{"id":"https://openalex.org/W3165529210","doi":"https://doi.org/10.1145/3445794","title":"Graph-based Multimodal Ranking Models for Multimodal Summarization","display_name":"Graph-based Multimodal Ranking Models for Multimodal Summarization","publication_year":2021,"publication_date":"2021-05-26","ids":{"openalex":"https://openalex.org/W3165529210","doi":"https://doi.org/10.1145/3445794","mag":"3165529210"},"language":"en","primary_location":{"id":"doi:10.1145/3445794","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3445794","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","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/A5015809194","display_name":"Junnan Zhu","orcid":"https://orcid.org/0000-0002-9856-2946"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":"Junnan Zhu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, CAS, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9856-2946","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, CAS, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101569772","display_name":"Lu Xiang","orcid":"https://orcid.org/0000-0001-6362-621X"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":"Lu Xiang","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, CAS, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, CAS, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016175345","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0003-4188-9953"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":"Yu Zhou","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, CAS, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing Fanyu Technology Co., Ltd, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, CAS, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing Fanyu Technology Co., Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319572","display_name":"Jiajun Zhang","orcid":"https://orcid.org/0000-0001-5293-7434"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":"Jiajun Zhang","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, CAS, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing Academy of Artificial Intelligence, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, CAS, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing Academy of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015785439","display_name":"Chengqing Zong","orcid":"https://orcid.org/0000-0002-9864-3818"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":"Chengqing Zong","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, CAS, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, CAS, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8844,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.87701938,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"20","issue":"4","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9976999759674072,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9962999820709229,"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":0.9722504615783691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8429299592971802},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6780463457107544},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5461207628250122},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5305571556091309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5168986320495605},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4809081554412842},{"id":"https://openalex.org/keywords/multi-document-summarization","display_name":"Multi-document summarization","score":0.46603912115097046},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45700183510780334},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44400250911712646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3732862174510956},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3282107710838318},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2870892584323883},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.06090301275253296}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9722504615783691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429299592971802},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6780463457107544},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5461207628250122},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5305571556091309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5168986320495605},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4809081554412842},{"id":"https://openalex.org/C134714966","wikidata":"https://www.wikidata.org/wiki/Q6934448","display_name":"Multi-document summarization","level":3,"score":0.46603912115097046},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45700183510780334},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44400250911712646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3732862174510956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3282107710838318},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2870892584323883},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.06090301275253296},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3445794","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3445794","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1904325426","https://openalex.org/W1905882502","https://openalex.org/W1987366351","https://openalex.org/W2014699069","https://openalex.org/W2026012689","https://openalex.org/W2039844788","https://openalex.org/W2093541376","https://openalex.org/W2128629010","https://openalex.org/W2149557440","https://openalex.org/W2165469059","https://openalex.org/W2185175083","https://openalex.org/W2233620181","https://openalex.org/W2290496532","https://openalex.org/W2317486713","https://openalex.org/W2461084364","https://openalex.org/W2526278568","https://openalex.org/W2529165750","https://openalex.org/W2560835477","https://openalex.org/W2606473278","https://openalex.org/W2613031639","https://openalex.org/W2617240292","https://openalex.org/W2759570332","https://openalex.org/W2794988145","https://openalex.org/W2808399042","https://openalex.org/W2809191921","https://openalex.org/W2890721473","https://openalex.org/W2891444075","https://openalex.org/W2962965405","https://openalex.org/W2963385935","https://openalex.org/W2964051877","https://openalex.org/W2971139875","https://openalex.org/W2997326549","https://openalex.org/W2997617958","https://openalex.org/W2998559045","https://openalex.org/W3035691816","https://openalex.org/W3098767300","https://openalex.org/W3115803208"],"related_works":["https://openalex.org/W2380641910","https://openalex.org/W2104677027","https://openalex.org/W65350537","https://openalex.org/W2093597205","https://openalex.org/W2389846579","https://openalex.org/W2392495745","https://openalex.org/W132250100","https://openalex.org/W1486300815","https://openalex.org/W2725657302","https://openalex.org/W2786925157"],"abstract_inverted_index":{"Multimodal":[0],"summarization":[1,37,86,93,113,166,183,204],"aims":[2],"to":[3,19,68,71,148],"extract":[4],"the":[5,10,20,40,108,116,150,164,181,185,188,197],"most":[6,53],"important":[7],"information":[8],"from":[9],"multimedia":[11,24,189],"input.":[12],"It":[13],"is":[14,146],"becoming":[15],"increasingly":[16],"popular":[17],"due":[18],"rapid":[21],"growth":[22],"of":[23,54,59,118,187],"data":[25],"in":[26],"recent":[27],"years.":[28],"There":[29],"are":[30],"various":[31],"researches":[32],"focusing":[33],"on":[34,168,202],"different":[35,104],"multimodal":[36,49,85,95,112,128,132,138,203],"tasks.":[38],"However,":[39],"existing":[41],"methods":[42,167],"can":[43,88,178,193],"only":[44],"generate":[45],"single-modal":[46,91,165,182],"output":[47,92,96],"or":[48,74],"output.":[50],"In":[51,98],"addition,":[52],"them":[55],"need":[56],"a":[57,81],"lot":[58],"annotated":[60,121],"samples":[61],"for":[62,84,124,199],"training,":[63],"which":[64],"makes":[65],"it":[66],"difficult":[67],"be":[69,194],"generalized":[70],"other":[72],"tasks":[73],"domains.":[75],"Motivated":[76],"by":[77],"this,":[78],"we":[79,101],"propose":[80,107],"unified":[82],"framework":[83],"that":[87,159],"cover":[89],"both":[90,169],"and":[94,106,134,155,171],"summarization.":[97],"our":[99,160,176],"framework,":[100],"consider":[102],"three":[103],"scenarios":[105],"respective":[109],"unsupervised":[110],"graph-based":[111],"models":[114,162,177],"without":[115],"requirement":[117],"any":[119],"manually":[120],"document-summary":[122],"pairs":[123],"training:":[125],"(1)":[126],"generic":[127],"ranking,":[129,133],"(2)":[130],"modal-dominated":[131],"(3)":[135],"non-redundant":[136],"text-image":[137],"ranking.":[139],"Furthermore,":[140],"an":[141],"image-text":[142],"similarity":[143,152],"estimation":[144],"model":[145],"introduced":[147],"measure":[149],"semantic":[151],"between":[153],"image":[154],"text.":[156],"Experiments":[157],"show":[158],"proposed":[161],"outperform":[163],"automatic":[170],"human":[172],"evaluation":[173],"metrics.":[174],"Besides,":[175],"also":[179],"improve":[180],"with":[184],"guidance":[186],"information.":[190],"This":[191],"study":[192,201],"applied":[195],"as":[196],"benchmark":[198],"further":[200],"task.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}