{"id":"https://openalex.org/W4399418473","doi":"https://doi.org/10.1145/3652583.3658038","title":"UBiSS: A Unified Framework for Bimodal Semantic Summarization of Videos","display_name":"UBiSS: A Unified Framework for Bimodal Semantic Summarization of Videos","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418473","doi":"https://doi.org/10.1145/3652583.3658038"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658038","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658038","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658038","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658038","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048118429","display_name":"Yuting Mei","orcid":"https://orcid.org/0009-0009-6036-8687"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuting Mei","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-6036-8687","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100599428","display_name":"Linli Yao","orcid":"https://orcid.org/0000-0002-9809-8864"},"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":"Linli Yao","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9809-8864","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6486-6020","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048118429"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.2381,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47900391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1034","last_page":"1042"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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/T11439","display_name":"Video Analysis and Summarization","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/T11309","display_name":"Music and Audio Processing","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9908999800682068,"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":0.9688932299613953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8980710506439209},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6243228316307068},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6045536994934082},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5690773129463196},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5417041182518005},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5225027203559875},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4908815026283264},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.48108264803886414},{"id":"https://openalex.org/keywords/multi-document-summarization","display_name":"Multi-document summarization","score":0.460996150970459},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4387854337692261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3502121567726135},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3263760507106781}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9688932299613953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8980710506439209},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6243228316307068},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6045536994934082},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5690773129463196},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5417041182518005},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5225027203559875},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4908815026283264},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48108264803886414},{"id":"https://openalex.org/C134714966","wikidata":"https://www.wikidata.org/wiki/Q6934448","display_name":"Multi-document summarization","level":3,"score":0.460996150970459},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4387854337692261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3502121567726135},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3263760507106781},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3652583.3658038","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658038","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658038","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.16301","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.16301","pdf_url":"https://arxiv.org/pdf/2406.16301","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":"doi:10.1145/3652583.3658038","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658038","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658038","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1899978318","display_name":null,"funder_award_id":"L233008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4419243359","display_name":null,"funder_award_id":"62072462","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G8390650537","display_name":null,"funder_award_id":"62072462","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418473.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1926243429","https://openalex.org/W1956340063","https://openalex.org/W1979354511","https://openalex.org/W2069870183","https://openalex.org/W2097117768","https://openalex.org/W2139501017","https://openalex.org/W2467794422","https://openalex.org/W2529272619","https://openalex.org/W2600463316","https://openalex.org/W2893972119","https://openalex.org/W2902616437","https://openalex.org/W2963916161","https://openalex.org/W2963919999","https://openalex.org/W2964167369","https://openalex.org/W2967219836","https://openalex.org/W2982084422","https://openalex.org/W3027431227","https://openalex.org/W3153469116","https://openalex.org/W3166366124","https://openalex.org/W3197682865","https://openalex.org/W3214448253","https://openalex.org/W3217340782","https://openalex.org/W4206423448","https://openalex.org/W4234552385","https://openalex.org/W4239584046","https://openalex.org/W4312544061","https://openalex.org/W4312560592","https://openalex.org/W4312748990","https://openalex.org/W4313038449","https://openalex.org/W4319049530","https://openalex.org/W4319300174","https://openalex.org/W4386066385","https://openalex.org/W4389161308"],"related_works":["https://openalex.org/W3164984162","https://openalex.org/W2104677027","https://openalex.org/W402673672","https://openalex.org/W2902627734","https://openalex.org/W2112885393","https://openalex.org/W2173208124","https://openalex.org/W2568827738","https://openalex.org/W1990695371","https://openalex.org/W2365100044","https://openalex.org/W1943954554"],"abstract_inverted_index":{"With":[0],"the":[1,4,28,32,80,97,102,106,144],"surge":[2],"in":[3,105],"amount":[5],"of":[6,31,50,143],"video":[7,9,43,107],"data,":[8],"summarization":[10,25,44,158],"techniques,":[11],"including":[12],"visual-modal(VM)":[13],"and":[14,20,108,112,161],"textual-modal(TM)":[15],"summarization,":[16],"are":[17,163],"attracting":[18],"more":[19,21,41],"attention.":[22],"However,":[23],"unimodal":[24],"inevitably":[26],"loses":[27],"rich":[29],"semantics":[30],"video.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37,53,90,133],"focus":[38],"on":[39,88],"a":[40,56,73,92,110,121,135,140],"comprehensive":[42],"task":[45],"named":[46],"Bimodal":[47],"Semantic":[48],"Summarization":[49],"Videos(BiSSV).":[51],"Specifically,":[52],"first":[54],"construct":[55],"large-scale":[57],"dataset,":[58],"BIDS,":[59,89],"in(video,":[60],"VM-Summary,":[61],"TM-Summary)":[62],"triplet":[63],"format.":[64],"Unlike":[65],"traditional":[66],"processing":[67],"methods,":[68],"our":[69,118,150],"construction":[70],"procedure":[71],"contains":[72],"VM-Summary":[74],"extraction":[75],"algorithm":[76],"aiming":[77],"to":[78,125,129,138],"preserve":[79],"most":[81],"salient":[82],"content":[83],"within":[84],"long":[85],"videos.":[86],"Based":[87],"propose":[91,134],"Unified":[93],"framework":[94,152],"UBiSS":[95],"for":[96],"BiSSV":[98],"task,":[99],"which":[100],"models":[101],"saliency":[103],"information":[104],"generates":[109],"TM-summary":[111],"VM-summary":[113],"simultaneously.":[114],"We":[115],"further":[116],"optimize":[117],"model":[119],"with":[120],"list-wise":[122],"ranking-based":[123],"objective":[124],"improve":[126],"its":[127],"capacity":[128],"capture":[130],"highlights.":[131],"Lastly,":[132],"metric,":[136],"NDCGMS,":[137],"provide":[139],"joint":[141],"evaluation":[142],"bimodal":[145],"summary.":[146],"Experiments":[147],"show":[148],"that":[149],"unified":[151],"achieves":[153],"better":[154],"performance":[155],"than":[156],"multi-stage":[157],"pipelines.":[159],"Code":[160],"data":[162],"available":[164],"at":[165],"https://github.com/MeiYutingg/UBiSS.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}