{"id":"https://openalex.org/W2913150433","doi":"https://doi.org/10.1109/tmm.2019.2895511","title":"End-to-End Automatic Image Annotation Based on Deep CNN and Multi-Label Data Augmentation","display_name":"End-to-End Automatic Image Annotation Based on Deep CNN and Multi-Label Data Augmentation","publication_year":2019,"publication_date":"2019-01-25","ids":{"openalex":"https://openalex.org/W2913150433","doi":"https://doi.org/10.1109/tmm.2019.2895511","mag":"2913150433"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2019.2895511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2895511","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5101498868","display_name":"Xiao Ke","orcid":"https://orcid.org/0000-0001-9059-5391"},"institutions":[{"id":"https://openalex.org/I354108","display_name":"Minjiang University","ror":"https://ror.org/00s7tkw17","country_code":"CN","type":"education","lineage":["https://openalex.org/I354108"]},{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Ke","raw_affiliation_strings":["Fujian Key Laboratory of Network Computing and Intelligent Information Processing, College of Mathematics and Computer Science and the Key Laboratory of Spatial Data Mining and Information Sharing, Ministry of Education, Fuzhou University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9059-5391","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Network Computing and Intelligent Information Processing, College of Mathematics and Computer Science and the Key Laboratory of Spatial Data Mining and Information Sharing, Ministry of Education, Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I354108","https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101935966","display_name":"Jiawei Zou","orcid":"https://orcid.org/0000-0003-1549-0340"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Zou","raw_affiliation_strings":["Fujian Key Laboratory of Network Computing and Intelligent Information Processing, College of Mathematics and Computer Science, Fuzhou University, Fuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Network Computing and Intelligent Information Processing, College of Mathematics and Computer Science, Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066931530","display_name":"Yuzhen Niu","orcid":"https://orcid.org/0000-0002-9874-9719"},"institutions":[{"id":"https://openalex.org/I354108","display_name":"Minjiang University","ror":"https://ror.org/00s7tkw17","country_code":"CN","type":"education","lineage":["https://openalex.org/I354108"]},{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhen Niu","raw_affiliation_strings":["Fujian Key Laboratory of Network Computing and Intelligent Information Processing, College of Mathematics and Computer Science and the Key Laboratory of Spatial Data Mining and Information Sharing, Ministry of Education, Fuzhou University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9874-9719","affiliations":[{"raw_affiliation_string":"Fujian Key Laboratory of Network Computing and Intelligent Information Processing, College of Mathematics and Computer Science and the Key Laboratory of Spatial Data Mining and Information Sharing, Ministry of Education, Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I354108","https://openalex.org/I80947539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.3899,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":{"value":0.97926725,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"21","issue":"8","first_page":"2093","last_page":"2106"},"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":0.9991000294685364,"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":0.9991000294685364,"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":0.9984999895095825,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9976000189781189,"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":0.8493506908416748},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.7545779943466187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7545726895332336},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6859132647514343},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6572116613388062},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6458935141563416},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5839419364929199},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5381105542182922},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4956439733505249},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4895056486129761},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43687939643859863},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3392219841480255}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8493506908416748},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.7545779943466187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7545726895332336},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6859132647514343},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6572116613388062},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6458935141563416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5839419364929199},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5381105542182922},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4956439733505249},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4895056486129761},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43687939643859863},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3392219841480255},