{"id":"https://openalex.org/W4402557613","doi":"https://doi.org/10.1109/tcsvt.2024.3462433","title":"Surveillance Video-and-Language Understanding: From Small to Large Multimodal Models","display_name":"Surveillance Video-and-Language Understanding: From Small to Large Multimodal Models","publication_year":2024,"publication_date":"2024-09-17","ids":{"openalex":"https://openalex.org/W4402557613","doi":"https://doi.org/10.1109/tcsvt.2024.3462433"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3462433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3462433","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5042100540","display_name":"Tongtong Yuan","orcid":"https://orcid.org/0000-0002-8224-9891"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongtong Yuan","raw_affiliation_strings":["School of Computer, Beijing University of Technology (BJUT), Beijing, China","Beijing University of Technology (BJUT), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8224-9891","affiliations":[{"raw_affiliation_string":"School of Computer, Beijing University of Technology (BJUT), Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing University of Technology (BJUT), Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068284913","display_name":"Xuange Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuange Zhang","raw_affiliation_strings":["School of Computer, Beijing University of Technology (BJUT), Beijing, China","Beijing University of Technology (BJUT), Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-8562-6071","affiliations":[{"raw_affiliation_string":"School of Computer, Beijing University of Technology (BJUT), Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing University of Technology (BJUT), Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042428983","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-3482-6930"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["School of Computer, Beijing University of Technology (BJUT), Beijing, China","Beijing University of Technology (BJUT), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3482-6930","affiliations":[{"raw_affiliation_string":"School of Computer, Beijing University of Technology (BJUT), Beijing, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing University of Technology (BJUT), Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kun Liu","orcid":"https://orcid.org/0009-0004-8398-6369"},"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":"Kun Liu","raw_affiliation_strings":["JD.COM., Beijing, China","JD.COM, China"],"raw_orcid":"https://orcid.org/0009-0004-8398-6369","affiliations":[{"raw_affiliation_string":"JD.COM., Beijing, China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD.COM, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019598467","display_name":"Jian Gang Jin","orcid":"https://orcid.org/0000-0002-8507-1435"},"institutions":[{"id":"https://openalex.org/I4210130112","display_name":"China Academy of Information and Communications Technology","ror":"https://ror.org/038dte259","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210130112","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Jin","raw_affiliation_strings":["China Academy of Information and Communications Technology (CAICT), Beijing, China","CAICT, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Academy of Information and Communications Technology (CAICT), Beijing, China","institution_ids":["https://openalex.org/I4210130112"]},{"raw_affiliation_string":"CAICT, CN","institution_ids":["https://openalex.org/I4210130112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103231700","display_name":"Zhenzhen Jiao","orcid":"https://orcid.org/0009-0006-5940-6445"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhen Jiao","raw_affiliation_strings":["Beijing Teleinfo Technology Company., Ltd., Beijing, China","Beijing Teleinfo Technology Co., Ltd, CAICT, CN"],"raw_orcid":"https://orcid.org/0009-0006-5940-6445","affiliations":[{"raw_affiliation_string":"Beijing Teleinfo Technology Company., Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210155967"]},{"raw_affiliation_string":"Beijing Teleinfo Technology Co., Ltd, CAICT, CN","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.2163,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.98687715,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"35","issue":"1","first_page":"300","last_page":"314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.4659000039100647,"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"}},"topics":[{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.4659000039100647,"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"}},{"id":"https://openalex.org/T11121","display_name":"Public Relations and Crisis Communication","score":0.4228000044822693,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11982","display_name":"Rhetoric and Communication Studies","score":0.4198000133037567,"subfield":{"id":"https://openalex.org/subfields/1211","display_name":"Philosophy"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7468967437744141},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4589442312717438},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4293188452720642},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.35096561908721924},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3336418867111206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7468967437744141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4589442312717438},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4293188452720642},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.35096561908721924},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3336418867111206}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3462433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3462433","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