{"id":"https://openalex.org/W2914306086","doi":"https://doi.org/10.1109/tetci.2019.2892755","title":"Visual to Text: Survey of Image and Video Captioning","display_name":"Visual to Text: Survey of Image and Video Captioning","publication_year":2019,"publication_date":"2019-01-29","ids":{"openalex":"https://openalex.org/W2914306086","doi":"https://doi.org/10.1109/tetci.2019.2892755","mag":"2914306086"},"language":"en","primary_location":{"id":"doi:10.1109/tetci.2019.2892755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2019.2892755","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","raw_type":"journal-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/A5100359839","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0003-1205-8632"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sheng Li","raw_affiliation_strings":["Department of Computer Science, University of Georgia, Athens, GA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Georgia, Athens, GA, USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021486404","display_name":"Zhiqiang Tao","orcid":"https://orcid.org/0000-0002-5639-7540"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiqiang Tao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456986","display_name":"Kang Li","orcid":"https://orcid.org/0000-0002-8136-9816"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kang Li","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005819096","display_name":"Yun Fu","orcid":"https://orcid.org/0000-0002-5098-2853"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Fu","raw_affiliation_strings":["Department of Electrical and Computer Engineering and the Khoury College of Computer and Information Sciences, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and the Khoury College of Computer and Information Sciences, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100359839"],"corresponding_institution_ids":["https://openalex.org/I165733156"],"apc_list":null,"apc_paid":null,"fwci":4.1976,"has_fulltext":false,"cited_by_count":101,"citation_normalized_percentile":{"value":0.95309912,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"3","issue":"4","first_page":"297","last_page":"312"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987000226974487,"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":0.9976999759674072,"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/automatic-summarization","display_name":"Automatic summarization","score":0.8667930364608765},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8625515699386597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8469152450561523},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.5491951107978821},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5412425994873047},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.522135317325592},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5063997507095337},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.49318116903305054},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4850401282310486},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4822883903980255},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4739765524864197},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42372068762779236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36264556646347046},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2641136348247528},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.18661820888519287}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8667930364608765},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8625515699386597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8469152450561523},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.5491951107978821},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5412425994873047},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.522135317325592},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5063997507095337},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.49318116903305054},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4850401282310486},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4822883903980255},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4739765524864197},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42372068762779236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36264556646347046},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2641136348247528},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.18661820888519287},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetci.2019.2892755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2019.2892755","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3571051887","display_name":null,"funder_award_id":"