{"id":"https://openalex.org/W4416286442","doi":"https://doi.org/10.1109/tpami.2025.3633657","title":"Language-Guided Graph Representation Learning for Video Summarization","display_name":"Language-Guided Graph Representation Learning for Video Summarization","publication_year":2025,"publication_date":"2025-11-17","ids":{"openalex":"https://openalex.org/W4416286442","doi":"https://doi.org/10.1109/tpami.2025.3633657","pmid":"https://pubmed.ncbi.nlm.nih.gov/41247907"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3633657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3633657","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wenrui Li","orcid":"https://orcid.org/0000-0002-2393-9016"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenrui Li","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-2393-9016","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101675585","display_name":"Wei Han","orcid":"https://orcid.org/0000-0002-8736-4629"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Han","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072721151","display_name":"Hengyu Man","orcid":"https://orcid.org/0009-0004-8164-0700"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengyu Man","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0004-8164-0700","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042587571","display_name":"Wangmeng Zuo","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangmeng Zuo","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-3330-783X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079412089","display_name":"Xiaopeng Fan","orcid":"https://orcid.org/0000-0002-9660-3636"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Fan","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-9660-3636","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104293962","display_name":"Yonghong Tian","orcid":null},"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"]},{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Tian","raw_affiliation_strings":["School of AI for Science, Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2978-5935","affiliations":[{"raw_affiliation_string":"School of AI for Science, Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628","https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3394,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.93328324,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"48","issue":"3","first_page":"3216","last_page":"3232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.6003999710083008,"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":0.6003999710083008,"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":0.2386000007390976,"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/T10028","display_name":"Topic Modeling","score":0.03460000082850456,"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/automatic-summarization","display_name":"Automatic summarization","score":0.751800000667572},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5145000219345093},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49050000309944153},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4878999888896942},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4431000053882599},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.40880000591278076},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.36730000376701355},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.36309999227523804},{"id":"https://openalex.org/keywords/video-content-analysis","display_name":"Video content analysis","score":0.34450000524520874},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3409999907016754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8285999894142151},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.751800000667572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6157000064849854},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5145000219345093},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49050000309944153},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4431000053882599},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.40880000591278076},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C2778598663","wikidata":"https://www.wikidata.org/wiki/Q1407599","display_name":"Video content