{"id":"https://openalex.org/W4393641546","doi":"https://doi.org/10.5281/zenodo.8188570","title":"VISIONE Feature Repository for VBS: Multi-Modal Features and Detected Objects from V3C1+V3C2 Dataset","display_name":"VISIONE Feature Repository for VBS: Multi-Modal Features and Detected Objects from V3C1+V3C2 Dataset","publication_year":2023,"publication_date":"2023-07-27","ids":{"openalex":"https://openalex.org/W4393641546","doi":"https://doi.org/10.5281/zenodo.8188570"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.8188570","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8188570","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.8188570","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072396889","display_name":"Giuseppe Amato","orcid":"https://orcid.org/0000-0003-0171-4315"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Amato","raw_affiliation_strings":["CNR-ISTI"],"raw_orcid":"https://orcid.org/0000-0003-0171-4315","affiliations":[{"raw_affiliation_string":"CNR-ISTI","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033711815","display_name":"Paolo Bolettieri","orcid":"https://orcid.org/0000-0002-5225-4278"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Bolettieri","raw_affiliation_strings":["CNR-ISTI"],"raw_orcid":"https://orcid.org/0000-0002-5225-4278","affiliations":[{"raw_affiliation_string":"CNR-ISTI","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059447545","display_name":"Fabio Carrara","orcid":"https://orcid.org/0000-0001-5014-5089"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Carrara","raw_affiliation_strings":["CNR-ISTI"],"raw_orcid":"https://orcid.org/0000-0001-5014-5089","affiliations":[{"raw_affiliation_string":"CNR-ISTI","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047189288","display_name":"Fabrizio Falchi","orcid":"https://orcid.org/0000-0001-6258-5313"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabrizio Falchi","raw_affiliation_strings":["CNR-ISTI"],"raw_orcid":"https://orcid.org/0000-0001-6258-5313","affiliations":[{"raw_affiliation_string":"CNR-ISTI","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072879702","display_name":"Claudio Gennaro","orcid":"https://orcid.org/0000-0002-3715-149X"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Claudio Gennaro","raw_affiliation_strings":["CNR-ISTI"],"raw_orcid":"https://orcid.org/0000-0002-3715-149X","affiliations":[{"raw_affiliation_string":"CNR-ISTI","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007125882","display_name":"Nicola Messina","orcid":"https://orcid.org/0000-0003-3011-2487"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Messina","raw_affiliation_strings":["CNR-ISTI"],"raw_orcid":"https://orcid.org/0000-0003-3011-2487","affiliations":[{"raw_affiliation_string":"CNR-ISTI","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072640757","display_name":"Lucia Vadicamo","orcid":"https://orcid.org/0000-0001-7182-7038"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lucia Vadicamo","raw_affiliation_strings":["CNR-ISTI"],"raw_orcid":"https://orcid.org/0000-0001-7182-7038","affiliations":[{"raw_affiliation_string":"CNR-ISTI","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045424388","display_name":"Claudio Vairo","orcid":"https://orcid.org/0000-0003-2740-4331"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Claudio Vairo","raw_affiliation_strings":["CNR-ISTI"],"raw_orcid":"https://orcid.org/0000-0003-2740-4331","affiliations":[{"raw_affiliation_string":"CNR-ISTI","institution_ids":["https://openalex.org/I122991210"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I122991210"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.6628999710083008,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.6628999710083008,"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/T10399","display_name":"Hydrocarbon exploration and reservoir