{"id":"https://openalex.org/W2963829244","doi":"https://doi.org/10.1609/aaai.v33i01.33018909","title":"Hierarchical Photo-Scene Encoder for Album Storytelling","display_name":"Hierarchical Photo-Scene Encoder for Album Storytelling","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2963829244","doi":"https://doi.org/10.1609/aaai.v33i01.33018909","mag":"2963829244"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33018909","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018909","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4918/4791","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4918/4791","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008341143","display_name":"Bairui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bairui Wang","raw_affiliation_strings":["Shandong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017116858","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0002-7331-6132"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100756628","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0001-5556-3896"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Shandong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024453719","display_name":"Wenhao Jiang","orcid":"https://orcid.org/0000-0002-0795-366X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Jiang","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100401285","display_name":"Feng Zhang","orcid":"https://orcid.org/0000-0002-7995-918X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhang","raw_affiliation_strings":["Tencent AILab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AILab","institution_ids":["https://openalex.org/I2250653659"]}]}],"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":true,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"8909","last_page":"8916"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.989799976348877,"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/T11439","display_name":"Video Analysis and Summarization","score":0.989799976348877,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9871000051498413,"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":0.9715999960899353,"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/encoder","display_name":"Encoder","score":0.8592672348022461},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7893491983413696},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.6620814204216003},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6058787107467651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.603223979473114},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48987361788749695},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4786471128463745},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.42348411679267883},{"id":"https://openalex.org/keywords/scene-statistics","display_name":"Scene statistics","score":0.4111725389957428},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.07386213541030884}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.8592672348022461},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893491983413696},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.6620814204216003},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6058787107467651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.603223979473114},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48987361788749695},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4786471128463745},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.42348411679267883},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.4111725389957428},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.07386213541030884},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33018909","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018909","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4918/4791","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4918","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33018909","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018909","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4918/4791","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G130684094","display_name":null,"funder_award_id":"2017YFB1300205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4302921741","display_name":null,"funder_award_id":"2016JC014","funder_id":"https://openalex.org/F4320311026","funder_display_name":"Shandong University"},{"id":"https://openalex.org/G5189178657","display_name":null,"funder_award_id":"61573222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320311026","display_name":"Shandong University","ror":"https://ror.org/0207yh398"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963829244.pdf","grobid_xml":"https://content.openalex.org/works/W2963829244.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1606748815","https://openalex.org/W1895577753","https://openalex.org/W1916445035","https://openalex.org/W1956340063","https://openalex.org/W2112912048","https://openalex.org/W2117539524","https://openalex.org/W2123301721","https://openalex.org/W2139501017","https://openalex.org/W2140676672","https://openalex.org/W2154652894","https://openalex.org/W2183386595","https://openalex.org/W2194775991","https://openalex.org/W2242818861","https://openalex.org/W2273041409","https://openalex.org/W2546938941","https://openalex.org/W2556388456","https://openalex.org/W2559780844","https://openalex.org/W2604141702","https://openalex.org/W2678677036","https://openalex.org/W2744208073","https://openalex.org/W2755513316","https://openalex.org/W2788710361","https://openalex.org/W2794504309","https://openalex.org/W2796239628","https://openalex.org/W2800990595","https://openalex.org/W2885013662","https://openalex.org/W2890502146","https://openalex.org/W2894963073","https://openalex.org/W2962799512","https://openalex.org/W2963033554","https://openalex.org/W2963084599","https://openalex.org/W2963551569","https://openalex.org/W2963672682","https://openalex.org/W2963843052","https://openalex.org/W2964253311","https://openalex.org/W3098682680","https://openalex.org/W6639657675","https://openalex.org/W6680375555","https://openalex.org/W6682631176","https://openalex.org/W6687483927","https://openalex.org/W6729383884","https://openalex.org/W6730061300","https://openalex.org/W6730083651","https://openalex.org/W6735368939","https://openalex.org/W6748308768","https://openalex.org/W6750865830","https://openalex.org/W6753850902","https://openalex.org/W6753985741","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2997512100","https://openalex.org/W2331043530","https://openalex.org/W2275988210","https://openalex.org/W2393933887","https://openalex.org/W1891287906","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2166024367"],"abstract_inverted_index":{"In":[0,121],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,9,14,104,112,133],"novel":[6],"model":[7,153],"with":[8],"hierarchical":[10,186],"photo-scene":[11,23,187],"encoder":[12,24,56,188],"and":[13,31,38,85,93,99,189],"reconstructor":[15,134],"for":[16,60,80],"the":[17,29,44,48,54,74,82,90,96,126,139,145,149,168,171,181,184],"task":[18],"of":[19,47,106,115,148,183],"album":[20,107,141],"storytelling.":[21],"The":[22,69,151],"contains":[25],"two":[26],"subencoders,":[27],"namely":[28],"photo":[30,55,62,76,98],"scene":[32,70,83,87,100],"encoders,":[33],"which":[34,111,161],"are":[35],"stacked":[36],"together":[37],"behave":[39],"hierarchically":[40],"to":[41,102,123,137],"fully":[42,124],"exploit":[43],"structure":[45],"information":[46,129],"photos":[49],"within":[50],"an":[51,131,158,164],"album.":[52],"Specifically,":[53],"generates":[57],"semantic":[58,128],"representation":[59],"each":[61],"while":[63],"exploiting":[64],"temporal":[65],"relationships":[66],"among":[67],"them.":[68],"encoder,":[71],"relying":[72],"on":[73,110,144,170],"obtained":[75],"representations,":[77,108],"is":[78,119,135],"responsible":[79],"detecting":[81],"changes":[84],"generating":[86],"representations.":[88],"Subsequently,":[89],"decoder":[91],"dynamically":[92],"attentively":[94],"summarizes":[95],"encoded":[97],"representations":[101,142],"generate":[103],"sequence":[105],"based":[109,143],"story":[113],"consisting":[114],"multiple":[116],"coherent":[117],"sentences":[118],"generated.":[120],"order":[122],"extract":[125],"useful":[127],"from":[130],"album,":[132],"employed":[136],"reproduce":[138],"summarized":[140],"hidden":[146],"states":[147],"decoder.":[150],"proposed":[152,185],"can":[154],"be":[155],"trained":[156],"in":[157,163],"end-to-end":[159],"manner,":[160],"results":[162],"improved":[165],"performance":[166],"over":[167],"state-of-the-arts":[169],"public":[172],"visual":[173],"storytelling":[174],"(VIST)":[175],"dataset.":[176],"Ablation":[177],"studies":[178],"further":[179],"demonstrate":[180],"effectiveness":[182],"reconstructor.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}