{"id":"https://openalex.org/W1494977063","doi":"https://doi.org/10.1109/cbmi.2015.7153609","title":"Web image size prediction for efficient focused image crawling","display_name":"Web image size prediction for efficient focused image crawling","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W1494977063","doi":"https://doi.org/10.1109/cbmi.2015.7153609","mag":"1494977063"},"language":"en","primary_location":{"id":"doi:10.1109/cbmi.2015.7153609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi.2015.7153609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 13th International Workshop on Content-Based Multimedia Indexing (CBMI)","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/A5019535517","display_name":"Katerina Andreadou","orcid":null},"institutions":[{"id":"https://openalex.org/I107613613","display_name":"Information Technology Institute","ror":"https://ror.org/04ynw2g14","country_code":"EG","type":"facility","lineage":["https://openalex.org/I107613613"]},{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["EG","GR"],"is_corresponding":false,"raw_author_name":"Katerina Andreadou","raw_affiliation_strings":["Information Technologies Institute (ITI), Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece","Information Technologies Institute (ITI) Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technologies Institute (ITI), Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]},{"raw_affiliation_string":"Information Technologies Institute (ITI) Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece","institution_ids":["https://openalex.org/I107613613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013616365","display_name":"Symeon Papadopoulos","orcid":"https://orcid.org/0000-0002-5441-7341"},"institutions":[{"id":"https://openalex.org/I107613613","display_name":"Information Technology Institute","ror":"https://ror.org/04ynw2g14","country_code":"EG","type":"facility","lineage":["https://openalex.org/I107613613"]},{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["EG","GR"],"is_corresponding":false,"raw_author_name":"Symeon Papadopoulos","raw_affiliation_strings":["Information Technologies Institute (ITI), Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece","Information Technologies Institute (ITI) Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technologies Institute (ITI), Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]},{"raw_affiliation_string":"Information Technologies Institute (ITI) Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece","institution_ids":["https://openalex.org/I107613613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084122016","display_name":"Ioannis Kompatsiaris","orcid":"https://orcid.org/0000-0001-6447-9020"},"institutions":[{"id":"https://openalex.org/I107613613","display_name":"Information Technology Institute","ror":"https://ror.org/04ynw2g14","country_code":"EG","type":"facility","lineage":["https://openalex.org/I107613613"]},{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["EG","GR"],"is_corresponding":false,"raw_author_name":"Yiannis Kompatsiaris","raw_affiliation_strings":["Information Technologies Institute (ITI), Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece","Information Technologies Institute (ITI) Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technologies Institute (ITI), Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]},{"raw_affiliation_string":"Information Technologies Institute (ITI) Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece","institution_ids":["https://openalex.org/I107613613"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.02961709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"47","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9850000143051147,"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/T11393","display_name":"Biosensors and Analytical Detection","score":0.9537000060081482,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8155778646469116},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7379434704780579},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6522154211997986},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6211345195770264},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5374847650527954},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5189580321311951},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5017356872558594},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4937642514705658},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.471798837184906},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46174079179763794},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.43293696641921997},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4279683828353882},{"id":"https://openalex.org/keywords/download","display_name":"Download","score":0.41373923420906067},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34092605113983154},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3173576891422272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31056106090545654},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2664601802825928}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8155778646469116},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7379434704780579},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6522154211997986},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6211345195770264},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5374847650527954},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5189580321311951},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5017356872558594},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4937642514705658},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.471798837184906},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46174079179763794},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.43293696641921997},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4279683828353882},{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.41373923420906067},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34092605113983154},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3173576891422272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31056106090545654},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2664601802825928},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi.2015.7153609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi.2015.7153609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 13th International Workshop on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W154538122","https://openalex.org/W1489992655","https://openalex.org/W1527252300","https://openalex.org/W2001832505","https://openalex.org/W2003471189","https://openalex.org/W2125681211","https://openalex.org/W2139138720","https://openalex.org/W2147682847","https://openalex.org/W2256124641","https://openalex.org/W2270949707","https://openalex.org/W2295639288","https://openalex.org/W2295785353","https://openalex.org/W2544700275","https://openalex.org/W6606264704","https://openalex.org/W6697165015","https://openalex.org/W6697190591","https://openalex.org/W6729100142"],"related_works":["https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W2137810919","https://openalex.org/W2089702591","https://openalex.org/W4385695127"],"abstract_inverted_index":{"In":[0,55],"the":[1,29,59,79,85,105,129,147,151,156,167,188,193,197,202,206,233,238],"context":[2],"of":[3,31,42,74,78,109,149,153,192,220,237],"using":[4,187],"Web":[5,157],"image":[6,19,32,53,117,194,239],"content":[7],"for":[8,35],"analysis":[9],"and":[10,70,127,163,196,214,235],"retrieval,":[11],"it":[12],"is":[13,99,179],"typically":[14],"necessary":[15],"to":[16,28,46,49,84,90,111,122,135,223],"perform":[17],"large-scale":[18],"crawling.":[20],"A":[21],"serious":[22],"bottleneck":[23],"in":[24,68,104,142,218],"such":[25],"set-ups":[26],"pertains":[27],"fetching":[30],"content,":[33],"since":[34,76],"each":[36],"web":[37],"page":[38],"a":[39,124,182,224],"large":[40],"number":[41],"HTTP":[43],"requests":[44],"need":[45,121],"be":[47],"issued":[48],"download":[50,128],"all":[51],"included":[52],"elements.":[54],"practice,":[56],"however,":[57],"only":[58,159],"relatively":[60],"big":[61],"images":[62,154],"(e.g.,":[63,93],"larger":[64],"than":[65],"400":[66],"pixels":[67],"width":[69],"height)":[71],"are":[72,82],"potentially":[73],"interest,":[75],"most":[77],"smaller":[80],"ones":[81],"irrelevant":[83],"main":[86],"subject":[87],"or":[88,190],"correspond":[89],"decorative":[91],"elements":[92,204],"icons,":[94],"buttons).":[95],"Given":[96],"that":[97,229],"there":[98],"often":[100],"no":[101],"dimension":[102],"information":[103,164],"HTML":[106,169,203],"img":[107],"tag":[108],"images,":[110,115],"filter":[112],"out":[113],"small":[114],"an":[116],"crawler":[118],"would":[119],"still":[120],"issue":[123],"GET":[125],"request":[126],"respective":[130],"files":[131],"before":[132],"deciding":[133],"whether":[134],"index":[136],"them.":[137],"To":[138],"address":[139],"this":[140,143],"limitation,":[141],"paper,":[144],"we":[145,209],"explore":[146],"challenge":[148],"predicting":[150],"size":[152],"on":[155,160,181,201],"based":[158,180],"their":[161],"URL":[162],"extracted":[165],"from":[166],"surrounding":[168,205],"code.":[170],"We":[171],"present":[172],"two":[173,212],"different":[174],"methodologies:":[175],"The":[176],"first":[177],"one":[178,199],"common":[183],"text":[184],"classification":[185],"approach":[186],"n-grams":[189],"tokens":[191],"URLs":[195],"second":[198],"relies":[200],"image.":[207],"Eventually,":[208],"combine":[210],"these":[211],"techniques,":[213],"achieve":[215],"considerable":[216],"improvement":[217],"terms":[219],"accuracy,":[221],"leading":[222],"highly":[225],"effective":[226],"filtering":[227],"component":[228],"can":[230],"significantly":[231],"improve":[232],"speed":[234],"efficiency":[236],"crawler.":[240]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}