{"id":"https://openalex.org/W4414757871","doi":"https://doi.org/10.1109/tkde.2025.3610544","title":"ASSM: Adaptive Subject-Focused Modeling for Multimodal Summarization via Semantic Matching","display_name":"ASSM: Adaptive Subject-Focused Modeling for Multimodal Summarization via Semantic Matching","publication_year":2025,"publication_date":"2025-10-02","ids":{"openalex":"https://openalex.org/W4414757871","doi":"https://doi.org/10.1109/tkde.2025.3610544"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2025.3610544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2025.3610544","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"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 Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","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/A5075393447","display_name":"Xujian Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xujian Zhao","raw_affiliation_strings":["Southwest University of Science and Technology, Mianyang, China"],"raw_orcid":"https://orcid.org/0000-0003-4717-9231","affiliations":[{"raw_affiliation_string":"Southwest University of Science and Technology, Mianyang, China","institution_ids":["https://openalex.org/I1297991670"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chuanpeng Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanpeng Deng","raw_affiliation_strings":["Southwest University of Science and Technology, Mianyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest University of Science and Technology, Mianyang, China","institution_ids":["https://openalex.org/I1297991670"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087025546","display_name":"Peiquan Jin","orcid":"https://orcid.org/0000-0002-3871-0548"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiquan Jin","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3871-0548","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13601013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"12","first_page":"6945","last_page":"6958"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9947999715805054,"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":0.9947999715805054,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9815999865531921,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9739000201225281,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8428999781608582},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5785999894142151},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.5331000089645386},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5149000287055969},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.46790000796318054},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.45899999141693115},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4058000147342682},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.40549999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8977000117301941},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8428999781608582},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5785999894142151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5339999794960022},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.5331000089645386},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39640000462532043},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3449000120162964},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3203999996185303},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.31790000200271606},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.29249998927116394},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.26100000739097595}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2025.3610544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2025.3610544","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"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 Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4757301124","display_name":null,"funder_award_id":"2072419","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2115322217","https://openalex.org/W2250539671","https://openalex.org/W2467173223","https://openalex.org/W2593341061","https://openalex.org/W2606974598","https://openalex.org/W2609482285","https://openalex.org/W2808413133","https://openalex.org/W2890721473","https://openalex.org/W2896457183","https://openalex.org/W2962965405","https://openalex.org/W2963407669","https://openalex.org/W2964165364","https://openalex.org/W2970785793","https://openalex.org/W2997326549","https://openalex.org/W3115803208","https://openalex.org/W3153101952","https://openalex.org/W3165529210","https://openalex.org/W3170083118","https://openalex.org/W3200369555","https://openalex.org/W3211495814","https://openalex.org/W4253028564","https://openalex.org/W4284708663","https://openalex.org/W4294170691","https://openalex.org/W4384642697","https://openalex.org/W4385245566","https://openalex.org/W4385571533","https://openalex.org/W4385572291","https://openalex.org/W4385767852","https://openalex.org/W4393161081"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Summarization":[1],"aims":[2],"to":[3,7,92,113,131,192],"use":[4],"multimodal":[5,29,56,77,83,120],"data":[6],"generate":[8],"accurate":[9],"and":[10,31,151,164,178],"concise":[11],"summaries":[12],"for":[13,36,55,140],"long":[14],"sentences.":[15],"While":[16],"previous":[17],"work":[18],"has":[19],"achieved":[20],"promising":[21],"success,":[22],"they":[23],"have":[24],"overlooked":[25],"the":[26,95,119,134,168,180,195],"mismatching":[27],"among":[28],"semantics":[30,96],"lacked":[32],"subject":[33,115,126,135],"information":[34],"guidance":[35,139],"adaptive":[37,105],"referential":[38],"images.":[39],"Motivated":[40],"by":[41],"this":[42],"observation,":[43],"we":[44,74,102,128,187],"propose":[45,75,103],"ASSM,":[46],"an":[47,104],"<bold":[48,51,59,62],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[49,52,60,63],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><u>A</u></b>daptive":[50],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><u>S</u></b>ubject-focused":[53],"modeling":[54],"summarization":[57],"via":[58],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><u>S</u></b>emantic":[61],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><u>M</u></b>atching.":[64],"The":[65,158],"novelty":[66],"of":[67,182,197],"ASSM":[68,153,170],"lies":[69],"in":[70],"two":[71,148],"aspects.":[72],"First,":[73],"a":[76,86,189],"semantic":[78,90,121],"matching":[79,122],"module":[80],"that":[81,167],"projects":[82],"inputs":[84],"into":[85],"shared":[87],"joint":[88],"embedding":[89],"space":[91],"determine":[93],"whether":[94],"between":[97],"multimodalities":[98],"are":[99,129],"mismatching.":[100],"Second,":[101],"subject-focused":[106],"guide":[107],"module,":[108],"which":[109],"adaptively":[110],"references":[111],"images":[112],"learn":[114],"tokens":[116],"based":[117],"on":[118,133,147],"results.":[123],"With":[124],"these":[125],"tokens,":[127],"able":[130],"focus":[132],"information,":[136],"providing":[137],"precise":[138],"summary":[141],"generation.":[142],"We":[143],"conduct":[144],"extensive":[145],"experiments":[146],"standard":[149],"benchmarks":[150],"compare":[152],"with":[154],"17":[155],"existing":[156],"models.":[157],"experimental":[159],"results":[160],"regarding":[161],"ROUGE,":[162],"BERTScore,":[163],"MoverScore":[165],"show":[166],"proposed":[169],"model":[171],"outperforms":[172],"all":[173],"competitors,":[174],"achieving":[175],"state-of-the-art":[176],"performance":[177],"suggesting":[179],"effectiveness":[181],"our":[183],"proposal.":[184],"In":[185],"addition,":[186],"provide":[188],"case":[190],"study":[191],"further":[193],"demonstrate":[194],"usability":[196],"ASSM.":[198]},"counts_by_year":[],"updated_date":"2025-11-11T23:18:09.558992","created_date":"2025-10-10T00:00:00"}