{"id":"https://openalex.org/W2963187786","doi":"https://doi.org/10.18653/v1/d17-1101","title":"Hierarchically-Attentive RNN for Album Summarization and Storytelling","display_name":"Hierarchically-Attentive RNN for Album Summarization and Storytelling","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2963187786","doi":"https://doi.org/10.18653/v1/d17-1101","mag":"2963187786"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1101","pdf_url":"https://www.aclweb.org/anthology/D17-1101.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D17-1101.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036418431","display_name":"Licheng Yu","orcid":"https://orcid.org/0000-0002-4943-6732"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Licheng Yu","raw_affiliation_strings":["UNC Chapel Hill"],"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I1333535994","https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001987532","display_name":"Mohit Bansal","orcid":"https://orcid.org/0000-0001-5522-1351"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohit Bansal","raw_affiliation_strings":["UNC Chapel Hill"],"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I1333535994","https://openalex.org/I114027177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008309880","display_name":"Tamara L. Berg","orcid":"https://orcid.org/0000-0002-1272-3359"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamara Berg","raw_affiliation_strings":["UNC Chapel Hill"],"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I1333535994","https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036418431"],"corresponding_institution_ids":["https://openalex.org/I114027177","https://openalex.org/I1333535994"],"apc_list":null,"apc_paid":null,"fwci":3.7886,"has_fulltext":true,"cited_by_count":72,"citation_normalized_percentile":{"value":0.96184502,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9994000196456909,"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":0.9973000288009644,"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/automatic-summarization","display_name":"Automatic summarization","score":0.9284502267837524},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.8451992273330688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8145720958709717},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6758893728256226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5973042249679565},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5868898630142212},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5831001996994019},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5075496435165405},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5006632804870605},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46210822463035583},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.21087148785591125},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19926705956459045},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07674551010131836}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9284502267837524},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.8451992273330688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8145720958709717},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6758893728256226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5973042249679565},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5868898630142212},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5831001996994019},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5075496435165405},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5006632804870605},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46210822463035583},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.21087148785591125},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19926705956459045},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07674551010131836},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d17-1101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1101","pdf_url":"https://www.aclweb.org/anthology/D17-1101.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1101","pdf_url":"https://www.aclweb.org/anthology/D17-1101.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1818042607","display_name":"RI: Medium: Collaborative Research: Text-to-Image Reference Resolution for Image Understanding and Manipulation","funder_award_id":"1562098","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7890117278","display_name":"BIGDATA: F: Collaborative Research: From Visual Data to Visual Understanding","funder_award_id":"1633295","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G884832516","display_name":"RI: Medium: Integrating Humans and Computers for Image and Video Understanding","funder_award_id":"1445409","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963187786.pdf","grobid_xml":"https://content.openalex.org/works/W2963187786.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1843891098","https://openalex.org/W1895577753","https://openalex.org/W1904325426","https://openalex.org/W1914581815","https://openalex.org/W1947481528","https://openalex.org/W1957740064","https://openalex.org/W1984899418","https://openalex.org/W1995945562","https://openalex.org/W2103908291","https://openalex.org/W2112077341","https://openalex.org/W2115857089","https://openalex.org/W2120645068","https://openalex.org/W2138779671","https://openalex.org/W2139501017","https://openalex.org/W2183386595","https://openalex.org/W2194775991","https://openalex.org/W2307381258","https://openalex.org/W2335943242","https://openalex.org/W2507756961","https://openalex.org/W2508429489","https://openalex.org/W2592375459","https://openalex.org/W2914699769","https://openalex.org/W2962905474","https://openalex.org/W2962965405","https://openalex.org/W2963220254","https://openalex.org/W2963576560","https://openalex.org/W2963919999","https://openalex.org/W2964173634","https://openalex.org/W3103014337","https://openalex.org/W4299341000","https://openalex.org/W4310299640"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W1517524280","https://openalex.org/W4389760904","https://openalex.org/W4306886878","https://openalex.org/W4323520239"],"abstract_inverted_index":{"We":[0],"address":[1],"the":[2,16,29,38,55,64],"problem":[3],"of":[4,37,46],"end-to-end":[5],"visual":[6],"storytelling.":[7],"Given":[8],"a":[9,24,43],"photo":[10],"album,":[11],"our":[12,71],"model":[13,44,72],"first":[14],"selects":[15],"most":[17],"representative":[18,59],"(summary)":[19,60],"photos,":[20,57,61],"and":[21,42,62,67,79],"then":[22],"composes":[23],"natural":[25],"language":[26],"story":[27],"for":[28],"album.":[30],"For":[31],"this":[32],"task,":[33],"we":[34],"make":[35],"use":[36],"Visual":[39],"Storytelling":[40],"dataset":[41],"composed":[45],"three":[47],"hierarchically-attentive":[48],"Recurrent":[49],"Neural":[50],"Nets":[51],"(RNNs)":[52],"to:":[53],"encode":[54],"album":[56],"select":[58],"compose":[63],"story.":[65],"Automatic":[66],"human":[68],"evaluations":[69],"show":[70],"achieves":[73],"better":[74],"performance":[75],"on":[76],"selection,":[77],"generation,":[78],"retrieval":[80],"than":[81],"baselines.":[82]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":10}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}