{"id":"https://openalex.org/W2963608398","doi":"https://doi.org/10.1109/icme.2017.8019372","title":"Improving object detection with region similarity learning","display_name":"Improving object detection with region similarity learning","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2963608398","doi":"https://doi.org/10.1109/icme.2017.8019372","mag":"2963608398"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2017.8019372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5043429007","display_name":"Feng Gag","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":true,"raw_author_name":"Feng Gag","raw_affiliation_strings":["Peking University, Beijing, Beijing, CN"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, CN","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063901345","display_name":"Yihang Lou","orcid":"https://orcid.org/0000-0002-8143-389X"},"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":"Yihang Lou","raw_affiliation_strings":["SECE of Shenzhen Graduate School, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"SECE of Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619463","display_name":"Yan Bai","orcid":"https://orcid.org/0000-0002-2152-9611"},"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":"Yan Bai","raw_affiliation_strings":["SECE of Shenzhen Graduate School, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"SECE of Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385178","display_name":"Shiqi Wang","orcid":"https://orcid.org/0000-0002-3583-959X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shiqi Wang","raw_affiliation_strings":["Rapid-Rich Object Search Laboratory, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Rapid-Rich Object Search Laboratory, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058066577","display_name":"Tiejun Huang","orcid":"https://orcid.org/0000-0002-4234-6099"},"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":"Tiejun Huang","raw_affiliation_strings":["National Engineering Lab for Video Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Lab for Video Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024879728","display_name":"Ling\u2010Yu Duan","orcid":"https://orcid.org/0000-0002-4491-2023"},"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":"Ling-Yu Duan","raw_affiliation_strings":["National Engineering Lab for Video Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Lab for Video Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5043429007"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.182,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60876212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"104","issue":null,"first_page":"1488","last_page":"1493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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/T10036","display_name":"Advanced Neural Network Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991000294685364,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9977999925613403,"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/pascal","display_name":"Pascal (unit)","score":0.7429453134536743},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7069775462150574},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.7015549540519714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.687609076499939},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6730271577835083},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6639247536659241},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6379029154777527},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6073575615882874},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5757925510406494},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5068991780281067},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5055131912231445},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47925853729248047},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4654572308063507},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41854792833328247},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3810886740684509},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14646294713020325}],"concepts":[{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.7429453134536743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7069775462150574},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7015549540519714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.687609076499939},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6730271577835083},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6639247536659241},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6379029154777527},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6073575615882874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5757925510406494},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5068991780281067},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5055131912231445},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47925853729248047},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4654572308063507},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41854792833328247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3810886740684509},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14646294713020325},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2017.8019372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1832500336","https://openalex.org/W1882819926","https://openalex.org/W1932624639","https://openalex.org/W1960182310","https://openalex.org/W2037511607","https://openalex.org/W2064675550","https://openalex.org/W2088049833","https://openalex.org/W2102605133","https://openalex.org/W2109255472","https://openalex.org/W2155893237","https://openalex.org/W2168356304","https://openalex.org/W2179352600","https://openalex.org/W2288122362","https://openalex.org/W2514274290","https://openalex.org/W2613718673","https://openalex.org/W2963093690","https://openalex.org/W2963315052","https://openalex.org/W2963516811","https://openalex.org/W3106250896","https://openalex.org/W6600313631","https://openalex.org/W6620707391","https://openalex.org/W6638601408","https://openalex.org/W6676338569","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W4376620596","https://openalex.org/W3177249605","https://openalex.org/W2534152068","https://openalex.org/W3138508047","https://openalex.org/W1972515067","https://openalex.org/W1689909837","https://openalex.org/W4293054914","https://openalex.org/W4298525700","https://openalex.org/W2953362004","https://openalex.org/W2549121492"],"abstract_inverted_index":{"Object":[0],"detection":[1],"aims":[2],"to":[3,24,71,110,127],"identify":[4],"instances":[5],"of":[6,9,19,28,46,68,76,80,96,104,154,162,182],"semantic":[7],"objects":[8],"a":[10,102,128,159,179],"certain":[11],"class":[12,131],"in":[13],"images":[14],"or":[15],"videos.":[16],"The":[17,52,117],"success":[18],"state-of-the-art":[20,167],"approaches":[21],"is":[22,54,61],"attributed":[23],"the":[25,59,74,94,141,146,152,166,173],"significant":[26],"progress":[27],"object":[29,88,99,130],"proposal":[30],"and":[31,49,132,176],"convolutional":[32],"neural":[33],"networks":[34],"(CNNs).":[35],"Most":[36],"promising":[37],"detectors":[38],"involve":[39],"multi-task":[40],"learning":[41,115],"with":[42,158],"an":[43],"optimization":[44],"objective":[45],"softmax":[47],"loss":[48],"regression":[50],"loss.":[51],"first":[53],"for":[55,62],"multi-class":[56],"categorization,":[57],"while":[58],"latter":[60],"improving":[63],"localization":[64],"accuracy.":[65],"However,":[66],"few":[67],"them":[69],"attempt":[70],"further":[72],"investigate":[73],"hardness":[75],"distinguishing":[77],"different":[78],"sorts":[79],"distracting":[81],"background":[82,106],"regions":[83,89,100],"(i.e.,":[84,90],"negatives)":[85],"from":[86,172],"true":[87],"positives).":[91],"To":[92],"improve":[93],"performance":[95,153],"classifying":[97],"positive":[98],"vs.":[101],"variety":[103],"negative":[105,125],"regions,":[107],"we":[108],"propose":[109],"incorporate":[111],"triplet":[112,118,148,174],"embedding":[113,149,175],"into":[114],"objective.":[116],"units":[119],"are":[120],"formed":[121],"by":[122,137],"assigning":[123],"each":[124],"region":[126],"meaningful":[129],"establishing":[133],"class-specific":[134],"negatives,":[135],"followed":[136],"triplets":[138],"construction.":[139],"Over":[140],"benchmark":[142],"PASCAL":[143],"VOC":[144],"2007,":[145],"proposed":[147],"has":[150,177],"improved":[151],"well-known":[155],"Fas-tRCNN":[156],"model":[157],"mAP":[160,180],"gain":[161],"2.1%.":[163],"In":[164],"particular,":[165],"approach":[168],"OHEM":[169],"can":[170],"benefit":[171],"achieved":[178],"improvement":[181],"1.2%.":[183]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}