W911NF-17-1-0367","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G4054672515","display_name":null,"funder_award_id":"1651902","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":189,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W129606432","https://openalex.org/W146597194","https://openalex.org/W877909479","https://openalex.org/W1485949349","https://openalex.org/W1499486838","https://openalex.org/W1505486987","https://openalex.org/W1514535095","https://openalex.org/W1522734439","https://openalex.org/W1527575280","https://openalex.org/W1548185736","https://openalex.org/W1566135517","https://openalex.org/W1572567476","https://openalex.org/W1586939924","https://openalex.org/W1601567445","https://openalex.org/W1614298861","https://openalex.org/W1638952162","https://openalex.org/W1639784222","https://openalex.org/W1677409904","https://openalex.org/W1686810756","https://openalex.org/W1687846465","https://openalex.org/W1811254738","https://openalex.org/W1836465849","https://openalex.org/W1858383477","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1895641373","https://openalex.org/W1895989618","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1942126453","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1964181696","https://openalex.org/W1965662797","https://openalex.org/W1976272094","https://openalex.org/W1987835821","https://openalex.org/W1988419820","https://openalex.org/W1995820507","https://openalex.org/W2007731511","https://openalex.org/W2016053056","https://openalex.org/W2019660985","https://openalex.org/W2029545460","https://openalex.org/W2030360076","https://openalex.org/W2035434106","https://openalex.org/W2035683813","https://openalex.org/W2042322506","https://openalex.org/W2048343491","https://openalex.org/W2052355211","https://openalex.org/W2056983531","https://openalex.org/W2063153269","https://openalex.org/W2064204546","https://openalex.org/W2066134726","https://openalex.org/W2071521210","https://openalex.org/W2078238240","https://openalex.org/W2086842362","https://openalex.org/W2087544865","https://openalex.org/W2091812280","https://openalex.org/W2094998392","https://openalex.org/W2097117768","https://openalex.org/W2098056602","https://openalex.org/W2101105183","https://openalex.org/W2102605133","https://openalex.org/W2104311745","https://openalex.org/W2105103432","https://openalex.org/W2106791119","https://openalex.org/W2107019937","https://openalex.org/W2108598243","https://openalex.org/W2109586012","https://openalex.org/W2110933980","https://openalex.org/W2111078031","https://openalex.org/W2114841702","https://openalex.org/W2117051369","https://openalex.org/W2123277412","https://openalex.org/W2124386111","https://openalex.org/W2125707784","https://openalex.org/W2126384256","https://openalex.org/W2128554449","https://openalex.org/W2128856065","https://openalex.org/W2130660124","https://openalex.org/W2130942839","https://openalex.org/W2132579158","https://openalex.org/W2132986783","https://openalex.org/W2133273100","https://openalex.org/W2133564696","https://openalex.org/W2139117248","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2143449221","https://openalex.org/W2144600658","https://openalex.org/W2146352414","https://openalex.org/W2149172860","https://openalex.org/W2149557440","https://openalex.org/W2151848798","https://openalex.org/W2153784897","https://openalex.org/W2154652894","https://openalex.org/W2156830856","https://openalex.org/W2157331557","https://openalex.org/W2161969291","https://openalex.org/W2163605009","https://openalex.org/W2164290393","https://openalex.org/W2164598857","https://openalex.org/W2166010828","https://openalex.org/W2167905777","https://openalex.org/W2168356304","https://openalex.org/W2171361956","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2251353663","https://openalex.org/W2251955524","https://openalex.org/W2282219577","https://openalex.org/W2302086703","https://openalex.org/W2429638696","https://openalex.org/W2463955103","https://openalex.org/W2474463024","https://openalex.org/W2506483933","https://openalex.org/W2534300396","https://openalex.org/W2552161745","https://openalex.org/W2556388456","https://openalex.org/W2557264465","https://openalex.org/W2565656701","https://openalex.org/W2575842049","https://openalex.org/W2607151106","https://openalex.org/W2618530766","https://openalex.org/W2620761940","https://openalex.org/W2752461516","https://openalex.org/W2753215597","https://openalex.org/W2803259101","https://openalex.org/W2805954242","https://openalex.org/W2887097088","https://openalex.org/W2896348597","https://openalex.org/W2917654327","https://openalex.org/W2951183276","https://openalex.org/W2962706528","https://openalex.org/W2962835968","https://openalex.org/W2962937869","https://openalex.org/W2962968835","https://openalex.org/