analysis","level":4,"score":0.34450000524520874},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3409999907016754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3368000090122223},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.32429999113082886},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29989999532699585},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.275299996137619},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.258899986743927},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3633657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3633657","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41247907","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41247907","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1947953275","display_name":null,"funder_award_id":"62425101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5430980299","display_name":null,"funder_award_id":"U22B2035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8191219995","display_name":null,"funder_award_id":"62502116","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8685418503","display_name":null,"funder_award_id":"624B2049","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1924343884","https://openalex.org/W1966872876","https://openalex.org/W2101980173","https://openalex.org/W2106229755","https://openalex.org/W2134577448","https://openalex.org/W2139009685","https://openalex.org/W2338907589","https://openalex.org/W2498094064","https://openalex.org/W2517959782","https://openalex.org/W2529272619","https://openalex.org/W2560681555","https://openalex.org/W2607326921","https://openalex.org/W2781922022","https://openalex.org/W2798970487","https://openalex.org/W2895758197","https://openalex.org/W2963220254","https://openalex.org/W2963319519","https://openalex.org/W2963432616","https://openalex.org/W2963508075","https://openalex.org/W2963919999","https://openalex.org/W2964158702","https://openalex.org/W2972712288","https://openalex.org/W2985331920","https://openalex.org/W2996811227","https://openalex.org/W2997217064","https://openalex.org/W3010790568","https://openalex.org/W3045623285","https://openalex.org/W3107128832","https://openalex.org/W3107252718","https://openalex.org/W3150815828","https://openalex.org/W3168126734","https://openalex.org/W4206423448","https://openalex.org/W4226103007","https://openalex.org/W4246193833","https://openalex.org/W4283399854","https://openalex.org/W4284696747","https://openalex.org/W4313343169","https://openalex.org/W4386065705","https://openalex.org/W4386065852","https://openalex.org/W4386072365","https://openalex.org/W4387934928","https://openalex.org/W4389104669","https://openalex.org/W4389161308","https://openalex.org/W4390970416","https://openalex.org/W4392904279","https://openalex.org/W4395470960","https://openalex.org/W4396918399","https://openalex.org/W4400269657","https://openalex.org/W4400748621","https://openalex.org/W4402671548","https://openalex.org/W4402727546","https://openalex.org/W4402916583","https://openalex.org/W4403780613","https://openalex.org/W4404784276","https://openalex.org/W4409368464","https://openalex.org/W4411549748","https://openalex.org/W4412530017","https://openalex.org/W7108068597"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,96,102,149,163],"rapid":[2],"growth":[3],"of":[4,107,156],"video":[5,10,30,41,65,71,76,97,108,141],"content":[6,31],"on":[7],"social":[8],"media,":[9],"summarization":[11],"has":[12],"become":[13],"a":[14,56,70,79,118,154],"crucial":[15],"task":[16],"in":[17,25,29],"multimedia":[18],"processing.":[19],"However,":[20],"existing":[21,173],"methods":[22],"face":[23],"challenges":[24],"capturing":[26],"global":[27],"dependencies":[28],"and":[32,86,93,104,159,185,190],"accommodating":[33],"multimodal":[34],"user":[35],"customization.":[36],"Moreover,":[37,178],"temporal":[38,84],"proximity":[39],"between":[40,131],"frames":[42,77,127],"does":[43],"not":[44],"always":[45],"correspond":[46],"to":[47,82],"semantic":[48],"proximity.":[49],"To":[50],"tackle":[51],"these":[52],"challenges,":[53],"we":[54,68,179],"propose":[55],"novel":[57],"Language-guided":[58],"Graph":[59],"Representation":[60],"Learning":[61],"Network":[62],"(LGRLN)":[63],"for":[64],"summarization.":[66],"Specifically,":[67],"introduce":[69],"graph":[72,81,98,120],"generator":[73,99],"that":[74,169],"converts":[75],"into":[78],"structured":[80],"preserve":[83],"order":[85],"contextual":[87,105],"dependencies.":[88],"By":[89],"constructing":[90],"forward,":[91],"backward":[92],"undirected":[94],"graphs,":[95],"effectively":[100],"preserves":[101],"sequentiality":[103],"relationships":[106],"content.":[109],"We":[110,147],"designed":[111],"an":[112],"intra-graph":[113],"relational":[114],"reasoning":[115],"module":[116,139],"with":[117,143,162],"dual-threshold":[119],"convolution":[121],"mechanism,":[122],"which":[123],"distinguishes":[124],"semantically":[125],"relevant":[126],"from":[128],"irrelevant":[129],"ones":[130],"nodes.":[132],"Additionally,":[133],"our":[134,170],"proposed":[135,180],"language-guided":[136],"cross-modal":[137],"embedding":[138],"generates":[140],"summaries":[142],"specific":[144],"textual":[145],"descriptions.":[146],"model":[148,186],"summary":[150],"generation":[151],"output":[152],"as":[153],"mixture":[155],"Bernoulli":[157],"distribution":[158],"solve":[160],"it":[161],"EM":[164],"algorithm.":[165],"Experimental":[166],"results":[167],"show":[168],"method":[171],"outperforms":[172],"approaches":[174],"across":[175],"multiple":[176],"benchmarks.":[177],"LGRLN":[181],"reduces":[182],"inference":[183],"time":[184],"parameters":[187],"by":[188],"87.8%":[189],"91.7%,":[191],"respectively.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":6}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-11-17T00:00:00"}