{"id":"https://openalex.org/W2137454801","doi":"https://doi.org/10.1109/cvpr.2007.383034","title":"Compositional Boosting for Computing Hierarchical Image Structures","display_name":"Compositional Boosting for Computing Hierarchical Image Structures","publication_year":2007,"publication_date":"2007-06-01","ids":{"openalex":"https://openalex.org/W2137454801","doi":"https://doi.org/10.1109/cvpr.2007.383034","mag":"2137454801"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2007.383034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2007.383034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","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/A5091159460","display_name":"Tianfu Wu","orcid":"https://orcid.org/0000-0001-8911-5506"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tian-Fu Wu","raw_affiliation_strings":["Lotus Hill Institute of Computer Vision and Information Science, Ezhou, China","Lotus Hill Inst. for Comput. Vision & Inf. Sci., Ezhou"],"affiliations":[{"raw_affiliation_string":"Lotus Hill Institute of Computer Vision and Information Science, Ezhou, China","institution_ids":[]},{"raw_affiliation_string":"Lotus Hill Inst. for Comput. Vision & Inf. Sci., Ezhou","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073032922","display_name":"Gui-Song Xia","orcid":"https://orcid.org/0000-0001-7660-6090"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gui-Song Xia","raw_affiliation_strings":["Lotus Hill Institute of Computer Vision and Information Science, Ezhou, China","Lotus Hill Inst. for Comput. Vision & Inf. Sci., Ezhou"],"affiliations":[{"raw_affiliation_string":"Lotus Hill Institute of Computer Vision and Information Science, Ezhou, China","institution_ids":[]},{"raw_affiliation_string":"Lotus Hill Inst. for Comput. Vision & Inf. Sci., Ezhou","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034228010","display_name":"Song\u2010Chun Zhu","orcid":"https://orcid.org/0009-0008-0876-8117"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song-Chun Zhu","raw_affiliation_strings":["Statistics Department, University of California, Los Angeles, CA, USA","Lotus Hill Inst. for Comput. Vision & Inf. Sci., Ezhou"],"affiliations":[{"raw_affiliation_string":"Statistics Department, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Lotus Hill Inst. for Comput. Vision & Inf. Sci., Ezhou","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091159460"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.1763,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.97747095,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.9911999702453613,"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"}},"topics":[{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.9911999702453613,"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"}},{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.984499990940094,"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/boosting","display_name":"Boosting (machine learning)","score":0.7283697724342346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.685780942440033},{"id":"https://openalex.org/keywords/iterated-function","display_name":"Iterated function","score":0.575417697429657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4678901731967926},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45729151368141174},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.436631441116333},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3230605125427246},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1782240867614746}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7283697724342346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685780942440033},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.575417697429657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4678901731967926},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45729151368141174},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.436631441116333},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3230605125427246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1782240867614746},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr.2007.383034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2007.383034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.133.3698","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.133.3698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.stat.ucla.edu/~sczhu/papers/Conf_2007/graphlets_cvpr07.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.577.8114","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.577.8114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.imageparsing.com/frame/Graphlet_for_CVPR2007_Final.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W128019999","https://openalex.org/W1983546739","https://openalex.org/W1986206193","https://openalex.org/W2024046085","https://openalex.org/W2106110775","https://openalex.org/W2108890589","https://openalex.org/W2115031589","https://openalex.org/W2115135404","https://openalex.org/W2124401358","https://openalex.org/W2135273733","https://openalex.org/W2138342591","https://openalex.org/W2141974812","https://openalex.org/W2144197083","https://openalex.org/W2144967509","https://openalex.org/W2154781256","https://openalex.org/W2164598857","https://openalex.org/W2165657641","https://openalex.org/W2165914352","https://openalex.org/W2168020168","https://openalex.org/W2171028456","https://openalex.org/W2171188998","https://openalex.org/W6605172141","https://openalex.org/W6676020639","https://openalex.org/W6677296758","https://openalex.org/W6678939483","https://openalex.org/W6680988417","https://openalex.org/W6681241391","https://openalex.org/W6684140288","https://openalex.org/W6684338786"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4231274751","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W4239293476","https://openalex.org/W1566995892"],"abstract_inverted_index":{"In":[0,48],"this":[1,49,242],"paper,":[2],"we":[3,76],"present":[4,77],"a":[5,43,78,137,162,181,192,196,236,245],"compositional":[6,79,221],"boosting":[7,80,122],"algorithm":[8,81,94,228,243],"for":[9,82,97,185,215],"detecting":[10],"and":[11,33,39,67,71,105,112,177,209,219,231,250],"recognizing":[12],"17":[13,85],"common":[14],"image":[15,143],"structures":[16],"in":[17,36,42,61,89,101,130,151,195],"low-middle":[18],"level":[19],"vision":[20],"tasks.":[21],"These":[22],"structures,":[23],"called":[24],"\"graphlets\",":[25],"are":[26,40,54,69,189,212],"the":[27,84,90,102,207,220,224,227],"most":[28],"frequently":[29],"occurring":[30],"primitives,":[31],"junctions":[32,35],"composite":[34],"natural":[37],"images,":[38],"arranged":[41],"3-layer":[44],"And-Or":[45,103],"graph":[46,104],"representation.":[47],"hierarchic":[50],"model,":[51],"larger":[52],"graphlets":[53,60,86],"decomposed":[55],"(in":[56],"And-nodes)":[57],"into":[58],"smaller":[59],"multiple":[62],"alternative":[63],"ways":[64],"(at":[65],"Or-nodes),":[66],"parts":[68],"shared":[70],"re-used":[72],"between":[73,107],"graphlets.":[74],"Then":[75],"computing":[83],"categories":[87],"collectively":[88],"Bayesian":[91],"framework.":[92],"The":[93,115,175],"runs":[95],"recursively":[96],"each":[98,216],"node":[99,186],"A":[100,128,149,160,187],"iterates":[106],"two":[108,119],"steps":[109],"-bottom-up":[110],"proposal":[111],"top-down":[113,193],"validation.":[114],"bottom-up":[116],"step":[117],"includes":[118],"types":[120],"of":[121,127,139,148,159,164,183,223,248],"methods,":[123],"(i)":[124],"Detecting":[125],"instances":[126,147],"(often":[129,150],"low":[131],"resolutions)":[132],"using":[133],"Adaboosting":[134,176,208],"method":[135],"through":[136,161],"sequence":[138,163],"tests":[140,166],"(weak":[141],"classifiers)":[142],"feature,":[144],"(ii)":[145],"Proposing":[146],"high":[152],"resolution)":[153],"by":[154,191],"binding":[155,178,210],"existing":[156],"children":[157],"nodes":[158],"compatibility":[165],"on":[167],"their":[168],"attributes":[169],"(e.g":[170],"angles,":[171],"relative":[172],"size":[173],"etc).":[174],"methods":[179,211],"generate":[180],"number":[182],"candidates":[184],"which":[188],"verified":[190],"process":[194],"way":[197],"similar":[198],"to":[199,244],"Data-Driven":[200],"Markov":[201],"Chain":[202],"Monte":[203],"Carlo":[204],"[18].":[205],"Both":[206],"trained":[213],"off-line":[214],"graphlet":[217],"category,":[218],"nature":[222],"model":[225],"means":[226],"is":[229],"recursive":[230],"can":[232],"be":[233],"learned":[234],"from":[235],"small":[237],"training":[238],"set.":[239],"We":[240],"apply":[241],"wide":[246],"range":[247],"indoor":[249],"outdoor":[251],"images":[252],"with":[253],"satisfactory":[254],"results.":[255]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}