{"id":"https://openalex.org/W4402980157","doi":"https://doi.org/10.1109/icme57554.2024.10688196","title":"A Dataset with Multi-Modal Information and Multi-Granularity Descriptions for Video Captioning","display_name":"A Dataset with Multi-Modal Information and Multi-Granularity Descriptions for Video Captioning","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980157","doi":"https://doi.org/10.1109/icme57554.2024.10688196"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688196","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688196","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/A5108993608","display_name":"Mingrui Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingrui Xiao","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101774556","display_name":"Zijian Zeng","orcid":"https://orcid.org/0009-0004-6133-3842"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijian Zeng","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030888636","display_name":"Yue Zheng","orcid":"https://orcid.org/0009-0005-0685-436X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zheng","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100689675","display_name":"Shu Yang","orcid":"https://orcid.org/0000-0003-1587-0474"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu Yang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346266","display_name":"Yali Li","orcid":"https://orcid.org/0000-0002-6629-7228"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yali Li","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030965866","display_name":"Shengjin Wang","orcid":"https://orcid.org/0000-0001-7809-1932"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengjin Wang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5108993608"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.5263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66327446,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9955999851226807,"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":0.9933000206947327,"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/granularity","display_name":"Granularity","score":0.9065883159637451},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8596422672271729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8195738792419434},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7154899835586548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38750630617141724},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34872570633888245},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0678321123123169}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.9065883159637451},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8596422672271729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8195738792419434},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7154899835586548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38750630617141724},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34872570633888245},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0678321123123169},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/icme57554.2024.10688196","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688196","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":0,"referenced_works":[],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Video":[0],"captioning":[1],"aims":[2],"to":[3,92],"generate":[4],"natural":[5],"language":[6],"descriptions":[7],"automatically":[8],"from":[9,71,83],"videos.":[10,147],"While":[11],"datasets":[12],"like":[13],"MSVD":[14],"and":[15,29,36,88],"MSR-VTT":[16],"have":[17],"driven":[18],"research":[19],"in":[20,51,146],"recent":[21],"years,":[22],"they":[23],"predominantly":[24],"focus":[25],"on":[26,101,153],"visual":[27],"features":[28],"describe":[30],"simple":[31],"actions,":[32],"ignoring":[33],"audio,":[34],"text,":[35],"other":[37],"modal":[38,130],"information.":[39],"Which,":[40],"however,":[41],"is":[42],"limited,":[43],"because":[44],"multi-modal":[45,69,105,115,123,136],"information":[46,70,124,137],"plays":[47],"an":[48],"important":[49],"role":[50],"generating":[52,98],"accurate":[53,99],"captions.":[54,90],"In":[55],"this":[56],"study,":[57],"we":[58,109,126],"introduce":[59],"a":[60,111],"dataset,":[61],"News-11k,":[62],"which":[63],"includes":[64],"over":[65],"150,000":[66],"captions":[67,82,100],"with":[68],"more":[72],"than":[73],"11,000":[74],"selected":[75],"news":[76,96],"video":[77,116],"clips.":[78],"We":[79],"annotate":[80],"multi-granularity":[81],"three":[84],"perspectives:":[85],"coarse-grained,":[86],"medium-grained,":[87],"fine-grained":[89],"Due":[91],"the":[93,120,128,140,143],"characteristics":[94],"of":[95,122,142],"videos,":[97],"our":[102],"dataset":[103],"requires":[104],"understanding":[106,141],"ability.":[107],"Therefore,":[108],"propose":[110],"baseline":[112],"model":[113],"for":[114],"captioning.":[117],"To":[118],"address":[119],"challenge":[121],"fusion,":[125],"devise":[127],"concatenating":[129],"embedding":[131],"strategy.":[132],"Experiments":[133],"indicate":[134],"that":[135],"significantly":[138],"enhances":[139],"deeper":[144],"semantics":[145],"Data":[148],"will":[149],"be":[150],"made":[151],"available":[152],"https://github.com/David-Zeng-Zijian/News-11k.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}