{"id":"https://openalex.org/W2896124351","doi":"https://doi.org/10.1145/3240508.3241910","title":"Images2Poem","display_name":"Images2Poem","publication_year":2018,"publication_date":"2018-10-15","ids":{"openalex":"https://openalex.org/W2896124351","doi":"https://doi.org/10.1145/3240508.3241910","mag":"2896124351"},"language":"en","primary_location":{"id":"doi:10.1145/3240508.3241910","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3241910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th 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/A5100399704","display_name":"Lixin Liu","orcid":"https://orcid.org/0000-0003-0321-279X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lixin Liu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029568096","display_name":"Xiaojun Wan","orcid":"https://orcid.org/0000-0001-6887-1994"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Wan","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001396675","display_name":"Zongming Guo","orcid":"https://orcid.org/0000-0002-4944-9621"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongming Guo","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1967","last_page":"1975"},"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":0.9987999796867371,"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":0.9968000054359436,"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":0.8895373344421387},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6561452746391296},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5987609028816223},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5788069367408752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5610020160675049},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5597251057624817},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.4100556969642639},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3605666756629944},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.25179409980773926},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12093591690063477}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8895373344421387},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6561452746391296},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5987609028816223},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5788069367408752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5610020160675049},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5597251057624817},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4100556969642639},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3605666756629944},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25179409980773926},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12093591690063477},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3240508.3241910","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3241910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2991077894","display_name":null,"funder_award_id":"(61772036, 61331011","funder_id":"https://openalex.org/F4320335595","funder_display_name":"National Natural Science Foundation of China-Yunnan Joint Fund"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335595","display_name":"National Natural Science Foundation of China-Yunnan Joint Fund","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W197120736","https://openalex.org/W342285082","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1902237438","https://openalex.org/W1904325426","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W2014699069","https://openalex.org/W2026189632","https://openalex.org/W2064675550","https://openalex.org/W2069598966","https://openalex.org/W2115221470","https://openalex.org/W2117539524","https://openalex.org/W2139501017","https://openalex.org/W2183386595","https://openalex.org/W2194775991","https://openalex.org/W2307381258","https://openalex.org/W2335943576","https://openalex.org/W2385617402","https://openalex.org/W2552161745","https://openalex.org/W2570565365","https://openalex.org/W2572589325","https://openalex.org/W2575842049","https://openalex.org/W2597655663","https://openalex.org/W2598569220","https://openalex.org/W2609482285","https://openalex.org/W2626778328","https://openalex.org/W2741375528","https://openalex.org/W2766237723","https://openalex.org/W2788148803","https://openalex.org/W2795429538","https://openalex.org/W2950178297","https://openalex.org/W2950476286","https://openalex.org/W2950577311","https://openalex.org/W2950909321","https://openalex.org/W2952136670","https://openalex.org/W2953022248","https://openalex.org/W2962795068","https://openalex.org/W2963187786","https://openalex.org/W2963558617","https://openalex.org/W2963576560","https://openalex.org/W2963919999","https://openalex.org/W2964018924","https://openalex.org/W2964121744","https://openalex.org/W3037108562","https://openalex.org/W3102307539"],"related_works":["https://openalex.org/W2045646185","https://openalex.org/W2487591596","https://openalex.org/W2184903154","https://openalex.org/W3046171011","https://openalex.org/W382594479","https://openalex.org/W4388532907","https://openalex.org/W2620905193","https://openalex.org/W3203142394","https://openalex.org/W3162676893","https://openalex.org/W2389015757"],"abstract_inverted_index":{"Natural":[0],"language":[1],"generation":[2],"from":[3,14,37,80,100],"visual":[4,15],"inputs":[5],"has":[6],"attracted":[7],"extensive":[8],"research":[9],"attention":[10,76],"recently.":[11],"Generating":[12],"poetry":[13,36,99],"content":[16],"is":[17],"an":[18,45,53],"interesting":[19],"but":[20],"very":[21],"challenging":[22],"task.":[23],"We":[24],"propose":[25,44],"and":[26,52,95],"address":[27],"the":[28,58,68,78,93,106,109],"new":[29],"multimedia":[30],"task":[31],"of":[32,108],"generating":[33],"classical":[34],"Chinese":[35],"image":[38,69,83,101],"streams.":[39,102],"In":[40],"this":[41],"paper,":[42],"we":[43],"Images2Poem":[46],"model":[47,61,113],"with":[48],"a":[49],"selection":[50],"mechanism":[51,56],"adaptive":[54],"self-attention":[55],"for":[57],"problem.":[59],"The":[60],"first":[62],"selects":[63],"representative":[64],"images":[65,94],"to":[66,77],"summarize":[67],"stream.":[70],"During":[71],"decoding,":[72],"it":[73],"adaptively":[74],"pays":[75],"information":[79],"either":[81],"source-side":[82],"stream":[84],"or":[85],"target-side":[86],"previously":[87],"generated":[88],"characters.":[89],"It":[90],"jointly":[91],"summarizes":[92],"generates":[96],"relevant,":[97],"high-quality":[98],"Experimental":[103],"results":[104],"demonstrate":[105],"effectiveness":[107],"proposed":[110],"approach.":[111],"Our":[112],"outperforms":[114],"baselines":[115],"in":[116],"different":[117],"human":[118],"evaluation":[119],"metrics.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2018-10-26T00:00:00"}