{"id":"https://openalex.org/W2962938439","doi":"https://doi.org/10.1109/tip.2019.2928144","title":"Re-Caption: Saliency-Enhanced Image Captioning Through Two-Phase Learning","display_name":"Re-Caption: Saliency-Enhanced Image Captioning Through Two-Phase Learning","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2962938439","doi":"https://doi.org/10.1109/tip.2019.2928144","mag":"2962938439","pmid":"https://pubmed.ncbi.nlm.nih.gov/31331893"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2019.2928144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2019.2928144","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/A5101897650","display_name":"Lian Zhou","orcid":"https://orcid.org/0000-0001-8394-1698"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lian Zhou","raw_affiliation_strings":["School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070073283","display_name":"Yuejie Zhang","orcid":"https://orcid.org/0000-0001-7993-7223"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuejie Zhang","raw_affiliation_strings":["School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375722","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0001-7561-0143"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["School of Information Management and Engineering, Shanghai Key Laboratory of Financial Information Technology, Shanghai University of Finance and Economics, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Information Management and Engineering, Shanghai Key Laboratory of Financial Information Technology, Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075964389","display_name":"Weiguo Fan","orcid":"https://orcid.org/0000-0003-1272-5538"},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiguo Fan","raw_affiliation_strings":["Department of Business Analytics, The University of Iowa, Iowa City, IA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Business Analytics, The University of Iowa, Iowa City, IA, USA","institution_ids":["https://openalex.org/I126307644"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101897650"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":3.9854,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.95065124,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"694","last_page":"709"},"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/T11605","display_name":"Visual Attention and Saliency Detection","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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9757288098335266},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.789623498916626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.689272940158844},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.6276044845581055},{"id":"https://openalex.org/keywords/saliency-map","display_name":"Saliency map","score":0.5532273650169373},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5275235772132874},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5131595730781555},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4989449977874756},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41786131262779236},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3520854115486145}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9757288098335266},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789623498916626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.689272940158844},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.6276044845581055},{"id":"https://openalex.org/C2779679900","wikidata":"https://www.wikidata.org/wiki/Q25304431","display_name":"Saliency map","level":3,"score":0.5532273650169373},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5275235772132874},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5131595730781555},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4989449977874756},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41786131262779236},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3520854115486145},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2019.2928144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2019.2928144","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:31331893","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31331893","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":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2372857774","display_name":null,"funder_award_id":"61976057","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G292109295","display_name":null,"funder_award_id":"61572140","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5101276346","display_name":null,"funder_award_id":"19ZR1417200","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320310841","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":112,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W648786980","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1632114991","https://openalex.org/W1686810756","https://openalex.org/W1706899115","https://openalex.org/W1772076007","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1934890906","https://openalex.org/W1956