5737841605","display_name":null,"funder_award_id":"62402023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7985209521","display_name":null,"funder_award_id":"62476181","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W1967456674","https://openalex.org/W1995820507","https://openalex.org/W2016053056","https://openalex.org/W2078238240","https://openalex.org/W2101105183","https://openalex.org/W2111078031","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2163612318","https://openalex.org/W2164261375","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2337252826","https://openalex.org/W2425121537","https://openalex.org/W2549139847","https://openalex.org/W2777342313","https://openalex.org/W2914306086","https://openalex.org/W2914868535","https://openalex.org/W2962681491","https://openalex.org/W2962799512","https://openalex.org/W2962990649","https://openalex.org/W2963017553","https://openalex.org/W2963795951","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2964232540","https://openalex.org/W2964350391","https://openalex.org/W2964532449","https://openalex.org/W2970898753","https://openalex.org/W2989322838","https://openalex.org/W2997429269","https://openalex.org/W3014565582","https://openalex.org/W3022778813","https://openalex.org/W3027013152","https://openalex.org/W3035339529","https://openalex.org/W3048306538","https://openalex.org/W3118451559","https://openalex.org/W3128401049","https://openalex.org/W3176425931","https://openalex.org/W3199096350","https://openalex.org/W3207454933","https://openalex.org/W3216765867","https://openalex.org/W3217340782","https://openalex.org/W4200629080","https://openalex.org/W4210446097","https://openalex.org/W4214663214","https://openalex.org/W4221049315","https://openalex.org/W4292092982","https://openalex.org/W4298364821","https://openalex.org/W4304197304","https://openalex.org/W4312560592","https://openalex.org/W4312683960","https://openalex.org/W4313123064","https://openalex.org/W4365509076","https://openalex.org/W4385801084","https://openalex.org/W4386071599","https://openalex.org/W4387245339","https://openalex.org/W4387757641","https://openalex.org/W4388901570","https://openalex.org/W4390871893","https://openalex.org/W4390874374","https://openalex.org/W4393154133","https://openalex.org/W4402704561","https://openalex.org/W4402727142","https://openalex.org/W6637373629","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6754337694","https://openalex.org/W6791353385","https://openalex.org/W6797716411","https://openalex.org/W6809510038","https://openalex.org/W6810334672","https://openalex.org/W6840384755","https://openalex.org/W6846989178","https://openalex.org/W6849177959","https://openalex.org/W6851334955","https://openalex.org/W6851432381","https://openalex.org/W6851950068","https://openalex.org/W6852776751","https://openalex.org/W6852952677","https://openalex.org/W6853515732","https://openalex.org/W6854585117"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"Surveillance":[0],"videos":[1,15,102],"play":[2],"a":[3,49],"crucial":[4],"role":[5],"in":[6,156],"public":[7,145],"security.":[8],"However,":[9],"current":[10],"tasks":[11,117,181],"related":[12],"to":[13,32,131,161,165,203],"surveillance":[14,58,65,73,127,151,157,205],"primarily":[16],"focus":[17],"on":[18,54,114,143,150],"classifying":[19,35],"and":[20,34,38,60,80,99,182,218,222],"localizing":[21],"anomalous":[22],"events.":[23],"Despite":[24],"achieving":[25],"notable":[26],"performance,":[27],"existing":[28,170],"methods":[29,176],"are":[30,103,224],"restricted":[31],"detecting":[33],"predefined":[36],"events":[37],"lack":[39],"satisfactory":[40],"semantic":[41],"understanding.":[42],"To":[43],"tackle":[44],"this":[45,119,200],"challenge,":[46],"we":[47,110,172,213],"introduce":[48],"novel":[50,175],"research":[51],"avenue":[52],"focused":[53],"Video-and-Language":[55],"Understanding":[56],"for":[57,126,177],"(VALU),":[59],"construct":[61],"the":[62,71,167,193,196,208],"first":[63],"multimodal":[64,116,178,184,201],"video":[66],"dataset.":[67,191],"We":[68],"manually":[69],"annotate":[70],"real-world":[72],"dataset":[74,202,221],"UCF-Crime":[75],"with":[76,92],"fine-grained":[77],"event":[78],"content":[79],"timing.":[81],"Our":[82,134],"newly":[83,120],"annotated":[84,101],"dataset,":[85,122],"UCA":[86],"(UCF-Crime":[87],"Annotation),":[88],"contains":[89],"23,542":[90],"sentences,":[91],"an":[93],"average":[94],"length":[95],"of":[96,169,198],"20":[97],"words,":[98],"its":[100],"as":[104,106],"long":[105],"110.7":[107],"hours.":[108],"Moreover,":[109],"evaluate":[111],"SOTA":[112],"models":[113,188],"five":[115],"using":[118,189],"created":[121],"establishing":[123],"new":[124,154],"baselines":[125],"VALU,":[128],"from":[129],"small":[130],"large":[132,185],"models.":[133],"experiments":[135,164,194],"reveal":[136],"that":[137],"mainstream":[138],"models,":[139,171],"which":[140],"perform":[141],"well":[142],"previously":[144],"datasets,":[146],"exhibit":[147],"poor":[148],"performance":[149,168],"video,":[152],"highlighting":[153],"challenges":[155],"VALU.":[158],"In":[159],"addition":[160],"conducting":[162],"baseline":[163],"compare":[166],"also":[173],"propose":[174],"anomaly":[179],"detection":[180],"finetune":[183],"language":[186],"model":[187],"our":[190],"All":[192],"highlight":[195],"necessity":[197],"constructing":[199],"advance":[204],"AI.":[206],"Upon":[207],"experimental":[209],"results":[210],"mentioned":[211],"above,":[212],"conduct":[214],"further":[215],"in-depth":[216],"analysis":[217],"discussion.":[219],"The":[220],"codes":[223],"provided":[225],"at":[226],"<uri":[227],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[228],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://xuange923.github.io/Surveillance-Video-Understanding</uri>.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":9}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}