{"id":"https://openalex.org/W3039115681","doi":"https://doi.org/10.1109/tip.2020.3004729","title":"Spatio-Temporal Memory Attention for Image Captioning","display_name":"Spatio-Temporal Memory Attention for Image Captioning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3039115681","doi":"https://doi.org/10.1109/tip.2020.3004729","mag":"3039115681"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2020.3004729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.3004729","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"],"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/A5035117617","display_name":"Junzhong Ji","orcid":"https://orcid.org/0000-0001-6951-741X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junzhong Ji","raw_affiliation_strings":["Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, China","Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101854034","display_name":"Cheng Xu","orcid":"https://orcid.org/0000-0001-5371-1218"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Xu","raw_affiliation_strings":["Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, China","Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356742","display_name":"Xiaodan Zhang","orcid":"https://orcid.org/0000-0001-7002-5447"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Zhang","raw_affiliation_strings":["Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, China","Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091545406","display_name":"Boyue Wang","orcid":"https://orcid.org/0000-0002-2677-8342"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyue Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computer Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computer Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055504013","display_name":"Xinhang Song","orcid":"https://orcid.org/0000-0002-0895-1076"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhang Song","raw_affiliation_strings":["Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, China","Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5035117617"],"corresponding_institution_ids":["https://openalex.org/I37796252","https://openalex.org/I4210100255"],"apc_list":null,"apc_paid":null,"fwci":5.3978,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.96719001,"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":"7615","last_page":"7628"},"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":0.9972000122070312,"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":0.9911999702453613,"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":0.9939068555831909},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7955813407897949},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.7016180753707886},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5749595761299133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5433789491653442},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4508589506149292},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36058974266052246},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32192426919937134},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.11367514729499817},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07856616377830505}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9939068555831909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955813407897949},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.7016180753707886},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5749595761299133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5433789491653442},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4508589506149292},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36058974266052246},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32192426919937134},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.11367514729499817},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07856616377830505}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tip.2020.3004729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.3004729","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1658396367","display_name":null,"funder_award_id":"61672065","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5486436434","display_name":null,"funder_award_id":"61902378","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6774628417","display_name":null,"funder_award_id":"KM202010005014","funder_id":"https://openalex.org/F4320325902","funder_display_name":"Beijing Municipal Science and Technology Commission"},{"id":"https://openalex.org/G783030459","display_name":null,"funder_award_id":"61906011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G89121010","display_name":null,"funder_award_id":"61906007","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/F4320325902","display_name":"Beijing Municipal Science and Technology Commission","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W68733909","https://openalex.org/W956551720","https://openalex.org/W1497599070","https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1793121960","https://openalex.org/W1811254738","https://openalex.org/W1858383477","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2064675550","https://openalex.org/W2089597841","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2105103432","https://openalex.org/W2109586012","https://openalex.org/W2121029939","https://openalex.org/W2122710056","https://openalex.org/W2127120487","https://openalex.org/W2133512280","https://openalex.org/W2133564696","https://openalex.org/W2135726080","https://openalex.org/W2144715671","https://openalex.org/W2147527908","https://openalex.org/W2149172860","https://openalex.org/W2154652894","https://openalex.org/W2164084182","https://openalex.org/W2164364459","https://openalex.org/W2169461290","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2293453011","https://openalex.org/W2295763703","https://openalex.org/W2296385829","https://openalex.org/W2302086703","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2884326683","https://openalex.org/W2887272576","https://openalex.org/W2890531016","https://openalex.org/W2900953995","https://openalex.org/W2908056713","https://openalex.org/W2950527759","https://openalex.org/W2951008357","https://openalex.org/W2951527505","https://openalex.org/W2953106684","https://openalex.org/W2962706528","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963344337","https://openalex.org/W2963403868","https://openalex.org/W2963579811","https://openalex.org/W2964018924","https://openalex.org/W2964308564","https://openalex.org/W2969262604","https://openalex.org/W4246876997","https://openalex.org/W4303633609","https://openalex.org/W4385245566","https://openalex.org/W6600334730","https://openalex.org/W6620707391","https://openalex.org/W6625044600","https://openalex.org/W6630875275","https://openalex.org/W6637373629","https://openalex.org/W6638318767","https://openalex.org/W6638742206","https://openalex.org/W6639102338","https://openalex.org/W6639118148","https://openalex.org/W6676497082","https://openalex.org/W6679434410","https://openalex.org/W6681516684","https://openalex.org/W6682086108","https://openalex.org/W6682137061","https://openalex.org/W6682631176","https://openalex.org/W6684821475","https://openalex.org/W6697449767","https://openalex.org/W6732742072","https://openalex.org/W6739901393","https://openalex.org/W6756383013","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/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W3217388757","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W3161816943"],"abstract_inverted_index":{"Visual":[0],"attention":[1,23,64,70,79,94,103,115,132,142,145,202],"has":[2],"been":[3],"successfully":[4],"applied":[5],"in":[6,24,69,102,146,196,201],"image":[7,26,74,105,180,208],"captioning":[8,27,75,181],"to":[9,16,77,97,113,127,140,176],"selectively":[10],"incorporate":[11],"the":[12,17,22,33,49,60,66,78,99,110,114,122,131,135,163,171,189,192,198,205],"most":[13],"relevant":[14,54],"areas":[15,51,168],"language":[18,37],"generation":[19],"procedure.":[20],"However,":[21],"current":[25,206],"methods":[28],"is":[29,71,125,138,174],"only":[30],"guided":[31],"by":[32],"hidden":[34],"state":[35],"of":[36,63,82,159,166,191],"model,":[38],"e.g.":[39],"LSTM":[40],"(Long-Short":[41],"Term":[42],"Memory),":[43],"indirectly":[44],"and":[45,47,129,134,152,161,203],"implicitly,":[46],"thus":[48],"attended":[50,167],"are":[52],"weakly":[53],"at":[55],"different":[56],"time":[57],"steps.":[58],"Besides":[59],"spatial":[61],"relationship":[62,68,101,165,200],"areas,":[65],"temporal":[67,157],"crucial":[72],"for":[73,104],"according":[76],"transmission":[80],"mechanism":[81,112],"human":[83],"vision.":[84],"In":[85],"this":[86],"paper,":[87],"we":[88],"propose":[89],"a":[90,118],"new":[91,123],"spatio-temporal":[92,100,164,199],"memory":[93,111,150],"(STMA)":[95],"model":[96,116,195],"learn":[98],"captioning.":[106,209],"The":[107,144],"STMA":[108,147,173,194],"introduces":[109],"through":[117],"tailored":[119],"LSTM,":[120],"where":[121],"cell":[124],"used":[126,139],"memorize":[128],"propagate":[130],"information,":[133],"output":[136],"gate":[137],"generate":[141],"weights.":[143],"transmits":[148],"with":[149,178],"adaptively":[151],"dependently,":[153],"which":[154],"builds":[155],"strong":[156],"connections":[158],"attentions":[160],"learns":[162],"simultaneously.":[169],"Besides,":[170],"proposed":[172,193],"flexible":[175],"combine":[177],"attention-based":[179,207],"frameworks.":[182],"Experiments":[183],"on":[184],"MS":[185],"COCO":[186],"dataset":[187],"demonstrate":[188],"superiority":[190],"exploring":[197],"improving":[204]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}