analysis","score":0.650600016117096,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.5651999711990356,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/modal","display_name":"Modal","score":0.7013412714004517},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6919764280319214},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4191368520259857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32756558060646057},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2127273678779602},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.20305845141410828},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1208970844745636},{"id":"https://openalex.org/keywords/polymer-chemistry","display_name":"Polymer chemistry","score":0.11715936660766602}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7013412714004517},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6919764280319214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4191368520259857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32756558060646057},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2127273678779602},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.20305845141410828},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1208970844745636},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.11715936660766602}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.8188570","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8188570","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.8188570","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8188570","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1322071649","display_name":"A European Excellence Centre for Media, Society and Democracy","funder_award_id":"951911","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"This":[0,134,198],"repository":[1,135,199,648],"contains":[2,205,247,281,297,315,331,411,430,445,502],"a":[3,104,108,139,248,493,503,506],"diverse":[4],"set":[5],"of":[6,40,72,110,228,236,257,386,388,398,467,505,538,550,564,674,681,803,848,915,1003],"features":[7,21,288,306,322,583,642],"extracted":[8,117,238,289,307,323,338,581],"from":[9,14,261,940],"the":[10,15,25,37,41,59,83,121,156,201,220,226,229,234,237,242,254,262,267,275,292,310,326,341,364,373,376,384,389,393,403,412,421,431,446,464,484,513,517,526,529,533,547,565,569,577,591,595,603,614,621,627,636,655,666,669,672,675,679,683,699,804,916,1004],"V3C1+V3C2":[11,50,592],"dataset,":[12,51],"sourced":[13],"Vimeo":[16],"Creative":[17,140],"Commons":[18,141],"Collection.":[19],"These":[20],"were":[22],"utilized":[23],"in":[24,131,148,516,568,668,696,758,880,974],"VISIONE":[26,676,715,742],"system":[27],"[Amato":[28,706,733],"et":[29,33,285,303,319,335,426,438,452,707,734,739,750,767,772,786,814,854,893,898,927,932,954,959,982],"al.":[30,34,286,304,320,336,427,439,453,708,735,740,751,768,787,815,855,894,928,955,983],"2023,":[31,713],"Amato":[32],"2022]":[35,287,305,736,895,956],"during":[36],"latest":[38],"editions":[39],"Video":[42,162,717,744],"Browser":[43,163,718,745],"Showdown":[44,164,719,746],"(VBS)":[45],"competition":[46],"(https://www.videobrowsershowdown.org/).":[47],"The":[48,536,580,841],"original":[49,276,656],"provided":[52,61,645],"by":[53],"NIST,":[54],"can":[55,599],"be":[56,460,600,618,633,651],"downloaded":[57],"using":[58,415,434,449,594,654],"instructions":[60],"at":[62,161,356,716,743],"https://videobrowsershowdown.org/about-vbs/existing-data-and-tools/.":[63],"It":[64],"comprises":[65,200],"7,235":[66],"video":[67,73,79,85,218,230,259,342,507],"files,":[68],"amounting":[69],"for":[70,151,209,216,290,308,324,339,496,638,907,967],"2,300h":[71],"content":[74],"and":[75,124,168,171,174,177,180,183,186,222,241,532,649,698,795,837,871,911,991,1010],"encompassing":[76],"2,508,113":[77],"predefined":[78,84],"segments.":[80,112,343],"We":[81,661],"subdivided":[82],"segments":[86,351,355,366],"longer":[87,99],"than":[88,100,408],"10":[89],"seconds":[90,359],"into":[91,620,641,688],"multiple":[92],"segments,":[93],"with":[94,233,375,546,602],"each":[95,114,210,217,258,497,500,551,558],"segment":[96,260,404,508],"spanning":[97],"no":[98,406],"16":[101],"seconds.":[102],"As":[103],"result,":[105],"we":[106,116,347,362,371],"obtained":[107,365],"total":[109],"2,648,219":[111],"For":[113],"segment,":[115,219,231],"one":[118],"frame,":[119],"specifically":[120],"middle":[122,239,255,294,312,328],"one,":[123],"computed":[125],"several":[126],"features,":[127],"which":[128],"are":[129,522],"described":[130],"detail":[132],"below.":[133],"is":[136,383,405,492,541,643,694,701],"released":[137],"under":[138],"Attribution":[142],"license.":[143],"If":[144],"you":[145,273],"use":[146,463],"it":[147],"any":[149],"form":[150],"your":[152],"work,":[153],"please":[154,270],"cite":[155],"following":[157,202],"paper:":[158],"@inproceedings{amato2023visione,":[159],"title={VISIONE":[160],"2023},":[165],"author={Amato,":[166],"Giuseppe":[167],"Bolettieri,":[169],"Paolo":[170],"Carrara,":[172],"Fabio":[173],"Falchi,":[175],"Fabrizio":[176],"Gennaro,":[178],"Claudio":[179],"Messina,":[181],"Nicola":[182],"Vadicamo,":[184],"Lucia":[185],"Vairo,":[187],"Claudio},":[188],"booktitle={International":[189],"Conference":[190,723,919,1006],"on":[191,420,442,456,483,576,611,724,808,885,920,947,1007],"Multimedia":[192,725,922],"Modeling},":[193],"pages={615--621},":[194],"year={2023},":[195],"organization={Springer}":[196],"}":[197],"files:":[203],"msb.tar.gz":[204],"tab-separated":[206],"files":[207,473],"(.tsv)":[208],"video.":[211],"Each":[212],"tsv":[213],"file":[214,495],"reports,":[215],"timestamp":[221,235],"frame":[223,240,256],"number":[224,385],"marking":[225],"start/end":[227],"along":[232],"associated":[243],"identifier":[244],"(\"id_visione\").":[245],"extract-keyframes-from-msb.tar.gz":[246],"Python":[249],"script":[250,268],"designed":[251],"to":[252,353,367,462,512,557,607,617,626,664,685],"extract":[253],"MSB":[263],"files.":[264],"To":[265],"run":[266],"successfully,":[269],"ensure":[271],"that":[272,392,402,477,635],"have":[274,478,662],"V3C":[277],"videos":[278],"available.":[279,704],"features-aladin.tar.gz\u2020":[280],"ALADIN":[282],"[Messina":[283,892],"N.":[284,897],"all":[291,309,325,340,682],"segment's":[293,311,327],"frames.":[295,313,329],"features-clip-laion.tar.gz\u2020":[296],"CLIP":[298,316],"ViT-H/14":[299],"-":[300],"LAION-2B":[301],"[Schuhmann":[302,953],"features-clip-openai.tar.gz\u2020":[314],"ViT-L/14":[317],"[Radford":[318,926],"2021]":[321,337,454,769,929,984],"features-clip2video.tar.gz\u2020":[330],"CLIP2Video":[332],"[Fang":[333,765],"H.":[334,766,771],"In":[344,721,801,882,913,944,1001],"particular":[345],"1)":[346],"concatenate":[348],"consecutive":[349],"short":[350],"so":[352],"create":[354],"least":[357],"3":[358],"long;":[360],"2)":[361],"downsample":[363],"2.5":[368],"fps;":[369],"3)":[370],"feed":[372],"network":[374,629],"first":[377],"min(36,":[378],"n)":[379],"frames,":[380,400],"where":[381,499],"n":[382],"frames":[387],"segment.":[390],"Notice":[391],"minimum":[394],"processed":[395],"length":[396],"consists":[397],"7":[399],"given":[401],"shorter":[407],"3s.":[409],"objects-frcnn-oiv4.tar.gz*":[410],"objects":[413,432,447,527,567,879],"detected":[414,433,448,552,559,566],"Faster":[416],"R-CNN+Inception":[417],"ResNet":[418],"(trained":[419,441,455],"Open":[422],"Images":[423],"V4":[424],"[Kuznetsova":[425,813],"2020]).":[428],"objects-mrcnn-lvis.tar.gz*":[429],"Mask":[435,799],"R-CNN":[436],"[He":[437,785],"2017]":[440,788],"LVIS).":[443],"objects-vfnet64-coco.tar.gz*":[444],"VfNet":[450],"[Zhang":[451,981],"COCO":[457],"dataset).":[458],"*Please":[459],"sure":[461],"v2":[465],"version":[466],"this":[468,647,692],"repository,":[469],"since":[470],"v1":[471],"feature":[472,657],"may":[474],"contain":[475],"inconsistencies":[476],"now":[479],"been":[480],"corrected":[481],"*Note":[482],"object":[485,489,999],"annotations:":[486],"Within":[487],"an":[488],"archive,":[490],"there":[491,521],"jsonl":[494],"video,":[498],"row":[501],"record":[504],"(the":[509],"\"_id\"":[510],"corresponds":[511],"\"id_visione\"":[514],"used":[515],"msb.tar.gz)":[518],".":[519],"Additionally,":[520],"three":[523],"arrays":[524,540],"representing":[525],"detected,":[528],"corresponding":[530,556],"scores,":[531],"bounding":[534,562],"boxes.":[535],"format":[537,570],"these":[539],"as":[542],"follows:":[543],"\"object_class_names\":":[544],"vector":[545],"class":[548],"name":[