{"id":"https://openalex.org/W1487980087","doi":"https://doi.org/10.1109/mva.2015.7153244","title":"Image annotation via deep neural network","display_name":"Image annotation via deep neural network","publication_year":2015,"publication_date":"2015-05-01","ids":{"openalex":"https://openalex.org/W1487980087","doi":"https://doi.org/10.1109/mva.2015.7153244","mag":"1487980087"},"language":"en","primary_location":{"id":"doi:10.1109/mva.2015.7153244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mva.2015.7153244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 14th IAPR International Conference on Machine Vision Applications (MVA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100526455","display_name":"Sun Chengjian","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun Chengjian","raw_affiliation_strings":["School of Automation, Nanjing University of Posts and Telecommunications, Nanjing, China","School of Automation, Nanjing University of Posts and Telecommunications, Nanjing, 210046, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Automation, Nanjing University of Posts and Telecommunications, Nanjing, 210046, China#TAB#","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101746227","display_name":"Songhao Zhu","orcid":"https://orcid.org/0000-0002-9891-5692"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songhao Zhu","raw_affiliation_strings":["School of Automation, Nanjing University of Posts and Telecommunications, Nanjing, China","School of Automation, Nanjing University of Posts and Telecommunications, Nanjing, 210046, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Automation, Nanjing University of Posts and Telecommunications, Nanjing, 210046, China#TAB#","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101470634","display_name":"Zhe Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Shi","raw_affiliation_strings":["School of Automation, Nanjing University of Posts and Telecommunications, Nanjing, China","School of Automation, Nanjing University of Posts and Telecommunications, Nanjing, 210046, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Automation, Nanjing University of Posts and Telecommunications, Nanjing, 210046, China#TAB#","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"518","last_page":"521"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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":0.9994999766349792,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.839603066444397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.779962420463562},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7499079704284668},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7437920570373535},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6182905435562134},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5989936590194702},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.586132824420929},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.536294162273407},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5318489074707031},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5267937779426575},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5205891728401184},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4947647452354431},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4454105794429779},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.43808454275131226},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.42340680956840515},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4001673460006714},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.38781827688217163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.839603066444397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.779962420463562},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7499079704284668},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7437920570373535},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6182905435562134},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5989936590194702},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.586132824420929},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.536294162273407},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5318489074707031},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5267937779426575},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5205891728401184},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4947647452354431},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4454105794429779},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.43808454275131226},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.42340680956840515},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4001673460006714},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.38781827688217163},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mva.2015.7153244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mva.2015.7153244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 14th IAPR International Conference on Machine Vision Applications (MVA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W54257720","https://openalex.org/W308556676","https://openalex.org/W1514027499","https://openalex.org/W1570963478","https://openalex.org/W1572401739","https://openalex.org/W1963520111","https://openalex.org/W1993882792","https://openalex.org/W1995997122","https://openalex.org/W2007972815","https://openalex.org/W2017637319","https://openalex.org/W2022261771","https://openalex.org/W2027922120","https://openalex.org/W2052684427","https://openalex.org/W2114227971","https://openalex.org/W2130325614","https://openalex.org/W2136922672","https://openalex.org/W2151103935","https://openalex.org/W2162762921","https://openalex.org/W2162915993","https://openalex.org/W2293078015","https://openalex.org/W2557865186","https://openalex.org/W2963346784","https://openalex.org/W6602211262","https://openalex.org/W6630792627","https://openalex.org/W6677288107","https://openalex.org/W6697139924","https://openalex.org/W6730042849"],"related_works":["https://openalex.org/W2566406229","https://openalex.org/W3177930984","https://openalex.org/W2052697133","https://openalex.org/W2119028572","https://openalex.org/W2376984068","https://openalex.org/W2152482390","https://openalex.org/W2365617273","https://openalex.org/W2076896210","https://openalex.org/W2506386910","https://openalex.org/W2117928543"],"abstract_inverted_index":{"Multilabel":[0],"image":[1,124],"annotation":[2],"is":[3],"one":[4],"of":[5,76,83,101,118,134],"the":[6,65,81,98,112,116,119,128,132,135],"most":[7],"important":[8],"open":[9],"problems":[10],"in":[11,105,126],"computer":[12],"vision":[13],"field.":[14],"Unlike":[15],"existing":[16],"works":[17],"that":[18,74],"usually":[19],"use":[20],"conventional":[21],"visual":[22],"features":[23,27],"to":[24,35,51,79,89,96],"annotate":[25],"images,":[26],"based":[28],"on":[29,111],"deep":[30,46,55,84],"learning":[31,47,72,78,95],"have":[32],"shown":[33],"potential":[34],"achieve":[36],"outstanding":[37],"performance.":[38],"In":[39,63],"this":[40],"work,":[41],"we":[42],"propose":[43],"a":[44,69,106],"multimodal":[45],"framework,":[48],"which":[49,127],"aims":[50],"optimally":[52],"integrate":[53],"multiple":[54],"neural":[56,61,85],"networks":[57],"pretrained":[58],"with":[59,87],"convolutional":[60],"networks.":[62],"particular,":[64],"proposed":[66,120,136],"framework":[67,121],"explores":[68],"unified":[70],"two-stage":[71],"scheme":[73],"consists":[75],"(i)":[77],"fune-tune":[80],"parameters":[82],"network":[86],"respect":[88],"each":[90],"individual":[91],"modality,":[92],"and":[93],"(ii)":[94],"find":[97],"optimal":[99],"combination":[100],"diverse":[102],"modalities":[103],"simultaneously":[104],"coherent":[107],"process.":[108],"Experiments":[109],"conducted":[110],"NUS-WIDE":[113],"dataset":[114],"evaluate":[115],"performance":[117],"for":[122],"multilabel":[123],"annotation,":[125],"encouraging":[129],"results":[130],"validate":[131],"effectiveness":[133],"algorithms.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}