{"id":"https://openalex.org/W4312834987","doi":"https://doi.org/10.1145/3561613.3561641","title":"Image-Based Storytelling Using Deep Learning","display_name":"Image-Based Storytelling Using Deep Learning","publication_year":2022,"publication_date":"2022-08-19","ids":{"openalex":"https://openalex.org/W4312834987","doi":"https://doi.org/10.1145/3561613.3561641"},"language":"en","primary_location":{"id":"doi:10.1145/3561613.3561641","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3561613.3561641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 The 5th International Conference on Control and Computer Vision","raw_type":"proceedings-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/A5110952523","display_name":"Yulin Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Yulin Zhu","raw_affiliation_strings":["Department of Computer Science, Auckland University of Technology, New Zealand"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Auckland University of Technology, New Zealand","institution_ids":["https://openalex.org/I39854758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064286235","display_name":"Wei Qi Yan","orcid":"https://orcid.org/0009-0006-5891-9919"},"institutions":[{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Wei Qi Yan","raw_affiliation_strings":["Department of Computer Science, Auckland University of Technology, New Zealand"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Auckland University of Technology, New Zealand","institution_ids":["https://openalex.org/I39854758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110952523"],"corresponding_institution_ids":["https://openalex.org/I39854758"],"apc_list":null,"apc_paid":null,"fwci":0.604,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.6802214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"179","last_page":"186"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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":0.9943000078201294,"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":0.9593485593795776},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8393145799636841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6797386407852173},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.6599029302597046},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6445592641830444},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5804312229156494},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.486345112323761},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4830342233181},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4554275572299957},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4374050199985504},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4198477268218994}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9593485593795776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8393145799636841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6797386407852173},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.6599029302597046},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6445592641830444},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5804312229156494},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.486345112323761},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4830342233181},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4554275572299957},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4374050199985504},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4198477268218994},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3561613.3561641","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3561613.3561641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 The 5th International Conference on Control and Computer Vision","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W323291900","https://openalex.org/W639708223","https://openalex.org/W1534234985","https://openalex.org/W1576278180","https://openalex.org/W1689711448","https://openalex.org/W2032005922","https://openalex.org/W2076063813","https://openalex.org/W2109255472","https://openalex.org/W2112796928","https://openalex.org/W2131774270","https://openalex.org/W2525579820","https://openalex.org/W2613718673","https://openalex.org/W2753588101","https://openalex.org/W2767361967","https://openalex.org/W2789876780","https://openalex.org/W2795061970","https://openalex.org/W2885195348","https://openalex.org/W2901187378","https://openalex.org/W2909267201","https://openalex.org/W2910522659","https://openalex.org/W2916310631","https://openalex.org/W2947411064","https://openalex.org/W2963073938","https://openalex.org/W3014952138","https://openalex.org/W3023402713","https://openalex.org/W3035245013","https://openalex.org/W3104769336","https://openalex.org/W3157914904","https://openalex.org/W4205275628","https://openalex.org/W4235988989","https://openalex.org/W4237786406","https://openalex.org/W4246853483","https://openalex.org/W4246999471","https://openalex.org/W4247924304","https://openalex.org/W4255556797","https://openalex.org/W6736419893"],"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":{"In":[0,96],"order":[1],"to":[2,57,107,129,149],"describe":[3],"a":[4,6,13,30,59,92],"journey,":[5],"story":[7],"could":[8],"be":[9],"automatically":[10,90],"generated":[11],"from":[12,74,133],"group":[14],"of":[15,19,26,29,39,70,119,126,139,157],"digital":[16,75,112],"photographs.":[17],"Most":[18],"the":[20,42,45,78,86,140,147,151],"existing":[21],"methods":[22],"focus":[23],"on":[24,64],"descriptions":[25],"specific":[27],"content":[28,136],"single":[31],"image,":[32],"such":[33],"as":[34,142],"image":[35,102],"captioning,":[36,103],"which":[37],"lack":[38],"correlation":[40,110],"between":[41,111],"images":[43,113,141,148],"and":[44,83,114,137],"spatiotemporal":[46,81],"relationships.":[47],"To":[48],"this":[49,52,97,120],"end,":[50],"in":[51,80,85],"paper,":[53],"our":[54,104],"goal":[55],"is":[56],"propose":[58],"novel":[60],"storytelling":[61],"architecture":[62],"based":[63],"computer":[65],"vision.":[66],"It":[67],"makes":[68],"use":[69,125],"visual":[71],"object":[72],"detection":[73],"images.":[76],"Combining":[77],"changes":[79],"domain":[82],"filling":[84],"predetermined":[87],"template,":[88],"we":[89],"generate":[91,130],"text-based":[93],"travel":[94,131],"diary.":[95],"project,":[98],"compared":[99],"with":[100],"conventional":[101],"aims":[105],"are":[106],"effectively":[108],"connect":[109],"background":[115],"information.":[116],"The":[117],"contributions":[118],"paper":[121],"are:":[122],"(1)":[123],"Innovative":[124],"preset":[127],"templates":[128],"diaries":[132],"photographs,":[134],"associating":[135],"context":[138],"an":[143],"event,":[144],"(3)":[145],"augmenting":[146],"expand":[150],"dataset,":[152],"(4)":[153],"shortening":[154],"training":[155],"time":[156],"deep":[158],"learning":[159],"models.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}