{"id":"https://openalex.org/W2981398794","doi":"https://doi.org/10.1145/3343031.3351005","title":"Learning Local Similarity with Spatial Relations for Object Retrieval","display_name":"Learning Local Similarity with Spatial Relations for Object Retrieval","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981398794","doi":"https://doi.org/10.1145/3343031.3351005","mag":"2981398794"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3351005","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","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/A5064272059","display_name":"Zhenfang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhenfang Chen","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054299179","display_name":"Zhanghui Kuang","orcid":"https://orcid.org/0000-0002-9102-5152"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanghui Kuang","raw_affiliation_strings":["SenseTime Research, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057842914","display_name":"Wayne Zhang","orcid":"https://orcid.org/0000-0002-8415-1062"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wayne Zhang","raw_affiliation_strings":["SenseTime Research, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kwan-Yee K. Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kwan-Yee K. Wong","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1703","last_page":"1711"},"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":0.9973000288009644,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7205495834350586},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6771792769432068},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.5564708709716797},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5551027059555054},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5248767733573914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46409764885902405},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.05729800462722778}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7205495834350586},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6771792769432068},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.5564708709716797},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5551027059555054},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5248767733573914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46409764885902405},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.05729800462722778}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3351005","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","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":48,"referenced_works":["https://openalex.org/W54214434","https://openalex.org/W204268067","https://openalex.org/W639708223","https://openalex.org/W764651262","https://openalex.org/W1861492603","https://openalex.org/W1929856797","https://openalex.org/W1945298332","https://openalex.org/W1955055330","https://openalex.org/W1972378554","https://openalex.org/W2012592962","https://openalex.org/W2023991840","https://openalex.org/W2040002737","https://openalex.org/W2062118960","https://openalex.org/W2071027807","https://openalex.org/W2100398441","https://openalex.org/W2103924867","https://openalex.org/W2104657103","https://openalex.org/W2117539524","https://openalex.org/W2124509324","https://openalex.org/W2128017662","https://openalex.org/W2131846894","https://openalex.org/W2141362318","https://openalex.org/W2147238549","https://openalex.org/W2148809531","https://openalex.org/W2151103935","https://openalex.org/W2164022341","https://openalex.org/W2174726731","https://openalex.org/W2194775991","https://openalex.org/W2204975001","https://openalex.org/W2295537791","https://openalex.org/W2320444803","https://openalex.org/W2340690086","https://openalex.org/W2499468060","https://openalex.org/W2544587078","https://openalex.org/W2559091987","https://openalex.org/W2604233003","https://openalex.org/W2620629206","https://openalex.org/W2765707474","https://openalex.org/W2951019013","https://openalex.org/W2962835968","https://openalex.org/W2963125676","https://openalex.org/W2963154697","https://openalex.org/W2963271314","https://openalex.org/W2963740830","https://openalex.org/W2964157791","https://openalex.org/W3141605214","https://openalex.org/W6679055200","https://openalex.org/W7053304325"],"related_works":["https://openalex.org/W2384888906","https://openalex.org/W2144190808","https://openalex.org/W2376314740","https://openalex.org/W2366644548","https://openalex.org/W2357241418","https://openalex.org/W2119214692","https://openalex.org/W2349125667","https://openalex.org/W4200607807","https://openalex.org/W2144071134","https://openalex.org/W2121899072"],"abstract_inverted_index":{"Many":[0],"state-of-the-art":[1],"object":[2],"retrieval":[3],"algorithms":[4],"aggregate":[5],"activations":[6],"of":[7,36,46,109],"convolutional":[8],"neural":[9],"networks":[10],"into":[11],"a":[12,70,80],"holistic":[13,27],"compact":[14],"feature,":[15],"and":[16,41,98,106,125],"utilize":[17],"global":[18,42,143],"similarity":[19,43,61,82,138,144],"for":[20,32],"an":[21,58],"efficient":[22],"nearest":[23],"neighbor":[24],"search.":[25],"However,":[26],"features":[28],"are":[29],"often":[30],"insufficient":[31],"representing":[33],"small":[34,88],"objects":[35],"interest":[37],"in":[38,50],"gallery":[39,99],"images,":[40],"drops":[44],"most":[45],"the":[47,51,74,96,104],"spatial":[48,93],"relations":[49,94],"images.":[52,100],"In":[53],"this":[54],"paper,":[55],"we":[56,78],"propose":[57],"end-to-end":[59],"local":[60,81,114,137],"learning":[62,139],"framework":[63,111,140],"to":[64,73],"tackle":[65],"these":[66],"problems.":[67],"By":[68],"applying":[69],"correlation":[71],"layer":[72],"locally":[75],"aggregated":[76],"features,":[77],"compute":[79],"that":[83,135],"can":[84,118],"not":[85],"only":[86,122],"handle":[87],"objects,":[89],"but":[90],"also":[91],"capture":[92],"between":[95],"query":[97],"We":[101],"further":[102],"reduce":[103],"memory":[105],"storage":[107],"footprints":[108],"our":[110,136],"by":[112],"quantizing":[113],"features.":[115],"Our":[116],"model":[117],"be":[119],"trained":[120],"using":[121],"synthetic":[123],"data,":[124],"achieve":[126],"competitive":[127],"performance.":[128],"Extensive":[129],"experiments":[130],"on":[131],"challenging":[132],"benchmarks":[133],"demonstrate":[134],"outperforms":[141],"previous":[142],"based":[145],"methods.":[146]},"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":5},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}