{"id":"https://openalex.org/W2294085349","doi":"https://doi.org/10.1109/icip.2015.7351466","title":"Mine the fine: Fine-grained fragment discovery","display_name":"Mine the fine: Fine-grained fragment discovery","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2294085349","doi":"https://doi.org/10.1109/icip.2015.7351466","mag":"2294085349"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2015.7351466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2015.7351466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Image Processing (ICIP)","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/A5014632144","display_name":"M. Hadi Kiapour","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M. Hadi Kiapour","raw_affiliation_strings":["University of North Carolina at Chapel Hill Chapel Hill, NC, USA"],"affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073588989","display_name":"Di Wei","orcid":"https://orcid.org/0000-0003-2670-6362"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Di","raw_affiliation_strings":["eBay Research Labs, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"eBay Research Labs, San Jose, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082732430","display_name":"Vignesh Jagadeesh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vignesh Jagadeesh","raw_affiliation_strings":["eBay Research Labs, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"eBay Research Labs, San Jose, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018704921","display_name":"Robinson Piramuthu","orcid":"https://orcid.org/0000-0002-1767-8382"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robinson Piramuthu","raw_affiliation_strings":["eBay Research Labs, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"eBay Research Labs, San Jose, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014632144"],"corresponding_institution_ids":["https://openalex.org/I114027177"],"apc_list":null,"apc_paid":null,"fwci":0.1841,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61105156,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3555","last_page":"3559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9990000128746033,"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":0.9990000128746033,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9940000176429749,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9912999868392944,"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/discriminative-model","display_name":"Discriminative model","score":0.9445784687995911},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7973920106887817},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7560184001922607},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.7144505977630615},{"id":"https://openalex.org/keywords/fragment","display_name":"Fragment (logic)","score":0.7143451571464539},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6136420369148254},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6082068681716919},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5971364974975586},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5102527141571045},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3724987506866455},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1539376974105835},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07188424468040466}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9445784687995911},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7973920106887817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7560184001922607},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.7144505977630615},{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.7143451571464539},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6136420369148254},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6082068681716919},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5971364974975586},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5102527141571045},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3724987506866455},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1539376974105835},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07188424468040466},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip.2015.7351466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2015.7351466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.75,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W82130502","https://openalex.org/W1590510366","https://openalex.org/W1616462885","https://openalex.org/W1663973292","https://openalex.org/W1797268635","https://openalex.org/W1994213117","https://openalex.org/W1999478155","https://openalex.org/W2014102544","https://openalex.org/W2033832873","https://openalex.org/W2055132753","https://openalex.org/W2083367367","https://openalex.org/W2088049833","https://openalex.org/W2102605133","https://openalex.org/W2110765924","https://openalex.org/W2118585731","https://openalex.org/W2118696714","https://openalex.org/W2119525058","https://openalex.org/W2124351162","https://openalex.org/W2152411181","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2169501191","https://openalex.org/W2171322814","https://openalex.org/W4212863985","https://openalex.org/W4385490361","https://openalex.org/W6602324145","https://openalex.org/W6603374121","https://openalex.org/W6629510986","https://openalex.org/W6635258101","https://openalex.org/W6636475194","https://openalex.org/W6648943923","https://openalex.org/W6664362714","https://openalex.org/W6677656871","https://openalex.org/W6684191040","https://openalex.org/W6684876274"],"related_works":["https://openalex.org/W4300812085","https://openalex.org/W4237171675","https://openalex.org/W2949303564","https://openalex.org/W2776054962","https://openalex.org/W3036286480","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W4287728368","https://openalex.org/W3039174484"],"abstract_inverted_index":{"While":[0],"discriminative":[1,52,153],"visual":[2,53,99],"element":[3],"mining":[4],"has":[5],"been":[6],"introduced":[7],"before,":[8],"in":[9,20,80,161],"this":[10],"paper":[11],"we":[12],"present":[13],"an":[14],"approach":[15,37,95,110],"that":[16,67,92,116,126,146],"requires":[17],"minimal":[18,85],"annotation":[19],"both":[21],"training":[22],"and":[23,48,132],"test":[24],"time.":[25,142],"Given":[26],"only":[27],"a":[28,44,89,130],"bounding":[29],"box":[30],"localization":[31],"of":[32,113],"the":[33,40,50,136,140,147],"foreground":[34],"objects,":[35],"our":[36,94,109],"automatically":[38,148],"transforms":[39],"input":[41],"images":[42],"into":[43],"roughly-aligned":[45],"pose":[46,81],"space":[47],"discovers":[49],"most":[51],"fragments":[54,59],"for":[55],"each":[56],"category.":[57],"These":[58],"are":[60,117,127],"then":[61],"used":[62],"to":[63,96,129],"learn":[64],"robust":[65],"classifiers":[66],"discriminate":[68],"between":[69],"very":[70],"similar":[71],"categories":[72],"under":[73],"challenging":[74],"conditions":[75],"such":[76],"as":[77],"large":[78],"variations":[79],"or":[82],"habitats.":[83],"The":[84],"required":[86],"input,":[87],"is":[88,104],"critical":[90],"characteristic":[91],"enables":[93],"generalize":[97,133],"over":[98],"domains":[100],"where":[101],"expert":[102],"knowledge":[103],"not":[105],"readily":[106],"available.":[107],"Moreover,":[108],"takes":[111],"advantage":[112],"deep":[114,159],"networks":[115],"targeted":[118],"towards":[119],"fine-grained":[120],"classification.":[121],"It":[122],"learns":[123],"mid-level":[124],"representations":[125],"specific":[128],"category":[131,137],"well":[134],"across":[135],"instances":[138],"at":[139],"same":[141],"Our":[143],"evaluations":[144],"demonstrate":[145],"learned":[149],"representation":[150],"based":[151],"on":[152],"fragments,":[154],"significantly":[155],"outperforms":[156],"globally":[157],"extracted":[158],"features":[160],"classification":[162],"accuracy.":[163]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}