{"id":"https://openalex.org/W4413144608","doi":"https://doi.org/10.1109/cvpr52734.2025.00788","title":"Event-Equalized Dense Video Captioning","display_name":"Event-Equalized Dense Video Captioning","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413144608","doi":"https://doi.org/10.1109/cvpr52734.2025.00788"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5034105691","display_name":"Kangyi Wu","orcid":"https://orcid.org/0000-0001-7382-4949"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kangyi Wu","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432714","display_name":"Peng Li","orcid":"https://orcid.org/0000-0002-5235-6311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengna Li","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060230441","display_name":"Jingwen Fu","orcid":"https://orcid.org/0000-0003-3256-1497"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingwen Fu","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045807386","display_name":"Yizhe Li","orcid":"https://orcid.org/0000-0002-4379-6200"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yizhe Li","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100741279","display_name":"Yang Wu","orcid":"https://orcid.org/0000-0001-8010-6857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Wu","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350529","display_name":"Yuhan Liu","orcid":"https://orcid.org/0000-0002-8464-0771"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhan Liu","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111883017","display_name":"Jinjun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinjun Wang","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113827261","display_name":"Sanping Zhou","orcid":"https://orcid.org/0000-0003-4100-2304"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanping Zhou","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3412,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8931235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8417","last_page":"8427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9987000226974487,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9987000226974487,"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/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/T11019","display_name":"Image Enhancement Techniques","score":0.9939000010490417,"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":0.9633828401565552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7921087741851807},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7006736397743225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35174131393432617},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12483221292495728}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9633828401565552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921087741851807},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7006736397743225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35174131393432617},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12483221292495728},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562"],"abstract_inverted_index":{"Dense":[0,154],"video":[1,100,191],"captioning":[2],"aims":[3],"to":[4,32,62,98,106,112,124,128,140,158],"localize":[5],"and":[6,75,136,163,174,184],"caption":[7],"all":[8,165],"events":[9,36,47,67,104,135,167],"in":[10,48],"arbitrary":[11],"untrimmed":[12],"videos.":[13],"Although":[14],"previous":[15],"methods":[16,183],"have":[17,68,107,129],"achieved":[18],"appealing":[19],"results,":[20],"they":[21],"still":[22],"face":[23],"the":[24,43,160,178,181],"issue":[25],"of":[26,46,133,180],"temporal":[27,39,44,89,161],"bias,":[28],"i.e,":[29],"models":[30],"tend":[31,105],"focus":[33],"more":[34,69,78],"on":[35,55,171,189],"with":[37,87],"certain":[38],"characteristics.":[40],"Specifically,":[41],"1)":[42],"distribution":[45],"training":[49],"datasets":[50,57],"is":[51],"uneven.":[52],"Models":[53],"trained":[54],"these":[56],"will":[58,76],"pay":[59,137],"less":[60],"attention":[61,139],"out-of-distribution":[63],"events.":[64],"2)":[65],"long-duration":[66],"frame":[70],"features":[71,127],"than":[72],"short":[73],"ones":[74],"attract":[77],"attention.":[79],"To":[80],"address":[81],"this,":[82],"we":[83,122,145],"argue":[84],"that":[85],"events,":[86],"varying":[88],"characteristics,":[90],"should":[91],"be":[92],"treated":[93],"equally":[94],"when":[95],"it":[96],"comes":[97],"dense":[99,190],"captioning.":[101,192],"Intuitively,":[102],"different":[103],"distinct":[108],"visual":[109,126],"differences":[110],"due":[111],"varied":[113],"camera":[114],"views,":[115],"backgrounds,":[116],"or":[117],"subjects.":[118],"Inspired":[119],"by":[120],"that,":[121],"intend":[123],"utilize":[125],"an":[130],"approximate":[131],"perception":[132],"possible":[134,166],"equal":[138],"them.":[141],"In":[142],"this":[143],"paper,":[144],"introduce":[146],"a":[147],"simple":[148],"but":[149],"effective":[150],"framework,":[151],"called":[152],"Event-Equalized":[153],"Video":[155],"Captioning":[156],"(E2DVC)":[157],"overcome":[159],"bias":[162],"treat":[164],"equally.":[168],"Experimental":[169],"results":[170],"ActivityNet":[172],"Captions":[173],"YouCook2":[175],"dataset":[176],"validate":[177],"effectiveness":[179],"proposed":[182],"show":[185],"State-of-the-art":[186],"(SOTA)":[187],"performance":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-10-10T00:00:00"}