{"id":"https://openalex.org/W2154158499","doi":"https://doi.org/10.1145/2623330.2623346","title":"Mining text snippets for images on the web","display_name":"Mining text snippets for images on the web","publication_year":2014,"publication_date":"2014-08-22","ids":{"openalex":"https://openalex.org/W2154158499","doi":"https://doi.org/10.1145/2623330.2623346","mag":"2154158499"},"language":"en","primary_location":{"id":"doi:10.1145/2623330.2623346","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5103559059","display_name":"Anitha Kannan","orcid":"https://orcid.org/0000-0003-3028-4959"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anitha Kannan","raw_affiliation_strings":["Microsoft, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061943510","display_name":"Simon Baker","orcid":"https://orcid.org/0000-0002-0716-6236"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simon Baker","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001302770","display_name":"Krishnan Ramnath","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishnan Ramnath","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002787569","display_name":"Juliet Fiss","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juliet Fiss","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010087030","display_name":"Dahua Lin","orcid":"https://orcid.org/0000-0002-8865-7896"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dahua Lin","raw_affiliation_strings":["TTI Chicago, Chicago, IA, USA"],"affiliations":[{"raw_affiliation_string":"TTI Chicago, Chicago, IA, USA","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038603050","display_name":"Lucy Vanderwende","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lucy Vanderwende","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048107707","display_name":"Rizwan Ansary","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rizwan Ansary","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046810768","display_name":"Ashish Kapoor","orcid":"https://orcid.org/0000-0002-4686-394X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashish Kapoor","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111827722","display_name":"Qifa Ke","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qifa Ke","raw_affiliation_strings":["Microsoft, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010182611","display_name":"Matt Uyttendaele","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matt Uyttendaele","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101839607","display_name":"Xinjing Wang","orcid":"https://orcid.org/0000-0002-4110-7811"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin-Jing Wang","raw_affiliation_strings":["Microsoft, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433824","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0001-6926-0538"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5103559059"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.9885,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81560843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1534","last_page":"1543"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9993000030517578,"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/snippet","display_name":"Snippet","score":0.8687608242034912},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.819011926651001},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7478703260421753},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6785324811935425},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6375318765640259},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5926995277404785},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5085405111312866},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.441540390253067},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.41853398084640503},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37376803159713745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3305286169052124},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3257976174354553}],"concepts":[{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.8687608242034912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819011926651001},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7478703260421753},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6785324811935425},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6375318765640259},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5926995277404785},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5085405111312866},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.441540390253067},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.41853398084640503},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37376803159713745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3305286169052124},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3257976174354553},{"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/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":2,"locations":[{"id":"doi:10.1145/2623330.2623346","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.648.1373","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.648.1373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/217931/textpopups_KDD2014.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W105299784","https://openalex.org/W158057341","https://openalex.org/W1564080049","https://openalex.org/W1577877742","https://openalex.org/W1680189815","https://openalex.org/W1897761818","https://openalex.org/W1978255832","https://openalex.org/W1980813323","https://openalex.org/W1987835821","https://openalex.org/W2026642282","https://openalex.org/W2032475142","https://openalex.org/W2051434435","https://openalex.org/W2066134726","https://openalex.org/W2067879405","https://openalex.org/W2085625396","https://openalex.org/W2086632330","https://openalex.org/W2098642746","https://openalex.org/W2109586012","https://openalex.org/W2120779048","https://openalex.org/W2144169111","https://openalex.org/W2149172860","https://openalex.org/W2156854610","https://openalex.org/W2165979968","https://openalex.org/W2173213060","https://openalex.org/W2181911139","https://openalex.org/W2251620981","https://openalex.org/W2593713917","https://openalex.org/W2604272474","https://openalex.org/W3118655244","https://openalex.org/W4240924539"],"related_works":["https://openalex.org/W1607713096","https://openalex.org/W3036724449","https://openalex.org/W2798329462","https://openalex.org/W2389761961","https://openalex.org/W2963706618","https://openalex.org/W2113184419","https://openalex.org/W1999548128","https://openalex.org/W4254300012","https://openalex.org/W2102475112","https://openalex.org/W2187540250"],"abstract_inverted_index":{"Images":[0],"are":[1,49,86,154],"often":[2],"used":[3],"to":[4,18,35,164],"convey":[5],"many":[6,11],"different":[7,12],"concepts":[8,183],"or":[9],"illustrate":[10],"stories.":[13],"We":[14,122,134],"propose":[15],"an":[16,68],"algorithm":[17,33,93],"mine":[19],"multiple":[20],"diverse,":[21],"relevant,":[22],"and":[23,80,84,156],"interesting":[24],"text":[25,53,120,187],"snippets":[26,72],"for":[27],"images":[28,37,116,148,174],"on":[29,38,98,149],"the":[30,39,64,99,110,124,127,136,139,150],"web.":[31,40],"Our":[32,92],"scales":[34],"all":[36,44],"For":[41],"each":[42],"image,":[43],"webpages":[45,153],"that":[46,73,167],"contain":[47],"it":[48],"considered.":[50],"The":[51,82],"top-K":[52],"snippet":[54],"selection":[55,62],"problem":[56],"is":[57,94,168],"posed":[58],"as":[59,152],"combinatorial":[60],"subset":[61],"with":[63,117],"goal":[65],"of":[66,71,77,103,112,115,126,138,147],"choosing":[67],"optimal":[69],"set":[70],"maximizes":[74],"a":[75,104,113,130],"combination":[76],"relevancy,":[78],"interestingness,":[79],"diversity.":[81],"relevancy":[83],"interestingness":[85],"scored":[87],"by":[88,170],"machine":[89],"learned":[90],"models.":[91],"run":[95],"at":[96],"scale":[97],"entire":[100],"image":[101,158],"index":[102],"major":[105],"search":[106],"engine":[107],"resulting":[108],"in":[109,162,184],"construction":[111],"database":[114,128,140],"their":[118,185],"corresponding":[119,186],"snippets.":[121,188],"validate":[123],"quality":[125],"through":[129,141,181],"large-scale":[131],"comparative":[132],"study.":[133],"showcase":[135],"utility":[137],"two":[142],"web-scale":[143],"applications:":[144],"(a)":[145],"augmentation":[146],"web":[151,165],"browsed":[155],"(b)~an":[157],"browsing":[159],"experience":[160],"(similar":[161],"spirit":[163],"browsing)":[166],"enabled":[169],"interconnecting":[171],"semantically":[172],"related":[173],"(which":[175],"may":[176],"not":[177],"be":[178],"visually":[179],"related)":[180],"shared":[182]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}