{"id":"https://openalex.org/W4372348950","doi":"https://doi.org/10.1109/icassp49357.2023.10095659","title":"Enhancing Multimodal Alignment with Momentum Augmentation for Dense Video Captioning","display_name":"Enhancing Multimodal Alignment with Momentum Augmentation for Dense Video Captioning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372348950","doi":"https://doi.org/10.1109/icassp49357.2023.10095659"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095659","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5059464565","display_name":"Yiwei Wei","orcid":"https://orcid.org/0000-0002-7627-5487"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiwei Wei","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101399146","display_name":"Shaozu Yuan","orcid":"https://orcid.org/0000-0001-5084-7064"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaozu Yuan","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357843","display_name":"Meng Chen","orcid":"https://orcid.org/0000-0001-5476-8662"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Chen","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059464565"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03748525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9993000030517578,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9990000128746033,"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/closed-captioning","display_name":"Closed captioning","score":0.9607936143875122},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.794009268283844},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7718179225921631},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6050374507904053},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5107007622718811},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47783923149108887},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.41754353046417236},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4015892744064331},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09071868658065796},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08569765090942383},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07002079486846924}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9607936143875122},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794009268283844},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7718179225921631},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6050374507904053},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5107007622718811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47783923149108887},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.41754353046417236},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4015892744064331},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09071868658065796},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08569765090942383},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07002079486846924},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095659","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2104352549","https://openalex.org/W2133459682","https://openalex.org/W2526050071","https://openalex.org/W2891303919","https://openalex.org/W2962799512","https://openalex.org/W2963351113","https://openalex.org/W2963524571","https://openalex.org/W2963782415","https://openalex.org/W2963916161","https://openalex.org/W2985144848","https://openalex.org/W2997296614","https://openalex.org/W3034815696","https://openalex.org/W3035524453","https://openalex.org/W3184735396","https://openalex.org/W4214663214","https://openalex.org/W4226097354","https://openalex.org/W4229042118","https://openalex.org/W4287777632","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6770717842","https://openalex.org/W6775036685","https://openalex.org/W6777481484","https://openalex.org/W6798805250","https://openalex.org/W6810880846","https://openalex.org/W6811072154","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":{"Dense":[0],"video":[1,11,98,115],"captioning":[2],"aims":[3],"to":[4,32,45,50,68,73,92],"localize":[5],"multiple":[6],"events":[7],"from":[8],"an":[9,87],"untrimmed":[10],"and":[12,81],"generate":[13],"corresponding":[14],"captions":[15],"for":[16,41,96,113],"each":[17],"event.":[18],"Fusing":[19],"different":[20,70],"modalities(e.g.":[21],"rgb,":[22],"flow,":[23],"audio)":[24],"via":[25],"transformer":[26,63],"structure":[27,64],"is":[28,39],"a":[29,61],"promising":[30],"way":[31],"improve":[33],"the":[34,42,75],"caption":[35],"performance.":[36],"However,":[37],"it":[38],"challenging":[40],"cross-modal":[43],"encoder":[44],"learn":[46],"multimodal":[47,110],"interactions":[48],"due":[49],"their":[51],"inherent":[52],"disparities":[53],"of":[54,77],"distribution.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,85],"propose":[60],"novel":[62],"with":[65],"contrastive":[66,83],"learning":[67,95],"align":[69],"modalities.":[71],"Specifically,":[72],"avoid":[74],"limitation":[76],"small":[78],"batch":[79],"size":[80],"false":[82],"targets,":[84],"design":[86],"event-aligned":[88],"momentum":[89],"augmentation":[90],"strategy":[91],"apply":[93],"contrast":[94],"dense":[97,114],"captioning.":[99,116],"The":[100],"experimental":[101],"result":[102],"shows":[103],"that":[104],"our":[105],"proposals":[106],"outperform":[107],"all":[108],"existing":[109],"fusion":[111],"methods":[112]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}