{"id":"https://openalex.org/W4399435792","doi":"https://doi.org/10.1145/3652583.3658069","title":"A Knowledge-Driven Approach to Enhance Topic Modeling with Multi-Modal Representation Learning","display_name":"A Knowledge-Driven Approach to Enhance Topic Modeling with Multi-Modal Representation Learning","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399435792","doi":"https://doi.org/10.1145/3652583.3658069"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658069","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658069","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658069","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658069","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042345951","display_name":"Hongzhang Mu","orcid":"https://orcid.org/0000-0003-0378-4587"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongzhang Mu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0378-4587","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056523030","display_name":"S. F. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuili Zhang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-6196-8263","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102840335","display_name":"Hongbo Xu","orcid":"https://orcid.org/0009-0008-0498-0743"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Xu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-0498-0743","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042345951"],"corresponding_institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06289971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1347","last_page":"1355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9983999729156494,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9879000186920166,"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":0.8241373300552368},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7197542786598206},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5821660757064819},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5593159198760986},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5330910086631775},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5130585432052612},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49755051732063293},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4827679693698883},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.42182624340057373},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4209810197353363},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4034915566444397},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.18492430448532104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8241373300552368},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7197542786598206},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5821660757064819},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5593159198760986},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5330910086631775},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5130585432052612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49755051732063293},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4827679693698883},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.42182624340057373},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4209810197353363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4034915566444397},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.18492430448532104},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3658069","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658069","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658069","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658069","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658069","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658069","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399435792.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W2038043464","https://openalex.org/W2042980227","https://openalex.org/W2072644219","https://openalex.org/W2094808586","https://openalex.org/W2128925311","https://openalex.org/W2294978630","https://openalex.org/W2405811584","https://openalex.org/W2731449405","https://openalex.org/W2798683079","https://openalex.org/W2803437449","https://openalex.org/W2976420234","https://openalex.org/W2981851019","https://openalex.org/W2983366375","https://openalex.org/W3008585262","https://openalex.org/W3021053579","https://openalex.org/W3036644138","https://openalex.org/W3045464143","https://openalex.org/W3047144459","https://openalex.org/W3159583533","https://openalex.org/W3176380929","https://openalex.org/W3211643415","https://openalex.org/W4210618583","https://openalex.org/W4214612132","https://openalex.org/W4224276467","https://openalex.org/W4386071547"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2714992399","https://openalex.org/W2383812217","https://openalex.org/W2326515389","https://openalex.org/W2491005386"],"abstract_inverted_index":{"multi-modal":[0,9,44,90,146],"topic":[1,24,127,147],"models":[2,148],"strive":[3],"to":[4,11,87],"integrate":[5],"semantic":[6],"information":[7],"from":[8],"data":[10],"generate":[12],"more":[13],"precise":[14],"topics.":[15],"Topic":[16],"modeling":[17,39],"methods":[18],"encounter":[19],"challenges":[20],"in":[21],"terms":[22],"of":[23,34,120],"diversity":[25],"and":[26,56,80,132],"effectiveness.":[27],"To":[28,116],"address":[29],"this":[30,60],"issue,":[31],"the":[32,40,95,113,118,121,135],"majority":[33],"current":[35],"approaches":[36],"focus":[37],"on":[38,52,112],"correlation":[41],"among":[42],"numerous":[43],"sources.":[45],"Nevertheless,":[46],"little":[47],"emphasis":[48],"has":[49],"been":[50],"placed":[51],"fine-grained":[53,65,100],"feature":[54],"representation":[55,67,97],"structured":[57,96],"knowledge.":[58],"In":[59],"regard,":[61],"we":[62,70,124],"propose":[63],"a":[64,72,76,89,105],"Prompt":[66],"method.":[68],"Specifically,":[69],"adopt":[71],"dual-stream":[73],"structure":[74],"where":[75],"pre-trained":[77],"language":[78],"model":[79,83],"an":[81],"image":[82],"are":[84],"parallelly":[85],"combined":[86],"construct":[88],"model.":[91],"We":[92],"then":[93],"enhance":[94],"by":[98],"integrating":[99],"scene":[101,114],"graph":[102],"knowledge":[103],"through":[104],"Knowledge-Enhanced":[106],"Encoder,":[107],"which":[108],"is":[109],"constructed":[110],"based":[111],"graph.":[115],"validate":[117],"effectiveness":[119],"proposed":[122],"framework,":[123],"significantly":[125],"improve":[126],"quality":[128],"(such":[129],"as":[130],"coherence":[131],"diversity)":[133],"using":[134],"aforementioned":[136],"approach.":[137],"On":[138],"publicly":[139],"available":[140],"datasets,":[141],"our":[142],"approach":[143],"outperforms":[144],"state-of-the-art":[145],"respectively.":[149]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}