{"id":"https://openalex.org/W2897464551","doi":"https://doi.org/10.1145/3240508.3240538","title":"Hierarchical Memory Modelling for Video Captioning","display_name":"Hierarchical Memory Modelling for Video Captioning","publication_year":2018,"publication_date":"2018-10-15","ids":{"openalex":"https://openalex.org/W2897464551","doi":"https://doi.org/10.1145/3240508.3240538","mag":"2897464551"},"language":"en","primary_location":{"id":"doi:10.1145/3240508.3240538","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","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/A5112578806","display_name":"Junbo Wang","orcid":"https://orcid.org/0009-0006-9955-7838"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junbo Wang","raw_affiliation_strings":["National Laboratory of Pattern Recognition & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602362","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-7028-9845"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["National Laboratory of Pattern Recognition & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101550628","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-8239-7229"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["National Laboratory of Pattern Recognition & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602506","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5224-8647"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["National Laboratory of Pattern Recognition & Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition & Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111885963","display_name":"Tieniu Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tieniu Tan","raw_affiliation_strings":["National Laboratory of Pattern Recognition & Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition & Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"71"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9986000061035156,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9958000183105469,"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/computer-science","display_name":"Computer science","score":0.9016547799110413},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8601329326629639},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6218533515930176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5757580995559692},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5642229914665222},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5287435054779053},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5256518125534058},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46310633420944214},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4539570212364197},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4435213506221771},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41207262873649597},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3811325430870056},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18019920587539673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9016547799110413},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8601329326629639},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6218533515930176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5757580995559692},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5642229914665222},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5287435054779053},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5256518125534058},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46310633420944214},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4539570212364197},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4435213506221771},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41207262873649597},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3811325430870056},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18019920587539673},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3240508.3240538","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"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":49,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1591801644","https://openalex.org/W1686810756","https://openalex.org/W1714639292","https://openalex.org/W1889081078","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2107878631","https://openalex.org/W2110933980","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2152984213","https://openalex.org/W2164290393","https://openalex.org/W2166010828","https://openalex.org/W2183341477","https://openalex.org/W2251353663","https://openalex.org/W2293453011","https://openalex.org/W2294130536","https://openalex.org/W2302086703","https://openalex.org/W2325920097","https://openalex.org/W2425121537","https://openalex.org/W2507365558","https://openalex.org/W2523937091","https://openalex.org/W2523993696","https://openalex.org/W2552161745","https://openalex.org/W2554906389","https://openalex.org/W2556388456","https://openalex.org/W2557264465","https://openalex.org/W2766375149","https://openalex.org/W2950527759","https://openalex.org/W2951008357","https://openalex.org/W2952238956","https://openalex.org/W2952469094","https://openalex.org/W2963149042","https://openalex.org/W2963576560","https://openalex.org/W2963773578","https://openalex.org/W2963843052","https://openalex.org/W2963937185","https://openalex.org/W2964018924","https://openalex.org/W2964241990","https://openalex.org/W3098682680","https://openalex.org/W4236965008","https://openalex.org/W4285719527","https://openalex.org/W6638318767","https://openalex.org/W6829199633"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Translating":[0],"videos":[1],"into":[2],"natural":[3],"language":[4],"sentences":[5],"has":[6,25],"drawn":[7],"much":[8,27],"attention":[9,16,87],"recently.":[10],"The":[11],"framework":[12],"of":[13,135],"combining":[14],"visual":[15,73],"with":[17,111],"Long":[18],"Short-Term":[19],"Memory":[20,57],"(LSTM)":[21],"based":[22],"text":[23,114,119],"decoder":[24,120],"achieved":[26],"progress.":[28],"However,":[29],"the":[30,38,101,116,124,133,136],"vision-language":[31],"translation":[32],"still":[33],"remains":[34],"unsolved":[35],"due":[36],"to":[37,99],"semantic":[39,48,94,125,164],"gap":[40],"and":[41,46,75,93,107,129,149,163],"misalignment":[42],"between":[43,127],"video":[44,64,90,105,128,161],"content":[45],"described":[47],"concept.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,139],"propose":[54],"a":[55,61,69,72,80],"Hierarchical":[56],"Model":[58],"(HMM)":[59],"-":[60],"novel":[62],"deep":[63],"captioning":[65],"architecture":[66],"which":[67],"unifies":[68],"textual":[70],"memory,":[71],"memory":[74,78],"an":[76],"attribute":[77,95],"in":[79,97],"hierarchical":[81],"way.":[82],"These":[83],"memories":[84],"can":[85,121,158,168],"guide":[86],"for":[88,104],"efficient":[89],"representation":[91,162],"extraction":[92],"selection":[96],"addition":[98],"modelling":[100],"long-term":[102],"dependency":[103],"sequence":[106],"sentences,":[108],"respectively.":[109],"Compared":[110],"traditional":[112],"vision-based":[113],"decoder,":[115],"proposed":[117,137],"attribute-based":[118],"largely":[122],"reduce":[123],"discrepancy":[126],"sentence.":[130],"To":[131],"prove":[132],"effectiveness":[134],"model,":[138],"perform":[140],"extensive":[141],"experiments":[142],"on":[143,177],"two":[144],"public":[145],"benchmark":[146],"datasets:":[147],"MSVD":[148],"MSR-VTT.":[150],"Experiments":[151],"show":[152],"that":[153],"our":[154],"model":[155],"not":[156],"only":[157],"discover":[159],"appropriate":[160],"attributes":[165],"but":[166],"also":[167],"achieve":[169],"comparable":[170],"or":[171],"superior":[172],"performances":[173],"than":[174],"state-of-the-art":[175],"methods":[176],"these":[178],"datasets.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}