{"id":"https://openalex.org/W2759570332","doi":"https://doi.org/10.18653/v1/d17-1114","title":"Multi-modal Summarization for Asynchronous Collection of Text, Image, Audio and Video","display_name":"Multi-modal Summarization for Asynchronous Collection of Text, Image, Audio and Video","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2759570332","doi":"https://doi.org/10.18653/v1/d17-1114","mag":"2759570332"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1114","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1114","pdf_url":"https://www.aclweb.org/anthology/D17-1114.pdf","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 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D17-1114.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100327720","display_name":"Haoran Li","orcid":"https://orcid.org/0000-0002-2368-7541"},"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":true,"raw_author_name":"Haoran Li","raw_affiliation_strings":["National Laboratory of Pattern Recognition, CASIA, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","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, CASIA, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101810188","display_name":"Cong Ma","orcid":"https://orcid.org/0000-0002-9787-6273"},"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":"Cong Ma","raw_affiliation_strings":["National Laboratory of Pattern Recognition, CASIA, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["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/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, CASIA, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["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/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"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":["University of Chinese Academy of Sciences, Beijing, China","CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China","National Laboratory of Pattern Recognition, CASIA, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100327720"],"corresponding_institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":2.0337,"has_fulltext":true,"cited_by_count":101,"citation_normalized_percentile":{"value":0.92519655,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1092","last_page":"1102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9977999925613403,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9977999925613403,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9968000054359436,"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/T10028","display_name":"Topic Modeling","score":0.9958000183105469,"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":0.867138147354126},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8511526584625244},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5534331798553467},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5524015426635742},{"id":"https://openalex.org/keywords/submodular-set-function","display_name":"Submodular set function","score":0.5142097473144531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4821721911430359},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.45288515090942383},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.4308125376701355},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42962661385536194},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4290730655193329},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3640788793563843},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19680795073509216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.867138147354126},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8511526584625244},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5534331798553467},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5524015426635742},{"id":"https://openalex.org/C178621042","wikidata":"https://www.wikidata.org/wiki/Q7631710","display_name":"Submodular set function","level":2,"score":0.5142097473144531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4821721911430359},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.45288515090942383},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.4308125376701355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42962661385536194},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4290730655193329},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3640788793563843},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19680795073509216},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d17-1114","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1114","pdf_url":"https://www.aclweb.org/anthology/D17-1114.pdf","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 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1114","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1114","pdf_url":"https://www.aclweb.org/anthology/D17-1114.pdf","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 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1103404643","display_name":null,"funder_award_id":"61403379","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2204133011","display_name":null,"funder_award_id":"61333018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2976037654","display_name":null,"funder_award_id":"No. 61333018 and No. 61403379","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5249178904","display_name":null,"funder_award_id":"Grant No. 6","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8863666567","display_name":null,"funder_award_id":"and No.","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2759570332.pdf","grobid_xml":"https://content.openalex.org/works/W2759570332.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1931795219","https://openalex.org/W1943253508","https://openalex.org/W1962684803","https://openalex.org/W1973010836","https://openalex.org/W1973894278","https://openalex.org/W1981974552","https://openalex.org/W2007291639","https://openalex.org/W2026012689","https://openalex.org/W2060724430","https://openalex.org/W2074051546","https://openalex.org/W2080379754","https://openalex.org/W2093541376","https://openalex.org/W2097241552","https://openalex.org/W2097606805","https://openalex.org/W2105395363","https://openalex.org/W2128618367","https://openalex.org/W2129291408","https://openalex.org/W2146113428","https://openalex.org/W2150824314","https://openalex.org/W2151170651","https://openalex.org/W2157023096","https://openalex.org/W2159940559","https://openalex.org/W2168154661","https://openalex.org/W2185175083","https://openalex.org/W2259890326","https://openalex.org/W2365919995","https://openalex.org/W2461084364","https://openalex.org/W2463955103","https://openalex.org/W2465299637","https://openalex.org/W2529165750","https://openalex.org/W2595558070","https://openalex.org/W2963389687","https://openalex.org/W3101913037","https://openalex.org/W4297813007"],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2032810564","https://openalex.org/W2370831213","https://openalex.org/W2972807713","https://openalex.org/W4285478380","https://openalex.org/W4315704968","https://openalex.org/W2963844234","https://openalex.org/W2803250016"],"abstract_inverted_index":{"The":[0,54,140],"rapid":[1],"increase":[2],"in":[3,128],"multimedia":[4],"data":[5],"transmission":[6],"over":[7],"the":[8,11,60,83,97,104,109,116,136],"Internet":[9],"necessitates":[10],"multi-modal":[12,30,64],"summarization":[13,31],"(MMS)":[14],"from":[15],"collections":[16],"of":[17,43,86,96,119],"text,":[18],"image,":[19],"audio":[20,67],"and":[21,47,88,113,130],"video.":[22],"In":[23],"this":[24,145],"work,":[25],"we":[26,69,81],"propose":[27],"an":[28,71,125],"extractive":[29],"method":[32,150],"that":[33,148],"can":[34],"automatically":[35],"generate":[36,103],"a":[37,41,51,91],"textual":[38,105],"summary":[39,106],"given":[40],"set":[42],"documents,":[44],"images,":[45],"audios":[46],"videos":[48],"related":[49],"to":[50,58,73,102,135],"specific":[52],"topic.":[53],"key":[55],"idea":[56],"is":[57,133],"bridge":[59],"semantic":[61],"gaps":[62],"between":[63],"content.":[65],"For":[66,78],"information,":[68,80],"design":[70],"approach":[72],"selectively":[74],"use":[75],"its":[76],"transcription.":[77],"visual":[79],"learn":[82],"joint":[84],"representations":[85],"text":[87],"images":[89],"using":[90],"neural":[92],"network.":[93],"Finally,":[94],"all":[95],"multimodal":[98],"aspects":[99],"are":[100],"considered":[101],"by":[107],"maximizing":[108],"salience,":[110],"non-redundancy,":[111],"readability":[112],"coverage":[114],"through":[115],"budgeted":[117],"optimization":[118],"submodular":[120],"functions.":[121],"We":[122],"further":[123],"introduce":[124],"MMS":[126],"corpus":[127],"English":[129],"Chinese,":[131],"which":[132],"released":[134],"public":[137],"1":[138],".":[139],"experimental":[141],"results":[142],"obtained":[143],"on":[144],"dataset":[146],"demonstrate":[147],"our":[149],"outperforms":[151],"other":[152],"competitive":[153],"baseline":[154],"methods.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}