549],"object.":[553,560],"\"object_scores\":":[554],"scores":[555,906],"\"object_boxes_yxyx\":":[561],"boxes":[563],"(ymin,":[571],"xmin,":[572],"ymax,":[573],"xmax).":[574],"\u2020Note":[575],"cross-modal":[578,689],"features:":[579],"multi-modal":[582],"(ALADIN,":[584],"CLIPs,":[585],"CLIP2Video)":[586],"enable":[587],"internal":[588],"searches":[589,609],"within":[590,646],"dataset":[593,844,966],"query-by-image":[596],"approach":[597],"(features":[598],"compared":[601],"dot":[604],"product).":[605],"However,":[606,691],"perform":[608],"based":[610],"free":[612],"text,":[613],"text":[615,640,687],"needs":[616],"transformed":[619],"joint":[622],"embedding":[623],"space":[624],"according":[625],"specific":[628],"being":[630],"used.":[631],"Please":[632],"aware":[634],"service":[637],"transforming":[639],"not":[644,702],"should":[650],"developed":[652],"independently":[653],"repositories":[658],"linked":[659],"above.":[660],"plans":[663],"release":[665],"code":[667,700],"future,":[670],"allowing":[671],"reproduction":[673],"system,":[677],"including":[678],"instantiation":[680],"services":[684],"transform":[686],"features.":[690],"work":[693],"still":[695],"progress,":[697],"currently":[703],"References:":[705],"2023]":[709],"Amato,":[710,737],"G.et":[711],"al.,":[712,773,899,933,960],"January.":[714],"2023.":[720],"International":[722,731,846,918,945],"Modeling":[726],"(pp.":[727,811,888,924,950,1013],"615-621).":[728],"Cham:":[729],"Springer":[730],"Publishing.":[732],"G.":[738],"(2022).":[741],"2022.":[747,755,961],"In:":[748],",":[749],"MultiMedia":[752],"Modeling.":[753],"MMM":[754],"Lecture":[756],"Notes":[757],"Computer":[759,849,1008],"Science,":[760],"vol":[761],"13142.":[762],"Springer,":[763,890],"Cham.":[764,891],"Fang":[770],"2021.":[774,994],"Clip2video:":[775],"Mastering":[776],"video-text":[777],"retrieval":[778],"via":[779],"image":[780],"clip.":[781],"arXiv":[782],"preprint":[783],"arXiv:2106.11097.":[784],"He,":[789],"K.,":[790],"Gkioxari,":[791],"G.,":[792],"Doll\u00e1r,":[793,869],"P.":[794,870],"Girshick,":[796],"R.,":[797],"2017.":[798],"r-cnn.":[800],"Proceedings":[802,914,1002],"IEEE":[805],"international":[806],"conference":[807,884,946],"computer":[809,886],"vision":[810,887],"2961-2969).":[812],"2020]":[816],"Kuznetsova,":[817],"A.,":[818],"Rom,":[819],"H.,":[820,986],"Alldrin,":[821],"N.,":[822,993],"Uijlings,":[823],"J.,":[824,828,864],"Krasin,":[825],"I.,":[826],"Pont-Tuset,":[827],"Kamali,":[829],"S.,":[830,832,862],"Popov,":[831],"Malloci,":[833],"M.,":[834,860],"Kolesnikov,":[835],"A.":[836,931],"Duerig,":[838],"T.,":[839],"2020.":[840],"open":[842,964],"images":[843],"v4.":[845],"Journal":[847],"Vision,":[850],"128(7),":[851],"pp.1956-1981.":[852],"[Lin":[853],"2014]":[856],"Lin,":[857],"T.Y.,":[858],"Maire,":[859],"Belongie,":[861],"Hays,":[863],"Perona,":[865],"P.,":[866],"Ramanan,":[867],"D.,":[868],"Zitnick,":[872],"C.L.,":[873],"2014,":[874],"September.":[875,901],"Microsoft":[876],"coco:":[877],"Common":[878],"context.":[881],"European":[883],"740-755).":[889],"Messina":[896],"2022,":[900],"Aladin:":[902],"distilling":[903],"fine-grained":[904],"alignment":[905],"efficient":[908],"image-text":[909,971],"matching":[910],"retrieval.":[912],"19th":[917],"Content-based":[921],"Indexing":[923],"64-70).":[925],"Radford":[930],"2021,":[934],"July.":[935],"Learning":[936],"transferable":[937],"visual":[938],"models":[939],"natural":[941],"language":[942],"supervision.":[943],"machine":[948],"learning":[949],"8748-8763).":[951],"PMLR.":[952],"Schuhmann":[957],"C.":[958],"Laion-5b:":[962],"An":[963,996],"large-scale":[965],"training":[968],"next":[969],"generation":[970],"models.":[972],"Advances":[973],"Neural":[975],"Information":[976],"Processing":[977],"Systems,":[978],"35,":[979],"pp.25278-25294.":[980],"Zhang,":[985],"Wang,":[987],"Y.,":[988],"Dayoub,":[989],"F.":[990],"Sunderhauf,":[992],"Varifocalnet:":[995],"iou-aware":[997],"dense":[998],"detector.":[1000],"IEEE/CVF":[1005],"Vision":[1009],"Pattern":[1011],"Recognition":[1012],"8514-8523).":[1014]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}