{"id":"https://openalex.org/W2965922392","doi":"https://doi.org/10.1109/tmm.2019.2931815","title":"Recall What You See Continually Using GridLSTM in Image Captioning","display_name":"Recall What You See Continually Using GridLSTM in Image Captioning","publication_year":2019,"publication_date":"2019-07-29","ids":{"openalex":"https://openalex.org/W2965922392","doi":"https://doi.org/10.1109/tmm.2019.2931815","mag":"2965922392"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2019.2931815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2931815","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5061646454","display_name":"Lingxiang Wu","orcid":"https://orcid.org/0000-0001-9346-3597"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lingxiang Wu","raw_affiliation_strings":["Global Big Data Technologies Centre, School of Electrical and Data Engineering, University of Technology Sydney, Ultimo, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9346-3597","affiliations":[{"raw_affiliation_string":"Global Big Data Technologies Centre, School of Electrical and Data Engineering, University of Technology Sydney, Ultimo, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413849","display_name":"Min Xu","orcid":"https://orcid.org/0000-0001-9581-8849"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Min Xu","raw_affiliation_strings":["Global Big Data Technologies Centre, School of Electrical and Data Engineering, University of Technology Sydney, Ultimo, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9581-8849","affiliations":[{"raw_affiliation_string":"Global Big Data Technologies Centre, School of Electrical and Data Engineering, University of Technology Sydney, Ultimo, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058420913","display_name":"Jinqiao Wang","orcid":"https://orcid.org/0000-0002-9118-2780"},"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinqiao Wang","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9118-2780","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038845225","display_name":"Stuart Perry","orcid":"https://orcid.org/0000-0002-2794-3178"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Stuart Perry","raw_affiliation_strings":["Perceptual Imaging Laboratory (PILab), School of Electrical and Data Engineering, University of Technology Sydney, Ultimo, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2794-3178","affiliations":[{"raw_affiliation_string":"Perceptual Imaging Laboratory (PILab), School of Electrical and Data Engineering, University of Technology Sydney, Ultimo, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.949,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.93164533,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"22","issue":"3","first_page":"808","last_page":"818"},"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":0.9984999895095825,"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":0.9944000244140625,"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":0.9490042924880981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8617417216300964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5984604358673096},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5563795566558838},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5500126481056213},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5444589257240295},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5234367847442627},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5198169946670532},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4408970773220062},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43361979722976685},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4046306014060974},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3809509873390198},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36755555868148804},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3396286964416504}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9490042924880981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8617417216300964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5984604358673096},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5563795566558838},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5500126481056213},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5444589257240295},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5234367847442627},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5198169946670532},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4408970773220062},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43361979722976685},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4046306014060974},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3809509873390198},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36755555868148804},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3396286964416504},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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":2,"locations":[{"id":"doi:10.1109/tmm.2019.2931815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2