{"id":"https://openalex.org/W3172393158","doi":"https://doi.org/10.1109/icme51207.2021.9428353","title":"Show, Rethink, And Tell: Image Caption Generation With Hierarchical Topic Cues","display_name":"Show, Rethink, And Tell: Image Caption Generation With Hierarchical Topic Cues","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3172393158","doi":"https://doi.org/10.1109/icme51207.2021.9428353","mag":"3172393158"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100352729","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0002-9493-4976"},"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,410073"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,P. R. China,410073","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102335557","display_name":"Songxian Xie","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":"Songxian Xie","raw_affiliation_strings":["National University of Defense Technology,Changsha,P. R. China,410073"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,P. R. China,410073","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103153115","display_name":"Xinyi Li","orcid":"https://orcid.org/0000-0002-5389-4859"},"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,410073"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,P. R. China,410073","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,410073"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,P. R. China,410073","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034793034","display_name":"Kunyuan Pang","orcid":"https://orcid.org/0000-0002-9477-4458"},"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":"Kunyuan Pang","raw_affiliation_strings":["National University of Defense Technology,Changsha,P. R. China,410073"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,P. R. China,410073","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,410073"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,P. R. China,410073","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024544230","display_name":"Ting Wang","orcid":"https://orcid.org/0000-0002-3344-6231"},"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,410073"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,P. R. China,410073","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":0.2864,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58882146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9901000261306763,"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":0.9884999990463257,"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":0.9905146360397339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8566471338272095},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5809140205383301},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5803608894348145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5567919015884399},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.532319962978363},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4706035554409027},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4561831057071686},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4252150058746338},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07570895552635193}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9905146360397339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8566471338272095},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5809140205383301},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5803608894348145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5567919015884399},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.532319962978363},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4706035554409027},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4561831057071686},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4252150058746338},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07570895552635193},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme51207.2021.9428353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1880262756","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2506483933","https://openalex.org/W2552161745","https://openalex.org/W2560920409","https://openalex.org/W2745461083","https://openalex.org/W2754927243","https://openalex.org/W2885013662","https://openalex.org/W2889730805","https://openalex.org/W2896457183","https://openalex.org/W2914849303","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2965846473","https://openalex.org/W2967019968","https://openalex.org/W2973642807","https://openalex.org/W2983141445","https://openalex.org/W3035323998","https://openalex.org/W3039115681","https://openalex.org/W3045147787","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6639619044","https://openalex.org/W6678262379","https://openalex.org/W6730665891","https://openalex.org/W6739901393","https://openalex.org/W6754119793","https://openalex.org/W6755207826","https://openalex.org/W6767200354","https://openalex.org/W6781025829","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3217195652","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W3217388757","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W4252364083"],"abstract_inverted_index":{"Current":[0],"state-of-the-art":[1,145],"approaches":[2],"for":[3,127],"image":[4,23],"captioning":[5,38,82],"mainly":[6],"apply":[7],"the":[8,37,103,110,132],"encoder-decoder":[9],"framework":[10],"with":[11],"attention":[12,27],"mechanisms,":[13],"most":[14],"of":[15,22,100,105],"which":[16,66],"ignore":[17],"interactions":[18,93],"between":[19,94],"different":[20],"types":[21],"features":[24,99,117],"and":[25,63,96],"perform":[26],"operations":[28],"only":[29],"once":[30],"per":[31],"word.":[32],"The":[33],"mentioned":[34],"problems":[35],"limit":[36],"model\u2019s":[39],"capability":[40],"to":[41,45,54,69,84,112,120],"capture":[42,70],"sufficient":[43],"information":[44],"generate":[46],"high-quality":[47],"captions.":[48],"By":[49],"contrast,":[50],"humans":[51],"often":[52],"rethink":[53],"polish":[55],"up":[56],"descriptions":[57],"by":[58,91],"re-focusing":[59],"on":[60,131],"more":[61],"correct":[62],"important":[64],"information,":[65],"is":[67],"hard":[68],"at":[71],"first":[72,111],"glance.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77,108],"introduce":[78],"a":[79,87],"novel":[80],"topic-guided":[81],"model":[83,140],"imitate":[85],"such":[86],"human\u2019s":[88],"rethinking":[89,126],"process":[90],"modeling":[92],"visual":[95,122],"hierarchical":[97,115],"semantic":[98,116],"topics.":[101],"To":[102],"best":[104],"our":[106,138],"knowledge,":[107],"are":[109],"effectively":[113],"consider":[114],"as":[118],"guidance":[119],"facilitate":[121],"attention,":[123],"achieving":[124],"human-like":[125],"captioning.":[128],"Extensive":[129],"experiments":[130],"MS":[133],"COCO":[134],"dataset":[135],"show":[136],"that":[137],"proposed":[139],"achieves":[141],"superior":[142],"performance":[143],"over":[144],"methods.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}