{"id":"https://openalex.org/W4304092243","doi":"https://doi.org/10.1145/3503161.3548161","title":"Ordered Attention for Coherent Visual Storytelling","display_name":"Ordered Attention for Coherent Visual Storytelling","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304092243","doi":"https://doi.org/10.1145/3503161.3548161"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548161","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548161","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.02180","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082254010","display_name":"Tom Braude","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125051","display_name":"Microsoft (Israel)","ror":"https://ror.org/03819cc96","country_code":"IL","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210125051"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Tom Braude","raw_affiliation_strings":["Reichman University & Microsoft, Hertzliya, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reichman University & Microsoft, Hertzliya, Israel","institution_ids":["https://openalex.org/I4210125051"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082617813","display_name":"Idan Schwartz","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Idan Schwartz","raw_affiliation_strings":["Technion, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069704585","display_name":"Alex Schwing","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Schwing","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022467818","display_name":"Ariel Shamir","orcid":"https://orcid.org/0000-0001-7082-7845"},"institutions":[{"id":"https://openalex.org/I4210093787","display_name":"Herzliya Medical Center","ror":"https://ror.org/00m6hsp80","country_code":"IL","type":"healthcare","lineage":["https://openalex.org/I4210093787"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ariel Shamir","raw_affiliation_strings":["Reichman University, Hertzliya, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reichman University, Hertzliya, Israel","institution_ids":["https://openalex.org/I4210093787"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5899,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76744516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3310","last_page":"3318"},"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":0.9972000122070312,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9970999956130981,"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/storytelling","display_name":"Storytelling","score":0.6952869296073914},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5394372344017029},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3241526484489441},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.15703508257865906},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.13773170113563538},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.06931054592132568}],"concepts":[{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.6952869296073914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5394372344017029},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3241526484489441},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.15703508257865906},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.13773170113563538},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.06931054592132568}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3548161","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548161","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.02180","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.02180","pdf_url":"https://arxiv.org/pdf/2108.02180","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.02180","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.02180","pdf_url":"https://arxiv.org/pdf/2108.02180","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5600000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1895989618","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2183341477","https://openalex.org/W2745461083","https://openalex.org/W2963668753","https://openalex.org/W2963954913","https://openalex.org/W2964218959","https://openalex.org/W2964330332","https://openalex.org/W2996941455","https://openalex.org/W3016923549","https://openalex.org/W3087871082","https://openalex.org/W3101632758","https://openalex.org/W3109320561","https://openalex.org/W3205377310","https://openalex.org/W4206749883"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2884441370","https://openalex.org/W1536421369","https://openalex.org/W2086118318","https://openalex.org/W2082193010","https://openalex.org/W4319988281","https://openalex.org/W2993120730","https://openalex.org/W1765898938","https://openalex.org/W2970945984"],"abstract_inverted_index":{"We":[0],"address":[1],"the":[2,62,90,93,98,106,120,124],"problem":[3],"of":[4,15],"visual":[5],"storytelling,":[6],"i.e.,":[7],"generating":[8],"a":[9,12,23,26,76,101,130],"story":[10,19,28,63],"for":[11,80],"given":[13],"sequence":[14],"images.":[16,41,50],"While":[17],"each":[18],"sentence":[20],"should":[21],"describe":[22],"corresponding":[24],"image,":[25],"coherent":[27],"also":[29],"needs":[30],"to":[31,36,54,96],"be":[32],"consistent":[33],"and":[34,39,136],"relate":[35],"both":[37],"future":[38,69],"past":[40,66],"Current":[42],"approaches":[43],"encode":[44,55],"images":[45,56,91],"independently,":[46],"disregarding":[47],"relations":[48],"between":[49],"Our":[51],"approach":[52],"learns":[53],"with":[57,111],"different":[58],"interactions":[59,87,140],"based":[60],"on":[61,123],"position":[64],"(i.e.,":[65],"image":[67,82,108],"or":[68],"image).":[70],"To":[71],"this":[72],"end,":[73],"we":[74],"develop":[75],"novel":[77],"message-passing-like":[78],"algorithm":[79],"ordered":[81],"attention":[83,103,109],"(OIA)":[84],"that":[85,138],"collects":[86],"across":[88],"all":[89],"in":[92],"sequence.":[94],"Finally,":[95],"generate":[97],"story's":[99],"sentences,":[100],"second":[102],"mechanism":[104],"picks":[105],"important":[107],"vectors":[110],"an":[112],"Image-Sentence":[113],"Attention":[114],"(ISA).":[115],"The":[116],"obtained":[117],"results":[118],"improve":[119,142],"METEOR":[121],"score":[122],"VIST":[125],"dataset":[126],"by":[127],"1%.":[128],"Furthermore,":[129],"thorough":[131],"human":[132],"study":[133],"confirms":[134],"improvements":[135],"demonstrates":[137],"order-based":[139],"significantly":[141],"coherency":[143],"(64.20%":[144],"\\vs":[145],"28.70%).":[146],"Source":[147],"code":[148],"available":[149],"at":[150],"\\urlhttps://github.com/tomateb/OIAVist.git":[151]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}