{"id":"https://openalex.org/W3167776110","doi":"https://doi.org/10.1109/icme51207.2021.9428252","title":"Detecting Highlighted Video Clips Through Emotion-Enhanced Audio-Visual Cues","display_name":"Detecting Highlighted Video Clips Through Emotion-Enhanced Audio-Visual Cues","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3167776110","doi":"https://doi.org/10.1109/icme51207.2021.9428252","mag":"3167776110"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","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/A5065841632","display_name":"Linkang Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linkang Hu","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science and Technology","School of Computer Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science and Technology","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100724440","display_name":"Weidong He","orcid":"https://orcid.org/0000-0003-1986-9710"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong He","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science and Technology","School of Computer Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science and Technology","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350631","display_name":"Le Zhang","orcid":"https://orcid.org/0000-0002-6930-8674"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Zhang","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science and Technology","School of Computer Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science and Technology","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101570536","display_name":"Tong Xu","orcid":"https://orcid.org/0000-0001-5564-192X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xu","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science and Technology","School of Computer Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science and Technology","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101862104","display_name":"Hui Xiong","orcid":"https://orcid.org/0000-0001-6016-6465"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hui Xiong","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048237545","display_name":"Enhong Chen","orcid":"https://orcid.org/0000-0002-4835-4102"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enhong Chen","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science and Technology","School of Computer Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science and Technology","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.191,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48029384,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"50","issue":null,"first_page":"1","last_page":"6"},"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.9707000255584717,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8159846067428589},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6463030576705933},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6459628343582153},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5988752245903015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5222007632255554},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5046895742416382},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.49403244256973267},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4824284017086029},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.422870934009552},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35080486536026},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3381492793560028},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3106711208820343},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2684577703475952},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.26733291149139404},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.16957607865333557},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.07350021600723267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8159846067428589},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6463030576705933},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6459628343582153},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5988752245903015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5222007632255554},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5046895742416382},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.49403244256973267},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4824284017086029},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.422870934009552},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35080486536026},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3381492793560028},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3106711208820343},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2684577703475952},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.26733291149139404},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.16957607865333557},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.07350021600723267},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme51207.2021.9428252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1501669607","https://openalex.org/W1522734439","https://openalex.org/W1924343884","https://openalex.org/W2016053056","https://openalex.org/W2104657103","https://openalex.org/W2465534249","https://openalex.org/W2467794422","https://openalex.org/W2552027021","https://openalex.org/W2562476021","https://openalex.org/W2737677090","https://openalex.org/W2761514455","https://openalex.org/W2793756304","https://openalex.org/W2897230578","https://openalex.org/W2919974746","https://openalex.org/W2945956523","https://openalex.org/W2963729528","https://openalex.org/W2963919999","https://openalex.org/W2964167369","https://openalex.org/W2994107668","https://openalex.org/W2994814507","https://openalex.org/W3035111931","https://openalex.org/W4293665662","https://openalex.org/W6630073874","https://openalex.org/W6631456553","https://openalex.org/W6640109428","https://openalex.org/W6713349023","https://openalex.org/W6719667659","https://openalex.org/W6729263887","https://openalex.org/W6729831399","https://openalex.org/W6743913890","https://openalex.org/W6771724579","https://openalex.org/W7073743773"],"related_works":["https://openalex.org/W2417253731","https://openalex.org/W2350469024","https://openalex.org/W2491583298","https://openalex.org/W2036154621","https://openalex.org/W2327827625","https://openalex.org/W2395860100","https://openalex.org/W795077857","https://openalex.org/W4402262758","https://openalex.org/W3096250625","https://openalex.org/W3011716530"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"the":[4,36,57,92,96,110,145],"growing":[5],"research":[6],"interests":[7],"in":[8,19,60],"video":[9,61],"highlight":[10,65,136],"detection.":[11,66],"Existing":[12],"studies":[13],"mainly":[14],"focus":[15],"on":[16,26,32,102,141],"detecting":[17],"highlights":[18,43,79],"user-generated":[20],"videos":[21,45],"with":[22,46,74],"simple":[23],"topics":[24],"based":[25],"visual":[27,33,127],"content.":[28],"However,":[29],"relying":[30],"solely":[31],"features":[34,90,104],"limits":[35],"ability":[37],"of":[38,119,147],"conventional":[39],"methods":[40],"to":[41,55,63,77,105,115],"capture":[42],"for":[44,80,134],"more":[47],"complicated":[48],"semantics,":[49],"like":[50],"movies.":[51],"Therefore,":[52],"we":[53,68,86],"propose":[54],"mine":[56],"emotional":[58,107,124],"information":[59],"sounds":[62],"enhance":[64],"Specifically,":[67],"design":[69],"a":[70],"novel":[71],"emotion-enhanced":[72],"framework":[73],"multi-stage":[75],"fusion":[76,99,112],"detect":[78],"complex":[81],"videos.":[82],"Along":[83],"this":[84],"line,":[85],"first":[87],"extract":[88],"multi-grained":[89],"from":[91],"audio":[93,103,123],"waves.":[94],"Then,":[95],"tailored-designed":[97],"intra-modal":[98],"is":[100,113],"applied":[101],"obtain":[106],"representation.":[108],"Furthermore,":[109],"cross-modal":[111],"developed":[114],"generate":[116],"comprehensive":[117],"representation":[118,130],"clip":[120],"by":[121],"merging":[122],"representations":[125],"and":[126],"features.":[128],"This":[129],"can":[131],"be":[132],"leveraged":[133],"predicting":[135],"probability.":[137],"Finally,":[138],"extensive":[139],"experiments":[140],"real-world":[142],"datasets":[143],"demonstrate":[144],"effectiveness":[146],"our":[148],"method.":[149]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
