{"id":"https://openalex.org/W4375959452","doi":"https://doi.org/10.48550/arxiv.2305.04824","title":"Learning Summary-Worthy Visual Representation for Abstractive Summarization in Video","display_name":"Learning Summary-Worthy Visual Representation for Abstractive Summarization in Video","publication_year":2023,"publication_date":"2023-05-08","ids":{"openalex":"https://openalex.org/W4375959452","doi":"https://doi.org/10.48550/arxiv.2305.04824"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.04824","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.04824","pdf_url":"https://arxiv.org/pdf/2305.04824","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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.04824","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043757700","display_name":"Zenan Xu","orcid":"https://orcid.org/0000-0003-1662-0063"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xu, Zenan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693147","display_name":"Xiaojun Meng","orcid":"https://orcid.org/0000-0002-7809-7012"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Xiaojun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115592503","display_name":"Yasheng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yasheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043729465","display_name":"Qinliang Su","orcid":"https://orcid.org/0000-0002-5903-2504"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Qinliang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025921923","display_name":"Zexuan Qiu","orcid":"https://orcid.org/0000-0002-3360-544X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Zexuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086603207","display_name":"Xin Jiang","orcid":"https://orcid.org/0000-0002-9117-8247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Xin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101593048","display_name":"Qun Liu","orcid":"https://orcid.org/0000-0002-8308-7636"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Qun","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5043757700"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9970999956130981,"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":0.9749000072479248,"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":0.9497644901275635},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8529975414276123},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5581804513931274},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.538341224193573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5248522758483887},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5211396217346191},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4965096116065979},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4893442988395691},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4729616045951843},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4721629321575165},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.43374255299568176},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4259314239025116},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3704911470413208},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06785270571708679}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9497644901275635},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8529975414276123},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5581804513931274},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.538341224193573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5248522758483887},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5211396217346191},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4965096116065979},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4893442988395691},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4729616045951843},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4721629321575165},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.43374255299568176},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4259314239025116},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3704911470413208},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06785270571708679},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.04824","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.04824","pdf_url":"https://arxiv.org/pdf/2305.04824","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":"doi:10.48550/arxiv.2305.04824","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.04824","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:2305.04824","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.04824","pdf_url":"https://arxiv.org/pdf/2305.04824","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":[],"awards":[{"id":"https://openalex.org/G1232371104","display_name":null,"funder_award_id":"62276280","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2602136225","display_name":null,"funder_award_id":"2018B01","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3011155338","display_name":null,"funder_award_id":"202102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3505119546","display_name":null,"funder_award_id":"20210202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6069953956","display_name":null,"funder_award_id":"2018B0101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6840496190","display_name":null,"funder_award_id":"U1811264","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7276073139","display_name":null,"funder_award_id":"2021A1515012299","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G7320351434","display_name":null,"funder_award_id":"51501229","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7457013702","display_name":null,"funder_award_id":"U181126","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"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4375959452.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W17155033","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W1517524280","https://openalex.org/W4385571435"],"abstract_inverted_index":{"Multimodal":[0],"abstractive":[1,112],"summarization":[2],"for":[3],"videos":[4],"(MAS)":[5],"requires":[6],"generating":[7,45],"a":[8,17,75,101,162],"concise":[9],"textual":[10,47],"summary":[11],"to":[12,20,56,60,104],"describe":[13],"the":[14,26,34,37,58,67,81,106,117,122,127,132,152],"highlights":[15],"of":[16,36,154],"video":[18,27],"according":[19],"multimodal":[21,140],"resources,":[22],"in":[23,44],"our":[24,144,158],"case,":[25],"content":[28,48],"and":[29,126],"its":[30],"transcript.":[31],"Inspired":[32],"by":[33,63],"success":[35],"large-scale":[38],"generative":[39],"pre-trained":[40],"language":[41],"model":[42,94,159],"(GPLM)":[43],"high-quality":[46],"(e.g.,":[49],"summary),":[50],"recent":[51],"MAS":[52],"methods":[53],"have":[54,161],"proposed":[55],"adapt":[57],"GPLM":[59],"this":[61,97],"task":[62],"equipping":[64],"it":[65],"with":[66,151,171],"visual":[68,77,84,90,108,156],"information,":[69,91,157],"which":[70,92],"is":[71],"often":[72],"obtained":[73],"through":[74],"general-purpose":[76],"feature":[78],"extractor.":[79],"However,":[80],"generally":[82],"extracted":[83],"features":[85],"may":[86],"overlook":[87],"some":[88],"summary-worthy":[89,107,118,155],"impedes":[93],"performance.":[95],"In":[96],"work,":[98],"we":[99],"propose":[100],"novel":[102],"approach":[103],"learning":[105],"representation":[109],"that":[110,129,143],"facilitates":[111],"summarization.":[113],"Our":[114],"method":[115,145],"exploits":[116],"information":[119],"from":[120,131],"both":[121],"cross-modal":[123],"transcript":[124],"data":[125],"knowledge":[128],"distills":[130],"pseudo":[133],"summary.":[134],"Extensive":[135],"experiments":[136],"on":[137,165],"three":[138],"public":[139],"datasets":[141,167,170],"show":[142],"outperforms":[146],"all":[147],"competing":[148],"baselines.":[149],"Furthermore,":[150],"advantages":[153],"can":[160],"significant":[163],"improvement":[164],"small":[166],"or":[168],"even":[169],"limited":[172],"training":[173],"data.":[174]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2023-05-10T00:00:00"}