{"id":"https://openalex.org/W3201420176","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533418","title":"Looking Back and Forward: Enhancing Image Captioning with Global Semantic Guidance","display_name":"Looking Back and Forward: Enhancing Image Captioning with Global Semantic Guidance","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3201420176","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533418","mag":"3201420176"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5100699149","display_name":"Chen Feng","orcid":"https://orcid.org/0000-0002-6726-0259"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":["National University of Defense Technology, Changsha, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, P.R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102152035","display_name":"Jintao Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jintao Tang","raw_affiliation_strings":["National University of Defense Technology, Changsha, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, P.R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376019","display_name":"Shasha Li","orcid":"https://orcid.org/0000-0002-6508-5119"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shasha Li","raw_affiliation_strings":["National University of Defense Technology, Changsha, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, P.R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370278","display_name":"Xinyi Li","orcid":"https://orcid.org/0000-0002-4346-066X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Li","raw_affiliation_strings":["National University of Defense Technology, Changsha, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, P.R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100427905","display_name":"Ting Wang","orcid":"https://orcid.org/0000-0001-8545-1844"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Wang","raw_affiliation_strings":["National University of Defense Technology, Changsha, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, P.R. China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11338231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9959999918937683,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.974429726600647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8676866292953491},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6163631677627563},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.601793110370636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5456380248069763},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5373361110687256},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5253212451934814},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4952491819858551},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.46082058548927307},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4586932063102722},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4356675148010254},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32803231477737427},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08461394906044006},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07497167587280273}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.974429726600647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8676866292953491},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6163631677627563},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.601793110370636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5456380248069763},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5373361110687256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5253212451934814},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4952491819858551},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.46082058548927307},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4586932063102722},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4356675148010254},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32803231477737427},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08461394906044006},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07497167587280273},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G4821546698","display_name":null,"funder_award_id":"62002373,61690203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8901340350","display_name":null,"funder_award_id":"2018YFB1004502","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2130942839","https://openalex.org/W2154652894","https://openalex.org/W2176263492","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2552161745","https://openalex.org/W2560313346","https://openalex.org/W2560920409","https://openalex.org/W2575842049","https://openalex.org/W2604178507","https://openalex.org/W2745461083","https://openalex.org/W2754927243","https://openalex.org/W2885013662","https://openalex.org/W2887585070","https://openalex.org/W2889730805","https://openalex.org/W2890531016","https://openalex.org/W2911285743","https://openalex.org/W2914849303","https://openalex.org/W2950178297","https://openalex.org/W2962760898","https://openalex.org/W2962968835","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963248296","https://openalex.org/W2963403868","https://openalex.org/W2963623904","https://openalex.org/W2964121744","https://openalex.org/W2965697393","https://openalex.org/W2965846473","https://openalex.org/W2970569830","https://openalex.org/W2973642807","https://openalex.org/W2986670728","https://openalex.org/W3020826863","https://openalex.org/W3035323998","https://openalex.org/W3039115681","https://openalex.org/W3105136412","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6639102338","https://openalex.org/W6678262379","https://openalex.org/W6679436768","https://openalex.org/W6685322675","https://openalex.org/W6730665891","https://openalex.org/W6744684495","https://openalex.org/W6767200354","https://openalex.org/W6767736480"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2275988210","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Image":[0],"captioning":[1,13,175],"requires":[2],"models":[3,176],"to":[4,27,39,61,69,102,115,129,154,165,172],"translate":[5],"an":[6,29],"image":[7,30,94],"into":[8,31],"natural":[9],"language":[10],"description.":[11],"Recent":[12],"methods":[14],"are":[15,67],"mostly":[16],"based":[17],"on":[18,181],"the":[19,25,41,47,50,56,63,75,80,83,117,126,141,157,160,182],"popular":[20,174],"encoder-decoder":[21],"framework,":[22],"which":[23],"uses":[24],"encoder":[26],"encode":[28],"a":[32,37,92,108,122],"set":[33],"of":[34,74,79,91],"vectors":[35],"and":[36,143,162,177],"decoder":[38,51,124],"produce":[40,166],"caption":[42,86,119],"word-by-word.":[43],"However,":[44],"when":[45],"generating":[46],"next":[48],"word,":[49],"only":[52],"looks":[53],"back":[54],"at":[55],"preceding":[57],"words":[58],"but":[59,95],"fails":[60],"foresee":[62],"posterior":[64],"ones":[65],"that":[66,100,189],"supposed":[68],"be":[70,103],"produced,":[71],"lacking":[72],"awareness":[73],"global":[76,88,131],"semantic":[77,89,132,142,161],"information":[78,90,164],"image.":[81],"Moreover,":[82],"existing":[84],"generated":[85],"provides":[87],"given":[93],"sometimes":[96],"contains":[97],"inconsistent":[98],"content":[99],"needs":[101],"fixed.":[104],"This":[105],"paper":[106],"proposes":[107],"novel":[109],"Temporal-Free":[110],"Semantic-Guided":[111],"attention":[112],"mechanism":[113],"(TFSG)":[114],"utilize":[116],"raw":[118],"pre-generated":[120],"by":[121,139],"primary":[123],"as":[125],"extra":[127],"input":[128],"provide":[130],"guidance":[133],"during":[134],"generation,":[135],"deepening":[136],"visual":[137,144,163],"understanding":[138],"balancing":[140],"information.":[145],"Specifically,":[146],"we":[147],"design":[148],"two":[149,173],"attention-based":[150],"structures":[151],"for":[152],"TFSG":[153,171],"selectively":[155],"take":[156],"essence":[158],"from":[159],"refined":[167],"descriptions.":[168],"We":[169],"apply":[170],"conduct":[178],"extensive":[179],"experiments":[180],"public":[183],"MS":[184],"COCO":[185],"benchmark.":[186],"Results":[187],"show":[188],"our":[190],"proposed":[191],"model":[192],"achieves":[193],"superior":[194],"performance":[195],"over":[196],"many":[197],"state-of-the-art":[198],"models.":[199]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}