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2019.2895511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2895511","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2845678394","display_name":null,"funder_award_id":"2018J1798","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G3791469392","display_name":null,"funder_award_id":"61502105","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G725298673","display_name":"\u4e0e\u4e3b\u89c2\u611f\u77e5\u4e00\u81f4\u7684\u7acb\u4f53\u56fe\u50cf\u548c\u89c6\u9891\u89c6\u89c9\u8d28\u91cf\u5ba2\u89c2\u8bc4\u4ef7\u4e0e\u589e\u5f3a\u7814\u7a76","funder_award_id":"61672158","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W121593998","https://openalex.org/W170967611","https://openalex.org/W1510201436","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1877469910","https://openalex.org/W1934863104","https://openalex.org/W1938425378","https://openalex.org/W1992851697","https://openalex.org/W2001903799","https://openalex.org/W2006100391","https://openalex.org/W2025051526","https://openalex.org/W2046315448","https://openalex.org/W2057508887","https://openalex.org/W2069222105","https://openalex.org/W2074327556","https://openalex.org/W2095705004","https://openalex.org/W2099471712","https://openalex.org/W2102969168","https://openalex.org/W2109255472","https://openalex.org/W2114227971","https://openalex.org/W2115517344","https://openalex.org/W2130398002","https://openalex.org/W2137918516","https://openalex.org/W2156336347","https://openalex.org/W2165238043","https://openalex.org/W2172299630","https://openalex.org/W2173520492","https://openalex.org/W2194775991","https://openalex.org/W2283195891","https://openalex.org/W2300822134","https://openalex.org/W2401353841","https://openalex.org/W2513281263","https://openalex.org/W2536305071","https://openalex.org/W2539511637","https://openalex.org/W2574793465","https://openalex.org/W2587063199","https://openalex.org/W2601564443","https://openalex.org/W2618544249","https://openalex.org/W2738881192","https://openalex.org/W2739107216","https://openalex.org/W2742801844","https://openalex.org/W2751445731","https://openalex.org/W2763647787","https://openalex.org/W2786585376","https://openalex.org/W2884624567","https://openalex.org/W2888797051","https://openalex.org/W2904271401","https://openalex.org/W2962835968","https://openalex.org/W2963162313","https://openalex.org/W2963619659","https://openalex.org/W2963684088","https://openalex.org/W3099677434","https://openalex.org/W4320013936","https://openalex.org/W6606917465","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6677204712","https://openalex.org/W6677288107","https://openalex.org/W6684100978","https://openalex.org/W6685352114","https://openalex.org/W6728932512","https://openalex.org/W6742250094","https://openalex.org/W6779669310"],"related_works":["https://openalex.org/W3177930984","https://openalex.org/W2119028572","https://openalex.org/W2052697133","https://openalex.org/W2376984068","https://openalex.org/W2152482390","https://openalex.org/W2365617273","https://openalex.org/W2076896210","https://openalex.org/W2093596879","https://openalex.org/W2384288472","https://openalex.org/W2117928543"],"abstract_inverted_index":{"Automatic":[0],"image":[1,8,11,21,57,68,224],"annotation":[2,22,39,47,58,69,93,225],"is":[3,103],"a":[4,26,72,78,107,127,148,168],"key":[5],"step":[6],"in":[7,159],"retrieval":[9],"and":[10,32,46,172,191],"understanding.":[12],"In":[13],"this":[14],"paper,":[15],"we":[16,52,125],"present":[17],"an":[18,54],"end-to-end":[19,55,92],"automatic":[20,56,223],"method":[23,131],"based":[24,60,132],"on":[25,61,133,208],"deep":[27,62,79,108,169],"convolutional":[28],"neural":[29],"network":[30,185],"(CNN)":[31],"multi-label":[33,73,117,128,150],"data":[34,121,129,145,202],"augmentation.":[35],"Different":[36],"from":[37],"traditional":[38,120],"models":[40],"that":[41,216],"usually":[42],"perform":[43],"feature":[44,87],"extraction":[45],"as":[48],"two":[49],"independent":[50],"tasks,":[51],"propose":[53,126],"model":[59,110,171,200,219],"CNN":[63,80,109,170,180],"(E2E-DCNN).":[64],"E2E-DCNN":[65,199],"transforms":[66],"the":[67,85,91,144,160,163,174,178,184,197,205,217,221],"problem":[70,165],"into":[71],"learning":[74,88],"problem.":[75],"It":[76,102],"uses":[77],"structure":[81,94,186],"to":[82,105],"carry":[83],"out":[84],"adaptive":[86],"before":[89],"constructing":[90],"using":[95,111,119,188],"multiple":[96],"cross-entropy":[97],"loss":[98],"functions":[99],"for":[100],"training.":[101],"difficult":[104],"train":[106],"small-scale":[112],"datasets":[113,118],"or":[114],"scale":[115],"up":[116],"augmentation":[122,130,203],"methods;":[123],"hence,":[124],"Wasserstein":[134],"generative":[135],"adversarial":[136],"networks":[137],"(ML-WGAN).":[138],"The":[139,152,212],"ML-WGAN":[140,156,207],"generator":[141],"can":[142,157],"approximate":[143],"distribution":[146],"of":[147,162,166,177],"single":[149],"image.":[151],"images":[153],"generated":[154],"by":[155,187,204],"assist":[158],"reduction":[161],"over-fitting":[164],"training":[167],"enhance":[173],"generalization":[175],"ability":[176],"trained":[179],"model.":[181],"We":[182,195],"optimize":[183],"deformable":[189],"convolution":[190],"spatial":[192],"pyramid":[193],"pooling.":[194],"experiment":[196],"proposed":[198,206,218],"with":[201],"several":[209],"public":[210],"datasets.":[211],"experimental":[213],"results":[214],"demonstrate":[215],"outperforms":[220],"state-of-the-art":[222],"models.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}