{"id":"https://openalex.org/W3205377310","doi":"https://doi.org/10.1145/3474085.3475236","title":"Latent Memory-augmented Graph Transformer for Visual Storytelling","display_name":"Latent Memory-augmented Graph Transformer for Visual Storytelling","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205377310","doi":"https://doi.org/10.1145/3474085.3475236","mag":"3205377310"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475236","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th 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/A5103041611","display_name":"Mengshi Qi","orcid":"https://orcid.org/0000-0002-6955-6635"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengshi Qi","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061215231","display_name":"Jie Qin","orcid":"https://orcid.org/0000-0002-0306-534X"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Qin","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056972984","display_name":"Di Huang","orcid":"https://orcid.org/0000-0002-2412-9330"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Huang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015367334","display_name":"Zhiqiang Shen","orcid":"https://orcid.org/0000-0002-3749-3115"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiqiang Shen","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005421447","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"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":"Yi Yang","raw_affiliation_strings":["University of Technology Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5277,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89511673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4892","last_page":"4901"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9955000281333923,"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":0.9937000274658203,"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":0.7969886064529419},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5667057037353516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5657987594604492},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.5094044804573059},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4977701008319855},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43700796365737915},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4235534965991974},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3961920440196991},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3443247973918915},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3330867886543274},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.27354806661605835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7969886064529419},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5667057037353516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5657987594604492},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.5094044804573059},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4977701008319855},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43700796365737915},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4235534965991974},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3961920440196991},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3443247973918915},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3330867886543274},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27354806661605835},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3474085.3475236","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-115121","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-115121","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-115121","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-115121","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5799999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1924770834","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2137095888","https://openalex.org/W2183386595","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2506483933","https://openalex.org/W2549599535","https://openalex.org/W2556388456","https://openalex.org/W2559780844","https://openalex.org/W2579549467","https://openalex.org/W2607119937","https://openalex.org/W2626778328","https://openalex.org/W2739107216","https://openalex.org/W2766126435","https://openalex.org/W2768287968","https://openalex.org/W2795840542","https://openalex.org/W2804668597","https://openalex.org/W2886641317","https://openalex.org/W2896325387","https://openalex.org/W2914868535","https://openalex.org/W2931316642","https://openalex.org/W2949474740","https://openalex.org/W2951343884","https://openalex.org/W2951901104","https://openalex.org/W2952103128","https://openalex.org/W2953106684","https://openalex.org/W2953486038","https://openalex.org/W2962835968","https://openalex.org/W2963033554","https://openalex.org/W2963187786","https://openalex.org/W2963351113","https://openalex.org/W2963536419","https://openalex.org/W2963668753","https://openalex.org/W2963829244","https://openalex.org/W2963858333","https://openalex.org/W2963902384","https://openalex.org/W2963916161","https://openalex.org/W2964199361","https://openalex.org/W2965597639","https://openalex.org/W2966774251","https://openalex.org/W2968549119","https://openalex.org/W2969862959","https://openalex.org/W2970597249","https://openalex.org/W2971310675","https://openalex.org/W2981575209","https://openalex.org/W2981750519","https://openalex.org/W2981994675","https://openalex.org/W2982255917","https://openalex.org/W2990818246","https://openalex.org/W2996941455","https://openalex.org/W2998106530","https://openalex.org/W2998178282","https://openalex.org/W2998303222","https://openalex.org/W3022778813","https://openalex.org/W3034655362","https://openalex.org/W3035237998","https://openalex.org/W3037785019","https://openalex.org/W3048921104","https://openalex.org/W3049493117","https://openalex.org/W3087871082","https://openalex.org/W3092674849","https://openalex.org/W3093026747","https://openalex.org/W3093272234","https://openalex.org/W3093272873","https://openalex.org/W3093344337","https://openalex.org/W3093352373","https://openalex.org/W3093455776","https://openalex.org/W3095299523","https://openalex.org/W3100054454","https://openalex.org/W3100995281","https://openalex.org/W3101632758","https://openalex.org/W3103651098","https://openalex.org/W3106477714","https://openalex.org/W3128401049","https://openalex.org/W4287992577","https://openalex.org/W4297909472","https://openalex.org/W4299128829","https://openalex.org/W4301156730","https://openalex.org/W4302602837"],"related_works":["https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W41015297","https://openalex.org/W4387129494"],"abstract_inverted_index":{"Visual":[0],"storytelling":[1],"aims":[2],"to":[3,110],"automatically":[4],"generate":[5],"a":[6,43,50,76,81],"human-like":[7],"short":[8],"story":[9,56,135],"given":[10],"an":[11,120],"image":[12,30,95,139],"stream.":[13],"Most":[14],"existing":[15],"works":[16],"utilize":[17],"either":[18],"scene-level":[19],"or":[20],"object-level":[21],"representations,":[22],"neglecting":[23],"the":[24,32,61,64,86,91,105,134,138,142,152,158],"interaction":[25],"among":[26,94],"objects":[27],"in":[28],"each":[29],"and":[31,80,97,115,127,141],"sequential":[33],"dependency":[34],"between":[35],"consecutive":[36],"images.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41,118],"present":[42],"novel":[44],"Latent":[45],"Memory-augmented":[46],"Graph":[47],"Transformer~(LMGT":[48],"),":[49],"Transformer":[51],"based":[52,103],"framework":[53],"for":[54],"visual":[55,101],"generation.":[57],"LMGT":[58,156],"directly":[59],"inherits":[60],"merits":[62],"from":[63,137],"Transformer,":[65],"which":[66],"is":[67],"further":[68],"enhanced":[69],"with":[70],"two":[71],"carefully":[72],"designed":[73],"components,":[74],"i.e.,":[75],"graph":[77,87],"encoding":[78,88],"module":[79,89],"latent":[82,122,131],"memory":[83,123],"unit.":[84],"Specifically,":[85],"exploits":[90],"semantic":[92],"relationships":[93],"regions":[96],"attentively":[98],"aggregates":[99],"critical":[100],"features":[102],"on":[104,147],"parsed":[106],"scene":[107],"graphs.":[108],"Furthermore,":[109],"better":[111],"preserve":[112],"inter-sentence":[113],"coherence":[114],"topic":[116],"consistency,":[117],"introduce":[119],"augmented":[121],"unit":[124],"that":[125],"learns":[126],"records":[128],"highly":[129],"summarized":[130],"information":[132],"as":[133],"line":[136],"stream":[140],"sentence":[143],"history.":[144],"Experimental":[145],"results":[146],"three":[148],"widely-used":[149],"datasets":[150],"demonstrate":[151],"superior":[153],"performance":[154],"of":[155],"over":[157],"state-of-the-art":[159],"methods.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}