{"id":"https://openalex.org/W4403780703","doi":"https://doi.org/10.1145/3664647.3681214","title":"Egocentric Vehicle Dense Video Captioning","display_name":"Egocentric Vehicle Dense Video Captioning","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780703","doi":"https://doi.org/10.1145/3664647.3681214"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681214","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5068867974","display_name":"Feiyu Chen","orcid":"https://orcid.org/0009-0002-9098-4447"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feiyu Chen","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-9098-4447","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055434477","display_name":"Cong Xu","orcid":"https://orcid.org/0000-0002-9288-1743"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong Xu","raw_affiliation_strings":["IEIT SYSTEMS Co., Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9288-1743","affiliations":[{"raw_affiliation_string":"IEIT SYSTEMS Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100723367","display_name":"Qi Jia","orcid":"https://orcid.org/0000-0003-0481-4311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Jia","raw_affiliation_strings":["IEIT SYSTEMS Co., Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0481-4311","affiliations":[{"raw_affiliation_string":"IEIT SYSTEMS Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100703462","display_name":"Yihua Wang","orcid":"https://orcid.org/0009-0004-7470-960X"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihua Wang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-7470-960X","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350519","display_name":"Yuhan Liu","orcid":"https://orcid.org/0000-0001-5391-0217"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhan Liu","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5391-0217","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haotian Zhang","orcid":"https://orcid.org/0000-0001-5438-5960"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotian Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5438-5960","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033231117","display_name":"Endong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Endong Wang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-8104-6074","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5068867974"],"corresponding_institution_ids":["https://openalex.org/I25254941"],"apc_list":null,"apc_paid":null,"fwci":0.9523,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77036133,"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":"137","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9991999864578247,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9927999973297119,"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":0.9002467393875122},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7264742851257324},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4124349355697632},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4035932719707489},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.37016093730926514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3565157949924469},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1159297525882721}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9002467393875122},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7264742851257324},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4124349355697632},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4035932719707489},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.37016093730926514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3565157949924469},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1159297525882721}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681214","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":48,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1927052826","https://openalex.org/W1956340063","https://openalex.org/W2600463316","https://openalex.org/W2755876276","https://openalex.org/W2783963507","https://openalex.org/W2885138528","https://openalex.org/W2951098185","https://openalex.org/W2952132648","https://openalex.org/W2962799512","https://openalex.org/W2963016445","https://openalex.org/W2963315828","https://openalex.org/W2963351113","https://openalex.org/W2963753226","https://openalex.org/W2963916161","https://openalex.org/W2968104955","https://openalex.org/W2971278746","https://openalex.org/W2985144848","https://openalex.org/W2985775862","https://openalex.org/W2997706915","https://openalex.org/W3035524453","https://openalex.org/W3035564946","https://openalex.org/W3047922786","https://openalex.org/W3096609285","https://openalex.org/W3174257385","https://openalex.org/W3176739692","https://openalex.org/W3178322352","https://openalex.org/W3205786327","https://openalex.org/W4214663214","https://openalex.org/W4304699887","https://openalex.org/W4312683960","https://openalex.org/W4313031313","https://openalex.org/W4319300501","https://openalex.org/W4321512633","https://openalex.org/W4366999574","https://openalex.org/W4383097607","https://openalex.org/W4386066385","https://openalex.org/W4386076309","https://openalex.org/W4386076365","https://openalex.org/W4386076400","https://openalex.org/W4389519116","https://openalex.org/W4390871800","https://openalex.org/W4390871901","https://openalex.org/W4390872381","https://openalex.org/W4390874160","https://openalex.org/W4394596424","https://openalex.org/W4402727916","https://openalex.org/W4402733575"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Traditional":[0],"dense":[1],"video":[2],"captioning":[3],"predominantly":[4],"focuses":[5],"on":[6,103,179,194],"edited":[7,29],"exocentric":[8],"footage.":[9,60],"These":[10],"videos":[11,34],"are":[12],"filmed":[13],"from":[14,51],"an":[15,52],"external":[16],"perspective":[17],"and":[18,55,107,133,158,189],"generally":[19],"feature":[20],"distinct":[21],"transitions":[22],"between":[23],"different":[24],"events,":[25],"as":[26,138,140],"exemplified":[27],"in":[28,75],"instructional":[30],"videos.":[31,95],"However,":[32],"such":[33],"do":[35],"not":[36],"genuinely":[37],"reflect":[38],"the":[39,49,135,142,168,180,199],"way":[40],"we":[41,47,65,148],"perceive":[42],"our":[43,173,202],"real":[44],"lives.":[45],"Instead,":[46],"observe":[48],"world":[50],"egocentric":[53,93],"viewpoint":[54],"witness":[56],"only":[57],"continuous":[58],"unedited":[59],"To":[61,112],"facilitate":[62],"further":[63],"research,":[64],"introduce":[66],"a":[67,82,88,153,159],"new":[68,191],"topic:":[69],"Egocentric":[70],"Vehicle":[71],"Dense":[72],"Video":[73],"Captioning,":[74],"classic":[76],"vehicle":[77,108,154],"driving":[78,94,131],"scenarios.":[79],"This":[80],"is":[81,117],"multi-modal,":[83],"multi-task":[84],"subject":[85],"endeavor":[86],"for":[87],"comprehensive":[89],"understanding":[90],"of":[91,98,184,201],"untrimmed,":[92],"It":[96],"consists":[97],"three":[99,124],"sub-tasks":[100],"that":[101],"concentrate":[102],"event":[104],"localization,":[105],"captioning,":[106],"state":[109],"estimation":[110],"separately.":[111],"accomplish":[113],"these":[114],"tasks,":[115],"it":[116],"necessary":[118],"to":[119],"deal":[120],"with":[121],"at":[122],"least":[123],"challenges:":[125],"extracting":[126],"ego-motion":[127,155],"relevant":[128],"information,":[129],"describing":[130],"behavior":[132],"analyzing":[134],"underlying":[136],"rationale,":[137],"well":[139],"resolving":[141],"boundary":[143],"ambiguity":[144],"problem.":[145],"In":[146],"response,":[147],"devise":[149],"corresponding":[150],"solutions,":[151],"including":[152],"learning":[156,163],"strategy":[157],"novel":[160],"adjacent":[161],"contrastive":[162],"strategy,":[164],"which":[165,185,197],"effectively":[166],"address":[167],"aforementioned":[169],"issues.":[170],"We":[171],"validate":[172],"method":[174],"by":[175],"conducting":[176],"extensive":[177],"experiments":[178],"BDD-X":[181],"dataset,":[182],"all":[183],"show":[186],"promising":[187],"results":[188],"achieve":[190],"state-of-the-art":[192],"performance":[193],"most":[195],"metrics,":[196],"proves":[198],"effect":[200],"approach.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}