{"id":"https://openalex.org/W4408347295","doi":"https://doi.org/10.1109/icassp49660.2025.10890236","title":"Video-Poetry Retrieval with Multimodal Knowledge Graph Guided Unsupervised Pre-training","display_name":"Video-Poetry Retrieval with Multimodal Knowledge Graph Guided Unsupervised Pre-training","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347295","doi":"https://doi.org/10.1109/icassp49660.2025.10890236"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5112233597","display_name":"Xinru Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinru Wei","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Computer Science","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379933","display_name":"Yuqing Li","orcid":"https://orcid.org/0000-0002-2357-7107"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqing Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Computer Science","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043114890","display_name":"Bin Wu","orcid":"https://orcid.org/0000-0001-5787-9536"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Computer Science","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9794999957084656,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9544000029563904,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7928725481033325},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49771931767463684},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4634777009487152},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.45528990030288696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4295186400413513},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35987937450408936},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.08290901780128479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928725481033325},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49771931767463684},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4634777009487152},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.45528990030288696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4295186400413513},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35987937450408936},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.08290901780128479}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2896124351","https://openalex.org/W2952771545","https://openalex.org/W2981851019","https://openalex.org/W2984008963","https://openalex.org/W2999137220","https://openalex.org/W3035265375","https://openalex.org/W3168640669","https://openalex.org/W3176481196","https://openalex.org/W3204588463","https://openalex.org/W3213454282","https://openalex.org/W4280643747","https://openalex.org/W4285606530","https://openalex.org/W4304014690","https://openalex.org/W4312245858","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312999114","https://openalex.org/W4376607849","https://openalex.org/W4385573407","https://openalex.org/W4385573585","https://openalex.org/W4386072365","https://openalex.org/W4386076661","https://openalex.org/W4392908910","https://openalex.org/W4402660133","https://openalex.org/W6793736971","https://openalex.org/W6796559658","https://openalex.org/W6843263998","https://openalex.org/W6846157311","https://openalex.org/W6852060543","https://openalex.org/W6852908585","https://openalex.org/W6854451932","https://openalex.org/W6856659047","https://openalex.org/W6859272024","https://openalex.org/W6864544085","https://openalex.org/W6869164663"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W4387849428","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Classical":[0],"Chinese":[1,69,113],"poetry,":[2],"with":[3],"its":[4],"rich":[5],"cultural":[6],"heritage,":[7],"holds":[8],"immense":[9],"artistic":[10],"value.":[11],"Recently,":[12],"research":[13,24],"on":[14,27,94],"multi-modal":[15,108],"approaches":[16],"to":[17,64,101,115],"classical":[18,68,112],"poetry":[19,28,70,114],"has":[20],"garnered":[21],"attention.":[22],"Current":[23],"mainly":[25],"focuses":[26],"and":[29,71,74,125,143],"images,":[30],"but":[31],"images":[32],"cannot":[33],"fully":[34],"capture":[35],"dynamic":[36],"scenes":[37],"like":[38],"sunrises.":[39],"However,":[40],"the":[41,65,75,117,146],"inherent":[42],"temporal":[43],"nature":[44,77],"of":[45,78,111,148],"video":[46],"can":[47],"vividly":[48],"present":[49],"these":[50,103],"scene":[51],"transitions.":[52],"In":[53],"this":[54,141],"paper,":[55],"we":[56,134],"introduce":[57],"a":[58,89,107,137],"novel":[59],"task:":[60],"video-poetry":[61,90,131,138],"retrieval.":[62],"Due":[63],"disparities":[66],"between":[67],"modern":[72],"Chinese,":[73],"time-consuming":[76],"traditional":[79],"supervised":[80],"methods":[81,97],"for":[82,140],"collecting":[83],"parallel":[84],"data.":[85],"We":[86],"propose":[87],"VPR-MLCL,":[88],"pre-training":[91,96],"model":[92],"based":[93],"unsupervised":[95],"from":[98,122],"vision-language":[99],"field":[100],"address":[102],"issues.":[104],"VPR-MLCL":[105],"uses":[106],"knowledge":[109],"graph":[110],"bridge":[116],"gap,":[118],"learning":[119],"cross-modal":[120],"alignment":[121],"video-caption":[123],"pairs":[124],"poetry-image":[126],"entities":[127],"rather":[128],"than":[129],"direct":[130],"pairs.":[132],"Additionally,":[133],"have":[135],"constructed":[136],"dataset":[139],"task,":[142],"experiments":[144],"demonstrate":[145],"effectiveness":[147],"VPR-MLCL.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}