{"id":"https://openalex.org/W4408354660","doi":"https://doi.org/10.1109/icassp49660.2025.10889812","title":"CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusion","display_name":"CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusion","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354660","doi":"https://doi.org/10.1109/icassp49660.2025.10889812"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889812","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/A5051556141","display_name":"Yaowei Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaowei Guo","raw_affiliation_strings":["University of California,Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083788268","display_name":"Jiazheng Xing","orcid":"https://orcid.org/0000-0001-7280-249X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiazheng Xing","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103156798","display_name":"Xiaojun Hou","orcid":"https://orcid.org/0000-0002-5344-8517"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Hou","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111068042","display_name":"Shuo Xin","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Xin","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053162806","display_name":"Juntao Jiang","orcid":"https://orcid.org/0000-0003-2139-6449"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juntao Jiang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034397232","display_name":"Demetri Terzopoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Demetri Terzopoulos","raw_affiliation_strings":["University of California,Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068163735","display_name":"Chenfanfu Jiang","orcid":"https://orcid.org/0000-0003-3506-0583"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenfanfu Jiang","raw_affiliation_strings":["University of California,Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021253568","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0001-7748-3651"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9758999943733215,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9758999943733215,"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":0.9707000255584717,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9422000050544739,"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":0.839116096496582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7028508186340332},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6375737190246582},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5860322117805481},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5383864641189575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2920626401901245},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.16434380412101746},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.13171368837356567},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11674246191978455},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11151915788650513}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.839116096496582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7028508186340332},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6375737190246582},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5860322117805481},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5383864641189575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2920626401901245},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.16434380412101746},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.13171368837356567},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11674246191978455},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11151915788650513},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889812","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W329267344","https://openalex.org/W1904325426","https://openalex.org/W1924343884","https://openalex.org/W2751178015","https://openalex.org/W2919974746","https://openalex.org/W2963220254","https://openalex.org/W2963524571","https://openalex.org/W2963919999","https://openalex.org/W2972911652","https://openalex.org/W2980884691","https://openalex.org/W3094550259","https://openalex.org/W3109316002","https://openalex.org/W3113146884","https://openalex.org/W3196253003","https://openalex.org/W3201832684","https://openalex.org/W3202168743","https://openalex.org/W4312544061","https://openalex.org/W4313038449","https://openalex.org/W4386065705","https://openalex.org/W4386083094","https://openalex.org/W4390190760","https://openalex.org/W4390873341","https://openalex.org/W4390873423","https://openalex.org/W4393148542","https://openalex.org/W4402352082","https://openalex.org/W4402753830","https://openalex.org/W4404446900","https://openalex.org/W6631190155","https://openalex.org/W6719612900","https://openalex.org/W6739901393","https://openalex.org/W6791353385","https://openalex.org/W6797265648","https://openalex.org/W6799428148","https://openalex.org/W6839345753","https://openalex.org/W6859068429"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W2351187795","https://openalex.org/W4317547544","https://openalex.org/W4313395829"],"abstract_inverted_index":{"Video":[0],"summarization,":[1],"by":[2],"selecting":[3],"the":[4,78,82,135,151,162,187,204],"most":[5,68],"informative":[6],"and/or":[7],"user-relevant":[8],"parts":[9],"of":[10,94,208],"original":[11],"videos":[12],"to":[13,129,143,176],"create":[14],"concise":[15],"summary":[16],"videos,":[17],"has":[18,37],"high":[19],"research":[20,40],"value":[21],"and":[22,61,74,115,121,155,197,206],"consumer":[23],"demand":[24],"in":[25,91,150],"today\u2019s":[26],"video":[27,31,45,73,105,154],"proliferation":[28],"era.":[29],"Multi-modal":[30],"summarization":[32,46,106],"that":[33,84,180],"accomodates":[34],"user":[35],"input":[36],"become":[38],"a":[39,102,123],"hotspot.":[41],"However,":[42],"current":[43],"multi-modal":[44,69,104,138],"methods":[47,54,70,196],"suffer":[48],"from":[49,58],"two":[50],"limitations.":[51],"First,":[52],"existing":[53],"inadequately":[55],"fuse":[56],"information":[57,86,168],"different":[59],"modalities":[60],"cannot":[62],"effectively":[63],"utilize":[64,131],"modality-unique":[65,132],"features.":[66],"Second,":[67],"focus":[71],"on":[72,200],"text":[75,163],"modalities,":[76],"neglecting":[77],"audio":[79,85,116,156],"modality,":[80,178],"despite":[81],"fact":[83],"can":[87],"be":[88],"very":[89],"useful":[90],"certain":[92],"types":[93],"videos.":[95],"In":[96,134],"this":[97],"paper":[98],"we":[99],"propose":[100],"CFSum,":[101],"transformer-based":[103,125],"framework":[107,128],"with":[108,161,186],"coarse-fine":[109],"fusion.":[110],"CFSum":[111,171],"exploits":[112],"video,":[113],"text,":[114],"modal":[117,182],"features":[118,139,157],"as":[119],"input,":[120],"incorporates":[122],"two-stage":[124],"feature":[126,147,183],"fusion":[127],"fully":[130],"information.":[133],"first":[136],"stage,":[137,153],"are":[140,158],"fused":[141],"simultaneously":[142],"perform":[144],"initial":[145],"coarse-grained":[146],"fusion,":[148],"then,":[149],"second":[152],"explicitly":[159],"attended":[160],"representation":[164],"yielding":[165],"more":[166],"fine-grained":[167],"interaction.":[169],"The":[170],"architecture":[172],"gives":[173],"equal":[174],"importance":[175],"each":[177,181],"ensuring":[179],"interacts":[184],"deeply":[185],"other":[188],"modalities.":[189],"Our":[190],"extensive":[191],"comparative":[192],"experiments":[193],"against":[194],"prior":[195],"ablation":[198],"studies":[199],"various":[201],"datasets":[202],"confirm":[203],"effectiveness":[205],"superiority":[207],"CFSum.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