931815","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/136813","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/136813","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W1669302834","https://openalex.org/W1686810756","https://openalex.org/W1687846465","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1923211482","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1961891967","https://openalex.org/W2064675550","https://openalex.org/W2066134726","https://openalex.org/W2098407371","https://openalex.org/W2099257174","https://openalex.org/W2101105183","https://openalex.org/W2109586012","https://openalex.org/W2117539524","https://openalex.org/W2133459682","https://openalex.org/W2139380585","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2173180041","https://openalex.org/W2194775991","https://openalex.org/W2197223256","https://openalex.org/W2220981600","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2339652278","https://openalex.org/W2425253808","https://openalex.org/W2463955103","https://openalex.org/W2510373542","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2558834163","https://openalex.org/W2564898401","https://openalex.org/W2565591417","https://openalex.org/W2607151106","https://openalex.org/W2613718673","https://openalex.org/W2739107216","https://openalex.org/W2754689878","https://openalex.org/W2801271919","https://openalex.org/W2950577311","https://openalex.org/W2951183276","https://openalex.org/W2962828890","https://openalex.org/W2962965465","https://openalex.org/W2963084599","https://openalex.org/W2963758027","https://openalex.org/W2964049455","https://openalex.org/W2964121744","https://openalex.org/W3099884890","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6637306801","https://openalex.org/W6637373629","https://openalex.org/W6638205174","https://openalex.org/W6639432524","https://openalex.org/W6639694449","https://openalex.org/W6674758992","https://openalex.org/W6676497082","https://openalex.org/W6682631176","https://openalex.org/W6729046916"],"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/W2330246314","https://openalex.org/W3217195652"],"abstract_inverted_index":{"The":[0,31,156,217,248],"goal":[1],"of":[2,123,235],"image":[3,10,45,49,59,76,93,174,229,246],"captioning":[4],"is":[5,170,196],"to":[6,78,120,127,172,198,271],"automatically":[7],"describe":[8],"an":[9,111],"with":[11,95,153],"a":[12,85,142,166,263],"sentence,":[13],"and":[14,26,35,244,266],"the":[15,23,40,48,57,62,67,74,91,116,121,129,134,154,161,182,186,190,194,200,205,222,227,233,258,272],"task":[16],"has":[17],"attracted":[18],"research":[19,29],"attention":[20,112,130],"from":[21,133,224,226],"both":[22],"computer":[24],"vision":[25],"natural-language":[27],"processing":[28],"communities.":[30],"existing":[32,135],"encoder-decoder":[33,260],"model":[34,261],"its":[36],"variants,":[37],"which":[38,70,103,114],"are":[39,151],"most":[41],"popular":[42],"models":[43],"for":[44,147],"captioning,":[46],"use":[47],"features":[50,60,94,163,202],"in":[51,137],"three":[52],"ways:":[53],"first,":[54],"they":[55,89,109],"inject":[56],"encoded":[58,92],"into":[61],"decoder":[63,195,223],"only":[64],"once":[65],"at":[66,100],"initial":[68],"step,":[69,102],"does":[71],"not":[72],"enable":[73],"rich":[75],"content":[77],"be":[79],"explored":[80],"sufficiently":[81],"while":[82,176],"gradually":[83],"generating":[84,148,177],"text":[86,96],"caption;":[87],"second,":[88],"concatenate":[90],"as":[97,185],"extra":[98,124,212],"inputs":[99],"every":[101],"introduces":[104],"unnecessary":[105],"noise;":[106],"and,":[107,168],"third,":[108],"using":[110,165],"mechanism,":[113],"increases":[115],"computational":[117],"complexity":[118],"due":[119],"introduction":[122],"neural":[125,213],"nets":[126,214],"identify":[128],"regions.":[131],"Different":[132],"methods,":[136],"this":[138],"paper,":[139],"we":[140,238],"propose":[141],"novel":[143],"network,":[144],"Recall":[145,218],"Network,":[146],"captions":[149],"that":[150,253,267],"consistent":[152],"images.":[155],"recall":[157,173,255],"network":[158,256],"selectively":[159],"involves":[160],"visual":[162,183,201],"by":[164,262],"GridLSTM":[167],"thus,":[169],"able":[171,197],"contents":[175],"each":[178],"word.":[179],"By":[180],"importing":[181],"information":[184],"latent":[187],"memory":[188],"along":[189],"depth":[191],"dimension":[192],"LSTM,":[193],"admit":[199],"dynamically":[203],"through":[204],"inherent":[206],"LSTM":[207],"structure":[208],"without":[209],"adding":[210],"any":[211],"or":[215],"parameters.":[216],"Network":[219],"efficiently":[220],"prevents":[221],"deviating":[225],"original":[228],"content.":[230],"To":[231],"verify":[232],"efficiency":[234],"our":[236,254],"model,":[237],"conducted":[239],"exhaustive":[240],"experiments":[241],"on":[242],"full":[243],"dense":[245],"captioning.":[247],"experimental":[249],"results":[250],"clearly":[251],"demonstrate":[252],"outperforms":[257],"conventional":[259],"large":[264],"margin":[265],"it":[268],"performs":[269],"comparably":[270],"state-of-the-art":[273],"methods.":[274]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}