{"id":"https://openalex.org/W2345013272","doi":"https://doi.org/10.1109/vcip.2015.7457800","title":"Weighted transformable spatial pyramid and scalable query for object retrieval","display_name":"Weighted transformable spatial pyramid and scalable query for object retrieval","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2345013272","doi":"https://doi.org/10.1109/vcip.2015.7457800","mag":"2345013272"},"language":"en","primary_location":{"id":"doi:10.1109/vcip.2015.7457800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip.2015.7457800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Visual Communications and Image Processing (VCIP)","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/A5065863041","display_name":"Zi\u2019ou Zheng","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":"Zi'ou Zheng","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, 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":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050071143","display_name":"Ronggang Wang","orcid":"https://orcid.org/0000-0003-0873-0465"},"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":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":1.0,"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":1.0,"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":0.9983000159263611,"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":0.9972000122070312,"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/pyramid","display_name":"Pyramid (geometry)","score":0.7811521291732788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7758952975273132},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6319547891616821},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.605294942855835},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5505858659744263},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5249882936477661},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.508239209651947},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4898657500743866},{"id":"https://openalex.org/keywords/bag-of-words-model-in-computer-vision","display_name":"Bag-of-words model in computer vision","score":0.486680805683136},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4536643624305725},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.4512483477592468},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4409504532814026},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.43404918909072876},{"id":"https://openalex.org/keywords/scale-invariant-feature-transform","display_name":"Scale-invariant feature transform","score":0.42040693759918213},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38160771131515503},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.35470786690711975},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32979485392570496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1477569341659546},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1007695198059082}],"concepts":[{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.7811521291732788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7758952975273132},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6319547891616821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.605294942855835},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5505858659744263},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5249882936477661},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.508239209651947},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4898657500743866},{"id":"https://openalex.org/C167611913","wikidata":"https://www.wikidata.org/wiki/Q6884747","display_name":"Bag-of-words model in computer vision","level":5,"score":0.486680805683136},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4536643624305725},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4512483477592468},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4409504532814026},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.43404918909072876},{"id":"https://openalex.org/C61265191","wikidata":"https://www.wikidata.org/wiki/Q767770","display_name":"Scale-invariant feature transform","level":3,"score":0.42040693759918213},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38160771131515503},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35470786690711975},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32979485392570496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1477569341659546},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1007695198059082},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip.2015.7457800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip.2015.7457800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1979931042","https://openalex.org/W2036054070","https://openalex.org/W2064321430","https://openalex.org/W2065296697","https://openalex.org/W2081332440","https://openalex.org/W2089903940","https://openalex.org/W2097018403","https://openalex.org/W2099930951","https://openalex.org/W2104636679","https://openalex.org/W2122934855","https://openalex.org/W2141362318","https://openalex.org/W2147035467","https://openalex.org/W2148809531","https://openalex.org/W2154952031","https://openalex.org/W2162915993","https://openalex.org/W4247915583","https://openalex.org/W6659336525","https://openalex.org/W6666665630","https://openalex.org/W6674642818","https://openalex.org/W6682717316"],"related_works":["https://openalex.org/W2158102958","https://openalex.org/W1995462736","https://openalex.org/W2028757524","https://openalex.org/W2938717424","https://openalex.org/W2548286644","https://openalex.org/W2009049007","https://openalex.org/W2588241640","https://openalex.org/W2473933584","https://openalex.org/W2311865135","https://openalex.org/W2465112410"],"abstract_inverted_index":{"Object":[0],"retrieval":[1],"in":[2,63,67,101],"the":[3,52,68,102],"large-scale":[4],"image":[5,54,103],"corpus":[6],"is":[7,96,105],"an":[8,26],"appealing,":[9],"yet":[10],"challenging":[11],"task.":[12],"Most":[13],"of":[14,31,80,84,88],"existing":[15],"frameworks":[16],"are":[17,90],"based":[18],"on":[19],"bag-of-visual-words":[20],"(BoVW)":[21],"model.":[22],"However,":[23],"BoVW":[24,118],"has":[25,73],"obvious":[27],"drawback,":[28],"i.e.":[29],"lack":[30],"spatial":[32,41,78,121],"information.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"propose":[38],"weighted":[39],"transformable":[40],"pyramid":[42,122],"and":[43,57,119],"scalable":[44,108],"query":[45],"for":[46],"object":[47],"retrieval.":[48],"We":[49],"first":[50],"break":[51],"whole":[53],"into":[55],"sub-images":[56,61],"then":[58],"make":[59],"these":[60],"up":[62],"a":[64],"new":[65],"order":[66],"final":[69],"representation.":[70],"Our":[71],"method":[72],"two":[74],"contributions:":[75],"1)":[76],"relative":[77],"relationships":[79],"local":[81],"features":[82,89],"instead":[83],"absolute":[85],"geometric":[86],"layouts":[87],"encoded":[91],"so":[92],"that":[93,114],"translation":[94],"invariance":[95,100],"guaranteed,":[97],"2)":[98],"scaling":[99],"representation":[104],"ensured":[106],"by":[107],"query.":[109],"The":[110],"experimental":[111],"results":[112],"show":[113],"our":[115],"approach":[116],"outperforms":[117],"traditional":[120],"matching.":[123]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}