{"id":"https://openalex.org/W4402979147","doi":"https://doi.org/10.1109/icme57554.2024.10687664","title":"A Multimodal Transformer for Live Streaming Highlight Prediction","display_name":"A Multimodal Transformer for Live Streaming Highlight Prediction","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979147","doi":"https://doi.org/10.1109/icme57554.2024.10687664"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","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/A5001300667","display_name":"Jiaxin Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaxin Deng","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artifcial Intelligence Systems, Institute of Automation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artifcial Intelligence Systems, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066247528","display_name":"Shiyao Wang","orcid":"https://orcid.org/0000-0002-1567-8012"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyao Wang","raw_affiliation_strings":["KuaiShou Inc.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"KuaiShou Inc.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034770996","display_name":"Dong Shen","orcid":"https://orcid.org/0000-0003-1063-1351"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Shen","raw_affiliation_strings":["KuaiShou Inc.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"KuaiShou Inc.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100598364","display_name":"Liqin Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqin Zhao","raw_affiliation_strings":["KuaiShou Inc.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"KuaiShou Inc.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101591804","display_name":"Fan Yang","orcid":"https://orcid.org/0009-0005-4570-5885"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["KuaiShou Inc.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"KuaiShou Inc.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060887535","display_name":"G.J. Zhou","orcid":"https://orcid.org/0000-0002-0277-4638"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guorui Zhou","raw_affiliation_strings":["KuaiShou Inc.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"KuaiShou Inc.,Beijing,China","institution_ids":["https://openalex.org/I4210155967"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100675867","display_name":"Gaofeng Meng","orcid":"https://orcid.org/0000-0002-7103-6321"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaofeng Meng","raw_affiliation_strings":["Chinese Academy of Sciences,State Key Laboratory of Multimodal Artifcial Intelligence Systems, Institute of Automation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artifcial Intelligence Systems, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5001300667"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":0.7873,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73492746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","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/T11165","display_name":"Image and Video Quality Assessment","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/T11019","display_name":"Image Enhancement Techniques","score":0.9833999872207642,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9452999830245972,"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/computer-science","display_name":"Computer science","score":0.6417521834373474},{"id":"https://openalex.org/keywords/live-streaming","display_name":"Live streaming","score":0.6319310665130615},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5337209701538086},{"id":"https://openalex.org/keywords/video-streaming","display_name":"Video streaming","score":0.48365318775177},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.29153820872306824},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.25966301560401917},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.13859465718269348},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12745821475982666},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06935572624206543}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6417521834373474},{"id":"https://openalex.org/C2776741261","wikidata":"https://www.wikidata.org/wiki/Q3027665","display_name":"Live streaming","level":2,"score":0.6319310665130615},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5337209701538086},{"id":"https://openalex.org/C2986160907","wikidata":"https://www.wikidata.org/wiki/Q220499","display_name":"Video streaming","level":2,"score":0.48365318775177},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29153820872306824},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.25966301560401917},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13859465718269348},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12745821475982666},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06935572624206543}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/W2143331230","https://openalex.org/W2149427297","https://openalex.org/W2797074994","https://openalex.org/W2895907803","https://openalex.org/W2963919999","https://openalex.org/W3106645934","https://openalex.org/W3197682865","https://openalex.org/W3198464943","https://openalex.org/W4286233709","https://openalex.org/W4312247461","https://openalex.org/W4312348182","https://openalex.org/W4384659780","https://openalex.org/W6838542419"],"related_works":["https://openalex.org/W2157648540","https://openalex.org/W2293038204","https://openalex.org/W3082618691","https://openalex.org/W4245721987","https://openalex.org/W4238425831","https://openalex.org/W2132672198","https://openalex.org/W4200631746","https://openalex.org/W4235833544","https://openalex.org/W4393213830","https://openalex.org/W2149775235"],"abstract_inverted_index":{"Recently,":[0],"live":[1,27,88],"streaming":[2,28,89],"platforms":[3],"have":[4],"gained":[5],"immense":[6],"popularity.":[7],"Traditional":[8],"video":[9],"highlight":[10],"detection":[11],"mainly":[12],"focuses":[13],"on":[14,130],"visual":[15],"features":[16],"and":[17,21,36,44,95,111,134,143],"utilizes":[18],"both":[19,131],"past":[20],"future":[22,34],"content":[23],"for":[24,87],"prediction.":[25],"However,":[26],"requires":[29],"models":[30],"to":[31,69,105,145],"infer":[32],"without":[33],"frames":[35],"process":[37],"complex":[38],"multimodal":[39,54],"interactions,":[40],"including":[41],"images,":[42],"audio":[43],"text":[45],"comments.":[46],"To":[47],"address":[48],"these":[49],"issues,":[50],"we":[51,98,138],"propose":[52,99],"a":[53,63,100,108,117],"transformer":[55],"that":[56],"incorporates":[57],"historical":[58],"look-back":[59],"windows.":[60],"We":[61],"introduce":[62],"novel":[64,101],"Modality":[65],"Temporal":[66],"Alignment":[67],"Module":[68],"handle":[70],"the":[71],"temporal":[72],"shift":[73],"of":[74],"cross-modal":[75],"signals.":[76],"Additionally,":[77],"using":[78],"existing":[79],"datasets":[80],"with":[81],"limited":[82],"manual":[83],"annotations":[84],"is":[85],"insufficient":[86],"whose":[90],"topics":[91],"are":[92],"constantly":[93],"updated":[94],"changed.":[96],"Therefore,":[97],"Border-aware":[102],"Pairwise":[103],"Loss":[104],"learn":[106],"from":[107],"large-scale":[109],"dataset":[110,142],"utilize":[112],"user":[113],"implicit":[114],"feedback":[115],"as":[116],"weak":[118],"supervision":[119],"signal.":[120],"Extensive":[121],"experiments":[122],"show":[123],"our":[124,141],"model":[125],"outperforms":[126],"various":[127],"strong":[128],"baselines":[129],"real-world":[132],"scenarios":[133],"public":[135],"datasets.":[136],"And":[137],"will":[139],"release":[140],"code":[144],"better":[146],"assess":[147],"this":[148],"topic.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