W2963084599","https://openalex.org/W2963360726","https://openalex.org/W2963576560","https://openalex.org/W2963594498","https://openalex.org/W2963811219","https://openalex.org/W2963843052","https://openalex.org/W2963881583","https://openalex.org/W2964018924","https://openalex.org/W2964042428","https://openalex.org/W2964049455","https://openalex.org/W2964241990","https://openalex.org/W2964308564","https://openalex.org/W3098682680","https://openalex.org/W3099032148","https://openalex.org/W6600334730","https://openalex.org/W6605295763","https://openalex.org/W6606029161","https://openalex.org/W6623995992","https://openalex.org/W6630305801","https://openalex.org/W6630875275","https://openalex.org/W6631516269","https://openalex.org/W6634126550","https://openalex.org/W6636510571","https://openalex.org/W6636759891","https://openalex.org/W6637306801","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6638742206","https://openalex.org/W6639118148","https://openalex.org/W6676497082","https://openalex.org/W6677231853","https://openalex.org/W6678712372","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6681184217","https://openalex.org/W6681644459","https://openalex.org/W6682086108","https://openalex.org/W6682631176","https://openalex.org/W6683167905","https://openalex.org/W6684090549","https://openalex.org/W6684369376","https://openalex.org/W6685230081","https://openalex.org/W6691419566","https://openalex.org/W6703525202","https://openalex.org/W6729046916","https://openalex.org/W6738746457","https://openalex.org/W6743895910","https://openalex.org/W6744104549","https://openalex.org/W6752035164","https://openalex.org/W6755373699"],"related_works":["https://openalex.org/W4284703357","https://openalex.org/W2750434199","https://openalex.org/W2347374138","https://openalex.org/W2129428289","https://openalex.org/W2050635624","https://openalex.org/W2101447046","https://openalex.org/W2091753323","https://openalex.org/W2168037874","https://openalex.org/W2078285696","https://openalex.org/W2135728080"],"abstract_inverted_index":{"Visual":[0],"data":[1],"such":[2,49,72],"as":[3,95],"images":[4,177],"and":[5,11,33,63,89,127,155,178,180,183,205],"videos":[6,100],"are":[7,101,121,159,202],"easily":[8],"accessible":[9],"nowadays,":[10],"they":[12],"play":[13],"critical":[14,77],"roles":[15],"in":[16,143],"many":[17],"real-world":[18],"applications":[19],"like":[20],"surveillance.":[21],"This":[22],"raises":[23],"a":[24,45,96],"series":[25],"of":[26,48,57,60,99,119,196],"technological":[27],"demands":[28],"for":[29],"automatic":[30,73],"visual":[31,145,173],"understanding":[32,59],"content":[34,62],"summarization,":[35],"which":[36],"has":[37],"guided":[38],"the":[39,54,83,129,139,144,185,211],"research":[40,213],"community":[41],"to":[42,81,123,137,146,171],"move":[43],"towards":[44],"better":[46],"achievement":[47],"capabilities.":[50],"Meanwhile,":[51],"it":[52],"presents":[53],"big":[55],"challenge":[56],"semantic":[58,92,130],"video":[61],"automatically":[64],"translating":[65],"them":[66],"into":[67],"human":[68],"language.":[69],"When":[70],"developing":[71],"translation":[74],"systems,":[75],"one":[76],"issue":[78,110],"is":[79],"how":[80],"bridge":[82],"gap":[84,131],"between":[85],"low":[86],"level":[87,91],"features":[88],"high":[90],"information.":[93],"Furthermore,":[94],"large":[97],"amount":[98],"captured":[102],"under":[103],"unconstrained":[104],"conditions":[105],"by":[106,168],"nonprofessional":[107],"users,":[108],"this":[109,216],"becomes":[111],"even":[112],"more":[113],"serious.":[114],"Therefore,":[115],"brand":[116],"new":[117],"sets":[118],"technologies":[120],"required":[122],"address":[124],"these":[125],"difficulties":[126],"narrow":[128],"effectively.":[132],"These":[133],"thoughts":[134],"drive":[135],"us":[136],"survey":[138],"complete":[140],"state-of-the-art":[141],"techniques":[142],"text":[147,181],"topic.":[148,217],"Existing":[149],"methods,":[150],"popular":[151],"datasets,":[152],"technical":[153],"difficulties,":[154],"promising":[156,212],"future":[157],"directions":[158,214],"discussed":[160],"systematically.":[161],"In":[162],"particular,":[163],"we":[164,208],"classify":[165],"existing":[166],"methods":[167],"their":[169],"mechanism":[170],"link":[172],"information":[174],"(including":[175],"both":[176],"videos)":[179],"descriptions,":[182],"emphasize":[184],"latest":[186],"advances":[187],"on":[188,199,215],"deep":[189],"learning":[190],"based":[191],"approaches.":[192],"The":[193],"quantitative":[194],"evaluations":[195],"representative":[197],"approaches":[198],"benchmark":[200],"dataset":[201],"also":[203],"presented":[204],"discussed.":[206],"Finally,":[207],"provide":[209],"with":[210]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":3}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}