,105],"approach":[17,74],"is":[18,37,53],"a":[19,28,35],"recurrent":[20],"neural":[21],"network":[22],"that":[23],"attempts":[24],"dynamically":[26],"build":[27],"visual":[29,49,65,140],"representation":[30,43],"of":[31,55,94,117],"scene":[33],"as":[34],"caption":[36],"being":[38],"generated":[39,103,107],"or":[40,112,124],"read.":[41],"The":[42],"automatically":[44,106],"learns":[45],"remember":[47],"long-term":[48],"concepts.":[50],"Our":[51],"model":[52],"capable":[54],"both":[56],"generating":[57,95],"novel":[58,96],"captions":[59,108],"given":[60,67],"an":[61,68],"image,":[62],"reconstructing":[64],"features":[66],"image":[69,85,97,131],"description.":[70],"We":[71],"evaluate":[72],"on":[75,129],"several":[76],"tasks.":[77],"These":[78],"include":[79],"sentence":[80,82,133],"generation,":[81],"retrieval":[83,134],"retrieval.":[86],"State-of-the-art":[87],"results":[88,128],"are":[89,109,121],"shown":[90],"for":[91,136],"task":[93],"When":[99],"compared":[100],"human":[102],"captions,":[104],"equal":[110],"preferred":[113],"by":[114],"humans":[115],"21.0%":[116],"time.":[119],"Results":[120],"better":[122],"than":[123],"comparable":[125],"state-of-the-art":[127],"tasks":[135],"methods":[137],"using":[138],"similar":[139],"features.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":29},{"year":2021,"cited_by_count":41},{"year":2020,"cited_by_count":54},{"year":2019,"cited_by_count":75},{"year":2018,"cited_by_count":86},{"year":2017,"cited_by_count":72},{"year":2016,"cited_by_count":42},{"year":2015,"cited_by_count":18}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}