340063","https://openalex.org/W1994922096","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2101105183","https://openalex.org/W2112912048","https://openalex.org/W2130942839","https://openalex.org/W2133459682","https://openalex.org/W2133564696","https://openalex.org/W2143449221","https://openalex.org/W2147697413","https://openalex.org/W2154652894","https://openalex.org/W2163605009","https://openalex.org/W2176263492","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2296073425","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2510850444","https://openalex.org/W2518599539","https://openalex.org/W2520274358","https://openalex.org/W2528092473","https://openalex.org/W2552161745","https://openalex.org/W2558906385","https://openalex.org/W2560920409","https://openalex.org/W2563296158","https://openalex.org/W2575842049","https://openalex.org/W2586820357","https://openalex.org/W2604522653","https://openalex.org/W2612135493","https://openalex.org/W2729842244","https://openalex.org/W2753232960","https://openalex.org/W2754927243","https://openalex.org/W2757028014","https://openalex.org/W2774267535","https://openalex.org/W2780708736","https://openalex.org/W2788154928","https://openalex.org/W2798791651","https://openalex.org/W2807746031","https://openalex.org/W2884326683","https://openalex.org/W2887272576","https://openalex.org/W2948537313","https://openalex.org/W2950800384","https://openalex.org/W2962760898","https://openalex.org/W2962835968","https://openalex.org/W2962849532","https://openalex.org/W2962935746","https://openalex.org/W2962949934","https://openalex.org/W2962965915","https://openalex.org/W2962982762","https://openalex.org/W2963084599","https://openalex.org/W2963201326","https://openalex.org/W2963248296","https://openalex.org/W2963334022","https://openalex.org/W2963499204","https://openalex.org/W2963529609","https://openalex.org/W2963635628","https://openalex.org/W2963685207","https://openalex.org/W2963868681","https://openalex.org/W2964049455","https://openalex.org/W2964114039","https://openalex.org/W2964121744","https://openalex.org/W2964168617","https://openalex.org/W2964308564","https://openalex.org/W2965638232","https://openalex.org/W3098145348","https://openalex.org/W3101840568","https://openalex.org/W3104979525","https://openalex.org/W3122238731","https://openalex.org/W6600334730","https://openalex.org/W6621543089","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6637356508","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6674330103","https://openalex.org/W6676647902","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6681184217","https://openalex.org/W6682631176","https://openalex.org/W6684191040","https://openalex.org/W6685322675","https://openalex.org/W6714138976","https://openalex.org/W6725435199","https://openalex.org/W6729046916","https://openalex.org/W6730707965","https://openalex.org/W6736588697","https://openalex.org/W6741068176","https://openalex.org/W6744684495","https://openalex.org/W6747225742","https://openalex.org/W6748037084","https://openalex.org/W6749312877","https://openalex.org/W6763116793","https://openalex.org/W6765942151","https://openalex.org/W6766404499","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Visual":[0],"and":[1,46,55,73,165,175],"semantic":[2,47,87],"saliency":[3,17,20,45,48,66,71,75,83,88,110,117,139,157],"are":[4,49],"important":[5],"in":[6,101],"image":[7,11,39,79,127,152],"captioning.":[8,40,128],"However,":[9],"single-phase":[10,38],"captioning":[12,153,163],"benefits":[13],"little":[14],"from":[15,51],"limited":[16],"without":[18,80],"a":[19,25,70,74,82,102,156],"predictor.":[21,85],"In":[22,41,129],"this":[23],"paper,":[24],"novel":[26],"saliency-enhanced":[27,181],"re-captioning":[28],"framework":[29,148],"via":[30],"two-phase":[31],"learning":[32,81],"is":[33,111,144],"proposed":[34,112],"to":[35,113,132],"enhance":[36],"the":[37,42,52,58,94,116,134,173,180],"framework,":[43],"visual":[44,65],"distilled":[50],"first-phase":[53],"model":[54,60,62,154],"fused":[56],"with":[57,98],"second-phase":[59],"for":[61,77,124,140],"self-boosting.":[63],"The":[64,86,168],"mechanism":[67,89],"can":[68,149,183],"generate":[69],"map":[72,84],"mask":[76],"an":[78,151],"sheds":[90],"some":[91],"lights":[92],"on":[93,171],"properties":[95],"of":[96,107,119,138],"words":[97],"part-of-speech":[99],"Noun":[100],"caption.":[103],"Besides,":[104],"another":[105],"type":[106],"saliency,":[108],"sample":[109],"explicitly":[114],"compute":[115],"degree":[118],"each":[120],"sample,":[121],"which":[122,159],"helps":[123],"more":[125],"robust":[126],"addition,":[130],"how":[131],"combine":[133],"above":[135],"three":[136],"types":[137],"further":[141],"performance":[142,186],"boost":[143],"also":[145],"examined.":[146],"Our":[147],"treat":[150],"as":[155],"extractor,":[158],"may":[160],"benefit":[161],"other":[162],"models":[164,182],"related":[166],"tasks.":[167],"experimental":[169],"results":[170],"both":[172],"Flickr30k":[174],"MSCOCO":[176],"datasets":[177],"show":[178],"that":[179],"obtain":[184],"promising":[185],"gains.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}