{"id":"https://openalex.org/W3028430767","doi":"https://doi.org/10.1145/3397271.3401232","title":"Multi-Modal Summary Generation using Multi-Objective Optimization","display_name":"Multi-Modal Summary Generation using Multi-Objective Optimization","publication_year":2020,"publication_date":"2020-07-25","ids":{"openalex":"https://openalex.org/W3028430767","doi":"https://doi.org/10.1145/3397271.3401232","mag":"3028430767"},"language":"en","primary_location":{"id":"doi:10.1145/3397271.3401232","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.09252","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008197599","display_name":"Anubhav Jangra","orcid":"https://orcid.org/0000-0001-5571-6098"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anubhav Jangra","raw_affiliation_strings":["Indian Institute of Technology Patna, Patna, India","Indian Institute of Technology Patna Patna India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]},{"raw_affiliation_string":"Indian Institute of Technology Patna Patna India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060797340","display_name":"Sriparna Saha","orcid":"https://orcid.org/0000-0001-5458-9381"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriparna Saha","raw_affiliation_strings":["Indian Institute of Technology Patna, Patna, India","Indian Institute of Technology Patna Patna India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]},{"raw_affiliation_string":"Indian Institute of Technology Patna Patna India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079733597","display_name":"Adam Jatowt","orcid":"https://orcid.org/0000-0001-7235-0665"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Adam Jatowt","raw_affiliation_strings":["Kyoto University, Kyoto, Japan","Kyoto University,Kyoto,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University,Kyoto,Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026783387","display_name":"Mohammed Hasanuzzaman","orcid":"https://orcid.org/0000-0003-1838-0091"},"institutions":[{"id":"https://openalex.org/I4210100923","display_name":"Munster Technological University","ror":"https://ror.org/013xpqh61","country_code":"IE","type":"facility","lineage":["https://openalex.org/I4210100923"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Mohammad Hasanuzzaman","raw_affiliation_strings":["Cork Institute of Technology, Bishoptown, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cork Institute of Technology, Bishoptown, Ireland","institution_ids":["https://openalex.org/I4210100923"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04458051,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1745","last_page":"1748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9905999898910522,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9894000291824341,"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/modal","display_name":"Modal","score":0.8769756555557251},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8731076121330261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.690169095993042},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6394784450531006},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5162580013275146},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5104576349258423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4544338583946228},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4480295479297638},{"id":"https://openalex.org/keywords/salience","display_name":"Salience (neuroscience)","score":0.44316336512565613},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43872320652008057},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10913532972335815}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.8769756555557251},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8731076121330261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.690169095993042},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6394784450531006},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5162580013275146},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5104576349258423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4544338583946228},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4480295479297638},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.44316336512565613},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43872320652008057},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10913532972335815},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3397271.3401232","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.09252","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.09252","pdf_url":"https://arxiv.org/pdf/2005.09252","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3028430767","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2005.09252.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2005.09252","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.09252","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.09252","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.09252","pdf_url":"https://arxiv.org/pdf/2005.09252","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320325255","display_name":"Ministry of Electronics and Information technology","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3028430767.pdf","grobid_xml":"https://content.openalex.org/works/W3028430767.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1525595230","https://openalex.org/W1686810756","https://openalex.org/W1931795219","https://openalex.org/W1983753875","https://openalex.org/W2008002935","https://openalex.org/W2033177967","https://openalex.org/W2073459066","https://openalex.org/W2126105956","https://openalex.org/W2138810473","https://openalex.org/W2159527087","https://openalex.org/W2317879529","https://openalex.org/W2559013665","https://openalex.org/W2598569220","https://openalex.org/W2759570332","https://openalex.org/W2890721473","https://openalex.org/W2899410785","https://openalex.org/W2963389687","https://openalex.org/W3015685572","https://openalex.org/W3101913037"],"related_works":["https://openalex.org/W3034873860","https://openalex.org/W3153101952","https://openalex.org/W3015412648","https://openalex.org/W2859473401","https://openalex.org/W3157911070","https://openalex.org/W3188404242","https://openalex.org/W2905897455","https://openalex.org/W3154326567","https://openalex.org/W3022761309","https://openalex.org/W3206571301","https://openalex.org/W3027898822","https://openalex.org/W2783316752","https://openalex.org/W3177342479","https://openalex.org/W2240294096","https://openalex.org/W2575980463","https://openalex.org/W2583352266","https://openalex.org/W3193528024","https://openalex.org/W2080193489","https://openalex.org/W2134963155","https://openalex.org/W3036784071"],"abstract_inverted_index":{"Significant":[0],"development":[1],"of":[2,19],"communication":[3],"technology":[4],"over":[5],"the":[6,20],"past":[7],"few":[8],"years":[9],"has":[10,80,88],"motivated":[11],"research":[12],"in":[13,67],"multi-modal":[14,24,46,75],"summarization":[15,25],"techniques.":[16],"A":[17],"majority":[18],"previous":[21],"works":[22],"on":[23,27],"focus":[26],"text":[28],"and":[29,51,61,87],"images.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34],"propose":[35],"a":[36,45,68],"novel":[37],"extractive":[38],"multi-objective":[39,69],"optimization":[40,70],"based":[41],"model":[42,79],"to":[43,72,91],"produce":[44,73],"summary":[47],"containing":[48],"text,":[49],"images,":[50],"videos.":[52],"Important":[53],"objectives":[54],"such":[55],"as":[56],"intra-modality":[57],"salience,":[58],"cross-modal":[59,62],"redundancy":[60],"similarity":[63],"are":[64],"optimized":[65],"simultaneously":[66],"framework":[71],"effective":[74],"output.":[76],"The":[77],"proposed":[78],"been":[81,89],"evaluated":[82],"separately":[83],"for":[84],"different":[85],"modalities,":[86],"found":[90],"perform":[92],"better":[93],"than":[94],"state-of-the-art":[95],"approaches.":[96]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}