{"id":"https://openalex.org/W1560523163","doi":"https://doi.org/10.1109/icme.2015.7177433","title":"Learning class-specific pooling shapes for image classification","display_name":"Learning class-specific pooling shapes for image classification","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W1560523163","doi":"https://doi.org/10.1109/icme.2015.7177433","mag":"1560523163"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2015.7177433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2015.7177433","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 Multimedia and Expo (ICME)","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/A5084797829","display_name":"Jinzhuo Wang","orcid":"https://orcid.org/0000-0002-9464-4426"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinzhuo Wang","raw_affiliation_strings":["Digital Media R&D Center, Peking University Shenzhen Graduate School","Digital Media R & D Center, Peking University Shenzhen Graduate School, China"],"affiliations":[{"raw_affiliation_string":"Digital Media R&D Center, Peking University Shenzhen Graduate School","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Digital Media R & D Center, Peking University Shenzhen Graduate School, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017052768","display_name":"Wenmin Wang","orcid":"https://orcid.org/0000-0003-2664-4413"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenmin Wang","raw_affiliation_strings":["Digital Media R&D Center, Peking University Shenzhen Graduate School","Digital Media R & D Center, Peking University Shenzhen Graduate School, China"],"affiliations":[{"raw_affiliation_string":"Digital Media R&D Center, Peking University Shenzhen Graduate School","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Digital Media R & D Center, Peking University Shenzhen Graduate School, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082265046","display_name":"Ronggang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronggang Wang","raw_affiliation_strings":["Digital Media R&D Center, Peking University Shenzhen Graduate School","Digital Media R & D Center, Peking University Shenzhen Graduate School, China"],"affiliations":[{"raw_affiliation_string":"Digital Media R&D Center, Peking University Shenzhen Graduate School","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Digital Media R & D Center, Peking University Shenzhen Graduate School, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018478553","display_name":"Wen Gao","orcid":"https://orcid.org/0000-0002-8070-802X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Gao","raw_affiliation_strings":["National Engineering Laboratory for Video Technology, Peking University","[National Engineering Laboratory for Video Technology, Peking University, China]"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Video Technology, Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"[National Engineering Laboratory for Video Technology, Peking University, China]","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084797829"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.3682,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66237312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"6"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9965000152587891,"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":0.9954000115394592,"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/pooling","display_name":"Pooling","score":0.8368040919303894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7079219818115234},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6849384307861328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6665268540382385},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.5458517670631409},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.49751976132392883},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.456163227558136},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.44497573375701904},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4385174810886383},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.41171038150787354},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34235745668411255},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3042982220649719},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28383392095565796}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8368040919303894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7079219818115234},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6849384307861328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6665268540382385},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5458517670631409},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.49751976132392883},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.456163227558136},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.44497573375701904},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4385174810886383},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.41171038150787354},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34235745668411255},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3042982220649719},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28383392095565796},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2015.7177433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2015.7177433","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W33214042","https://openalex.org/W255846030","https://openalex.org/W1551774182","https://openalex.org/W1576445103","https://openalex.org/W1590510366","https://openalex.org/W1606858007","https://openalex.org/W1625255723","https://openalex.org/W2026188082","https://openalex.org/W2027922120","https://openalex.org/W2032982774","https://openalex.org/W2036054070","https://openalex.org/W2097018403","https://openalex.org/W2099528205","https://openalex.org/W2099930951","https://openalex.org/W2104371740","https://openalex.org/W2113855951","https://openalex.org/W2147035467","https://openalex.org/W2151103935","https://openalex.org/W2151800797","https://openalex.org/W2152161678","https://openalex.org/W2157639439","https://openalex.org/W2162248889","https://openalex.org/W2162915993","https://openalex.org/W2168133252","https://openalex.org/W2169177311","https://openalex.org/W6634343353","https://openalex.org/W6636494156","https://openalex.org/W6659336525","https://openalex.org/W6682139812","https://openalex.org/W6683265229","https://openalex.org/W6684872329"],"related_works":["https://openalex.org/W2022849497","https://openalex.org/W3081299480","https://openalex.org/W2407190427","https://openalex.org/W2907584218","https://openalex.org/W2919210741","https://openalex.org/W3002446410","https://openalex.org/W4390224712","https://openalex.org/W4322096758","https://openalex.org/W2748667022","https://openalex.org/W3211770882"],"abstract_inverted_index":{"Spatial":[0],"pyramid":[1],"(SP)":[2],"representation":[3],"is":[4,38,100],"an":[5,39,80],"extension":[6],"of":[7,15,30,55,83,120,160],"bag-of-feature":[8],"model":[9],"which":[10],"embeds":[11],"spatial":[12,24,31,84],"layout":[13],"information":[14],"local":[16],"features":[17],"by":[18,102],"pooling":[19,32,73],"feature":[20],"codes":[21],"over":[22,125],"pre-defined":[23],"shapes.":[25],"However,":[26],"the":[27,47,94,118,123,131,158,161],"uniform":[28],"style":[29],"shapes":[33,74,85],"used":[34],"in":[35],"standard":[36],"SP":[37],"ad-hoc":[40],"manner":[41],"without":[42],"theoretical":[43],"motivation,":[44],"thus":[45],"lacking":[46],"generalization":[48],"power":[49],"to":[50,52,69,130,137],"adapt":[51],"different":[53],"distribution":[54,113],"geometric":[56,91],"properties":[57],"across":[58],"image":[59],"classes.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64,77],"propose":[65],"a":[66,104,140],"data-driven":[67],"approach":[68],"adaptively":[70],"learn":[71],"class-specific":[72],"(CSPS).":[75],"Specifically,":[76],"first":[78],"establish":[79],"over-complete":[81],"set":[82],"providing":[86],"candidates":[87],"with":[88,107,139],"more":[89],"flexible":[90],"patterns.":[92],"Then":[93],"optimal":[95],"subset":[96],"for":[97,144],"each":[98],"class":[99],"selected":[101],"training":[103],"linear":[105],"classifier":[106],"structured":[108],"sparsity":[109],"constraint":[110],"and":[111,134,155,167],"color":[112],"cues.":[114],"To":[115],"further":[116],"enhance":[117],"robust":[119],"our":[121],"model,":[122],"representations":[124],"CSPS":[126],"are":[127],"compressed":[128],"according":[129],"shape":[132],"importance":[133],"finally":[135],"fed":[136],"SVM":[138],"multi-shape":[141],"matching":[142],"kernel":[143],"classification":[145],"task.":[146],"Experimental":[147],"results":[148],"on":[149,164],"three":[150],"challenging":[151],"datasets":[152],"(Caltech-256,":[153],"Scene-15":[154],"Indoor-67)":[156],"demonstrate":[157],"effectiveness":[159],"proposed":[162],"method":[163],"both":[165],"object":[166],"scene":[168],"images.":[169]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}