{"id":"https://openalex.org/W3206570195","doi":"https://doi.org/10.1145/3474085.3475321","title":"Multimodal Video Summarization via Time-Aware Transformers","display_name":"Multimodal Video Summarization via Time-Aware Transformers","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206570195","doi":"https://doi.org/10.1145/3474085.3475321","mag":"3206570195"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475321","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475321","pdf_url":null,"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 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3474085.3475321","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017342089","display_name":"Xindi Shang","orcid":"https://orcid.org/0000-0002-9308-2927"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Xindi Shang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039592275","display_name":"Zehuan Yuan","orcid":"https://orcid.org/0000-0002-0349-9367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zehuan Yuan","raw_affiliation_strings":["Bytedance.Inc, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Bytedance.Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100608462","display_name":"Anran Wang","orcid":"https://orcid.org/0000-0001-8112-5830"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anran Wang","raw_affiliation_strings":["Bytedance.Inc, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Bytedance.Inc, Singapore, Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055085354","display_name":"Changhu Wang","orcid":"https://orcid.org/0000-0001-8373-2597"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changhu Wang","raw_affiliation_strings":["ByteDance.Inc, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance.Inc, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5017342089"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":2.3056,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.90344771,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1756","last_page":"1765"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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":0.9972000122070312,"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":0.9011428356170654},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8799920082092285},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.7760214805603027},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7511005401611328},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5181964039802551},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4905528426170349},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46423640847206116},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.42033398151397705},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3682383894920349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3603588938713074},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.16633975505828857}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9011428356170654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8799920082092285},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.7760214805603027},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7511005401611328},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5181964039802551},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4905528426170349},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46423640847206116},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.42033398151397705},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3682383894920349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3603588938713074},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.16633975505828857},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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":1,"locations":[{"id":"doi:10.1145/3474085.3475321","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475321","pdf_url":null,"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 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3474085.3475321","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475321","pdf_url":null,"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 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1586939924","https://openalex.org/W1956340063","https://openalex.org/W2026012689","https://openalex.org/W2060724430","https://openalex.org/W2087095333","https://openalex.org/W2093541376","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2117051369","https://openalex.org/W2120645068","https://openalex.org/W2139501017","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2461084364","https://openalex.org/W2523993696","https://openalex.org/W2525579820","https://openalex.org/W2529272619","https://openalex.org/W2556388456","https://openalex.org/W2584992898","https://openalex.org/W2600463316","https://openalex.org/W2604178507","https://openalex.org/W2607119937","https://openalex.org/W2623255526","https://openalex.org/W2759570332","https://openalex.org/W2766375149","https://openalex.org/W2786670585","https://openalex.org/W2808413133","https://openalex.org/W2889844776","https://openalex.org/W2891444075","https://openalex.org/W2892181857","https://openalex.org/W2899274165","https://openalex.org/W2951098185","https://openalex.org/W2953104586","https://openalex.org/W2962934715","https://openalex.org/W2962944176","https://openalex.org/W2963351113","https://openalex.org/W2963403868","https://openalex.org/W2963432616","https://openalex.org/W2963916161","https://openalex.org/W2963925437","https://openalex.org/W2964089206","https://openalex.org/W2964109005","https://openalex.org/W2971680695","https://openalex.org/W2981851019","https://openalex.org/W2984008963","https://openalex.org/W2985185987","https://openalex.org/W2990113535","https://openalex.org/W2997326549","https://openalex.org/W2997591391","https://openalex.org/W3035635319","https://openalex.org/W3049478012","https://openalex.org/W3099839483","https://openalex.org/W3104210310","https://openalex.org/W3104915307","https://openalex.org/W3206723373","https://openalex.org/W4288083805","https://openalex.org/W4292928772"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W4287205925","https://openalex.org/W3161658874"],"abstract_inverted_index":{"With":[0],"the":[1,13,18,63,68,71,90,98,119,128,141,147,159],"growing":[2],"number":[3],"of":[4,17,38],"videos":[5,39,75],"in":[6,45],"video":[7,20,47,133],"sharing":[8],"platforms,":[9],"how":[10],"to":[11,61,88,92,126],"facilitate":[12],"searching":[14],"and":[15,33,52,59,157,165],"browsing":[16],"user-generated":[19],"has":[21],"attracted":[22],"intense":[23],"attention":[24,112,115],"by":[25],"multimedia":[26],"community.":[27],"To":[28],"help":[29],"people":[30],"efficiently":[31],"search":[32],"browse":[34],"relevant":[35],"videos,":[36],"summaries":[37],"become":[40],"important.":[41],"The":[42,114],"prior":[43],"works":[44],"multimodal":[46,64,95],"summarization":[48],"mainly":[49],"explore":[50,127],"visual":[51],"ASR":[53],"tokens":[54],"as":[55],"two":[56],"separate":[57],"sources":[58],"struggle":[60],"fuse":[62,140],"information":[65,73,130],"for":[66,97,145],"generating":[67],"summaries.":[69],"However,":[70],"time":[72,124,129],"inside":[74,132],"is":[76,86,155],"commonly":[77],"ignored.":[78],"In":[79],"this":[80],"paper,":[81],"we":[82],"find":[83],"that":[84,151],"it":[85],"important":[87],"leverage":[89],"timestamps":[91],"accurately":[93],"incorporate":[94],"signals":[96],"task.":[99],"We":[100],"propose":[101],"a":[102,108],"Time-Aware":[103],"Multimodal":[104],"Transformer":[105],"(TAMT)":[106],"with":[107],"novel":[109],"short-term":[110],"order-sensitive":[111],"mechanism.":[113],"mechanism":[116],"can":[117,139],"attend":[118],"inputs":[120],"differently":[121],"based":[122],"on":[123,162],"difference":[125],"inherent":[131],"more":[134],"thoroughly.":[135],"As":[136],"such,":[137],"TAMT":[138],"different":[142],"modalities":[143],"better":[144],"summarizing":[146],"videos.":[148],"Experiments":[149],"show":[150],"our":[152],"proposed":[153],"approach":[154],"effective":[156],"achieves":[158],"state-of-the-art":[160],"performances":[161],"both":[163],"YouCookII":[164],"open-domain":[166],"How2":[167],"datasets.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
