{"id":"https://openalex.org/W3003478339","doi":"https://doi.org/10.1109/tip.2020.2969330","title":"Image Captioning With End-to-End Attribute Detection and Subsequent Attributes Prediction","display_name":"Image Captioning With End-to-End Attribute Detection and Subsequent Attributes Prediction","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3003478339","doi":"https://doi.org/10.1109/tip.2020.2969330","mag":"3003478339","pmid":"https://pubmed.ncbi.nlm.nih.gov/32012014"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2020.2969330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.2969330","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5058825605","display_name":"Yiqing Huang","orcid":"https://orcid.org/0000-0002-2143-3329"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqing Huang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2143-3329","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668653","display_name":"Jiansheng Chen","orcid":"https://orcid.org/0000-0002-2040-7938"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiansheng Chen","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2040-7938","affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Beijing, China","institution_ids":["https://openalex.org/I4210156423"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087818121","display_name":"Wanli Ouyang","orcid":"https://orcid.org/0000-0002-9163-2761"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wanli Ouyang","raw_affiliation_strings":["School of Electrical and Information Engineering, The University of Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9163-2761","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100784791","display_name":"Weitao Wan","orcid":"https://orcid.org/0000-0002-6601-4873"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weitao Wan","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Beijing, China","institution_ids":["https://openalex.org/I4210156423"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015660577","display_name":"Youze Xue","orcid":"https://orcid.org/0000-0002-7054-5204"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youze Xue","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7054-5204","affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Beijing, China","institution_ids":["https://openalex.org/I4210156423"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.0375,"has_fulltext":false,"cited_by_count":104,"citation_normalized_percentile":{"value":0.97239143,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"4013","last_page":"4026"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9945999979972839,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9929999709129333,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.7875897884368896},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7875738739967346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6498047709465027},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6171057224273682},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5066050291061401},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.47772976756095886},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.42940041422843933},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41032886505126953},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3885711431503296},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.0844634473323822}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7875897884368896},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7875738739967346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6498047709465027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6171057224273682},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5066050291061401},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.47772976756095886},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.42940041422843933},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41032886505126953},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3885711431503296},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0844634473323822}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2020.2969330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.2969330","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:32012014","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32012014","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5552182671","display_name":null,"funder_award_id":"61673234","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1903029394","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2154652894","https://openalex.org/W2164290393","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2274287116","https://openalex.org/W2302086703","https://openalex.org/W2346746376","https://openalex.org/W2425121537","https://openalex.org/W2506483933","https://openalex.org/W2552161745","https://openalex.org/W2556388456","https://openalex.org/W2558834163","https://openalex.org/W2560346187","https://openalex.org/W2575842049","https://openalex.org/W2613718673","https://openalex.org/W2619947201","https://openalex.org/W2625940279","https://openalex.org/W2745461083","https://openalex.org/W2754927243","https://openalex.org/W2884561390","https://openalex.org/W2890531016","https://openalex.org/W2932399282","https://openalex.org/W2938603906","https://openalex.org/W2951390634","https://openalex.org/W2953461088","https://openalex.org/W2962681491","https://openalex.org/W2962760898","https://openalex.org/W2962934715","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2964018924","https://openalex.org/W2964121744","https://openalex.org/W2964350391","https://openalex.org/W2984862483","https://openalex.org/W6620707391","https://openalex.org/W6621543089","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6694260854","https://openalex.org/W6744684495","https://openalex.org/W6766991472","https://openalex.org/W6898505805","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W3164229987","https://openalex.org/W4299590256","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W2151749779"],"abstract_inverted_index":{"Semantic":[0],"attention":[1,19],"has":[2],"been":[3],"shown":[4],"to":[5,23,27,29,49,78,92,94,108,178,198,206],"be":[6],"effective":[7,121],"in":[8,160,216,252],"improving":[9],"the":[10,25,38,42,50,54,59,69,73,80,89,120,140,148,153,166,169,174,200,214,218,221,235,241,250],"performance":[11,230],"of":[12,17,53,123,156,171,202,231],"image":[13,114,149,175,203,254],"captioning.":[14],"The":[15,133,182,260],"core":[16],"semantic":[18,55],"based":[20,209],"methods":[21],"is":[22],"drive":[24],"model":[26,91,229],"attend":[28,93],"semantically":[30],"important":[31],"words,":[32],"or":[33],"attributes.":[34,204],"In":[35],"previous":[36,207],"works,":[37],"attribute":[39,111,135,141,184,192,208,257],"detector":[40,136],"and":[41,173,224,256],"captioning":[43,90,115,162,255],"network":[44],"are":[45,66,76,262],"usually":[46],"independent,":[47],"leading":[48],"insufficient":[51],"usage":[52],"information.":[56],"Also,":[57],"all":[58],"detected":[60],"attributes,":[61],"no":[62],"matter":[63],"whether":[64],"they":[65],"appropriate":[67,127],"for":[68],"linguistic":[70],"context":[71],"at":[72,129,194],"current":[74],"step,":[75],"attended":[77],"through":[79],"whole":[81],"caption":[82],"generation":[83],"process.":[84],"This":[85],"may":[86],"sometimes":[87],"disrupt":[88],"incorrect":[95],"visual":[96],"concepts.":[97],"To":[98],"solve":[99],"these":[100],"problems,":[101],"we":[102],"introduce":[103],"two":[104],"end-to-end":[105],"trainable":[106],"modules":[107],"closely":[109],"couple":[110],"detection":[112,142,258],"with":[113],"as":[116,118],"well":[117],"prompt":[119],"uses":[122],"attributes":[124,128,157,172,219],"by":[125,144],"predicting":[126],"each":[130,195],"time":[131,196],"step.":[132],"multimodal":[134],"(MAD)":[137],"module":[138,187],"improves":[139,249],"accuracy":[143],"using":[145],"not":[146],"only":[147],"features":[150,177],"but":[151],"also":[152],"word":[154],"embedding":[155],"already":[158],"existing":[159],"most":[161],"models.":[163],"MAD":[164],"models":[165],"similarity":[167],"between":[168],"semantics":[170],"object":[176],"facilitate":[179],"accurate":[180],"detection.":[181],"subsequent":[183],"predictor":[185],"(SAP)":[186],"dynamically":[188],"predicts":[189],"a":[190,226],"concise":[191],"subset":[193],"step":[197],"mitigate":[199],"diversity":[201],"Compared":[205],"methods,":[210],"our":[211,246],"approach":[212],"enhances":[213],"explainability":[215],"how":[217],"affect":[220],"generated":[222],"words":[223],"achieves":[225],"state-of-the-art":[227],"single":[228],"128.8":[232],"CIDEr-D":[233],"on":[234,240],"MSCOCO":[236,242],"dataset.":[237],"Extensive":[238],"experiments":[239],"dataset":[243],"show":[244],"that":[245],"proposal":[247],"actually":[248],"performances":[251],"both":[253],"simultaneously.":[259],"codes":[261],"available":[263],"at:":[264],"https://github.com/":[265],"RubickH/Image-Captioning-with-MAD-and-SAP.":[266]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}