{"id":"https://openalex.org/W4400066828","doi":"https://doi.org/10.1145/3663976.3664228","title":"The effect of using video title in attention-based video summarization","display_name":"The effect of using video title in attention-based video summarization","publication_year":2024,"publication_date":"2024-04-26","ids":{"openalex":"https://openalex.org/W4400066828","doi":"https://doi.org/10.1145/3663976.3664228"},"language":"en","primary_location":{"id":"doi:10.1145/3663976.3664228","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3663976.3664228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 2nd Asia Conference on Computer Vision, Image Processing and Pattern Recognition","raw_type":"proceedings-article"},"type":"conference-paper","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/A5016767409","display_name":"C. H. Li","orcid":"https://orcid.org/0009-0003-2767-3336"},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changwei Li","raw_affiliation_strings":["University of Cincinnati, USA"],"raw_orcid":"https://orcid.org/0009-0003-2767-3336","affiliations":[{"raw_affiliation_string":"University of Cincinnati, USA","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057845763","display_name":"Zhi-Ting Yeh","orcid":"https://orcid.org/0009-0004-8522-6937"},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiting Yeh","raw_affiliation_strings":["University of Cincinnati, USA"],"raw_orcid":"https://orcid.org/0009-0004-8522-6937","affiliations":[{"raw_affiliation_string":"University of Cincinnati, USA","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087845158","display_name":"Jeshmitha Gunuganti","orcid":"https://orcid.org/0000-0003-1725-6398"},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeshmitha Gunuganti","raw_affiliation_strings":["University of Cincinnati, USA"],"raw_orcid":"https://orcid.org/0000-0003-1725-6398","affiliations":[{"raw_affiliation_string":"University of Cincinnati, USA","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026387981","display_name":"J. Chang","orcid":"https://orcid.org/0009-0001-7269-4975"},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiabin Chang","raw_affiliation_strings":["University of Cincinnati, USA"],"raw_orcid":"https://orcid.org/0009-0001-7269-4975","affiliations":[{"raw_affiliation_string":"University of Cincinnati, USA","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103226773","display_name":"Mehdi Norouzi","orcid":"https://orcid.org/0000-0003-1701-2668"},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehdi Norouzi","raw_affiliation_strings":["University of Cincinnati, USA"],"raw_orcid":"https://orcid.org/0000-0003-1701-2668","affiliations":[{"raw_affiliation_string":"University of Cincinnati, USA","institution_ids":["https://openalex.org/I63135867"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63135867"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09475927,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998999834060669,"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":0.9998999834060669,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9307944774627686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7356616854667664},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5040746927261353},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4343684911727905},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.3886105418205261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30111435055732727}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9307944774627686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7356616854667664},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5040746927261353},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4343684911727905},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3886105418205261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30111435055732727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3663976.3664228","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3663976.3664228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 2nd Asia Conference on Computer Vision, Image Processing and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1996525269","https://openalex.org/W2097117768","https://openalex.org/W2194775991","https://openalex.org/W2529272619","https://openalex.org/W2737677090","https://openalex.org/W2963524571","https://openalex.org/W2963670497","https://openalex.org/W2963919999","https://openalex.org/W2964167369","https://openalex.org/W2967219836","https://openalex.org/W3033386097","https://openalex.org/W3210314917","https://openalex.org/W4234552385"],"related_works":["https://openalex.org/W2032408534","https://openalex.org/W2067511866","https://openalex.org/W4389850132","https://openalex.org/W1574724839","https://openalex.org/W2365286546","https://openalex.org/W2377190948","https://openalex.org/W2096476311","https://openalex.org/W4221117092","https://openalex.org/W4361855866","https://openalex.org/W169721953"],"abstract_inverted_index":{"The":[0,103,149],"current":[1],"state-of-the-art":[2],"supervised":[3],"video":[4,80,114],"summarization":[5,157],"models":[6,66],"employ":[7],"transformers":[8],"as":[9,20],"either":[10],"encoders":[11,21,60],"or":[12],"classifiers.":[13],"Self-attention":[14],"layers":[15],"are":[16,91],"being":[17],"widely":[18],"adopted":[19],"because":[22],"of":[23,36,49,55,145,151],"their":[24],"simplicity":[25],"and":[26,58,82,96,165],"efficiency":[27],"in":[28,39],"capturing":[29],"correlation":[30,35,78,129],"among":[31,130],"features.":[32],"However,":[33],"the":[34,46,77,108,113,128,143,146,152,156],"visual":[37,65,84],"frames":[38],"long":[40],"sequences":[41],"does":[42],"not":[43],"necessarily":[44],"represent":[45],"global":[47],"storyline":[48],"a":[50,73,87],"video.":[51],"Building":[52],"on":[53,127,162,167],"top":[54],"pre-trained":[56],"text":[57],"image":[59],"provided":[61],"by":[62,94,111,124,160],"CLIP":[63],"(transferable":[64],"from":[67],"natural":[68],"language":[69],"supervision),":[70],"we":[71,134],"propose":[72,135],"model":[74,154],"which":[75,119],"learns":[76],"between":[79],"title":[81,117],"frame":[83,100],"features":[85],"using":[86],"cross-attention.":[88],"Image-title":[89],"representations":[90],"further":[92],"analyzed":[93],"self-attention":[95],"used":[97],"for":[98],"estimating":[99],"importance":[101],"scores.":[102],"goal":[104],"is":[105,120],"to":[106,122],"enhance":[107,142],"model\u2019s":[109],"performance":[110,144,150,158],"providing":[112],"theme":[115],"-":[116,118],"challenging":[121],"learn":[123],"solely":[125],"relying":[126],"individual":[131],"frames.":[132],"Furthermore,":[133],"an":[136],"improved":[137],"loss":[138],"function":[139],"that":[140],"can":[141],"summary":[147],"generator.":[148],"proposed":[153],"increased":[155],"(F1-Score)":[159],"1.1%":[161],"TvSum":[163],"dataset":[164],"2.2%":[166],"SumMe":[168],"dataset.":[169]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}