{"id":"https://openalex.org/W3033022975","doi":"https://doi.org/10.1145/3372278.3390714","title":"Optimizing Queries over Video via Lightweight Keypoint-based Object Detection","display_name":"Optimizing Queries over Video via Lightweight Keypoint-based Object Detection","publication_year":2020,"publication_date":"2020-06-02","ids":{"openalex":"https://openalex.org/W3033022975","doi":"https://doi.org/10.1145/3372278.3390714","mag":"3033022975"},"language":"en","primary_location":{"id":"doi:10.1145/3372278.3390714","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research-information.bris.ac.uk/en/publications/fabce957-3915-41ae-b997-f7b16e6a427b","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076414931","display_name":"Jiansheng Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiansheng Dong","raw_affiliation_strings":["Wuhan University of Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062853168","display_name":"Jingling Yuan","orcid":"https://orcid.org/0000-0001-7924-8620"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingling Yuan","raw_affiliation_strings":["Wuhan University of Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412815","display_name":"Lin Li","orcid":"https://orcid.org/0000-0001-7553-6916"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Wuhan University of Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064738683","display_name":"Xian Zhong","orcid":"https://orcid.org/0000-0002-5242-0467"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Zhong","raw_affiliation_strings":["Wuhan University of Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002349071","display_name":"Weiru Liu","orcid":"https://orcid.org/0000-0001-8356-1361"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Weiru Liu","raw_affiliation_strings":["University of Bristol, Bristol, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Bristol, Bristol, United Kingdom","institution_ids":["https://openalex.org/I36234482"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5076414931"],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":null,"apc_paid":null,"fwci":0.2944,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.55815804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"548","last_page":"554"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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/T10036","display_name":"Advanced Neural Network Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.8737546801567078},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6760236620903015},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6693540811538696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6505013108253479},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6148859858512878},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6065330505371094},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5920349359512329},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.568191647529602},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.501126766204834},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4568136930465698},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44931501150131226},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4484975039958954},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4324778914451599},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4195745587348938},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4183599352836609},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.41648954153060913},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2564241290092468},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13687404990196228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8737546801567078},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6760236620903015},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6693540811538696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6505013108253479},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6148859858512878},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6065330505371094},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5920349359512329},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.568191647529602},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.501126766204834},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4568136930465698},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44931501150131226},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4484975039958954},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4324778914451599},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4195745587348938},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4183599352836609},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.41648954153060913},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2564241290092468},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13687404990196228},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":3,"locations":[{"id":"doi:10.1145/3372278.3390714","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:research-information.bris.ac.uk:openaire/fabce957-3915-41ae-b997-f7b16e6a427b","is_oa":true,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/fabce957-3915-41ae-b997-f7b16e6a427b","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Dong, J, Yuan, J, Li, L, Zhong, X & Liu, W 2020, Optimizing Queries over Video via Lightweight Keypoint-based Object Detection. in ACM International Conference on Multimedia Retrieval (ICMR)'2020. Association for Computing Machinery, pp. 548-554. https://doi.org/10.1145/3372278.3390714","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:research-information.bris.ac.uk:publications/fabce957-3915-41ae-b997-f7b16e6a427b","is_oa":false,"landing_page_url":"https://hdl.handle.net/1983/fabce957-3915-41ae-b997-f7b16e6a427b","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:research-information.bris.ac.uk:openaire/fabce957-3915-41ae-b997-f7b16e6a427b","is_oa":true,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/fabce957-3915-41ae-b997-f7b16e6a427b","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Dong, J, Yuan, J, Li, L, Zhong, X & Liu, W 2020, Optimizing Queries over Video via Lightweight Keypoint-based Object Detection. in ACM International Conference on Multimedia Retrieval (ICMR)'2020. Association for Computing Machinery, pp. 548-554. https://doi.org/10.1145/3372278.3390714","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2223137777","display_name":null,"funder_award_id":"15BGL048","funder_id":"https://openalex.org/F4320335869","funder_display_name":"National Social Science Fund of China"},{"id":"https://openalex.org/G4008716106","display_name":null,"funder_award_id":"61303029","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2102605133","https://openalex.org/W2307770531","https://openalex.org/W2531409750","https://openalex.org/W2570343428","https://openalex.org/W2610420510","https://openalex.org/W2612445135","https://openalex.org/W2752236330","https://openalex.org/W2796347433","https://openalex.org/W2916798096","https://openalex.org/W2951173410","https://openalex.org/W2953106684","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963163009","https://openalex.org/W2963342610","https://openalex.org/W2963510045","https://openalex.org/W2963786238","https://openalex.org/W2963927307","https://openalex.org/W2989604896","https://openalex.org/W2998752879","https://openalex.org/W3012573144","https://openalex.org/W3102262568","https://openalex.org/W3106250896"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,188],"convolutional":[3],"neural":[4],"networks":[5],"based":[6],"object":[7,35,81],"detection":[8],"have":[9],"enabled":[10],"analyzing":[11],"the":[12,33,39,67,87,97,104,113,131,141,147],"mounting":[13],"video":[14,28,45,56,189],"data":[15],"with":[16,155,163],"high":[17],"accuracy.":[18],"However,":[19],"inference":[20,118],"speed":[21],"is":[22,101,108],"a":[23,50,60,78,93,122,126,136],"major":[24],"drawback":[25],"of":[26,32,44,71,89,128],"these":[27],"analysis":[29],"system":[30,51],"because":[31],"heavy":[34],"detectors.":[36],"To":[37,116],"address":[38],"computational":[40],"and":[41,69,125],"practicability":[42],"challenges":[43],"analysis,":[46],"we":[47],"propose":[48],"FastQ,":[49],"for":[52,73],"efficient":[53],"querying":[54],"over":[55],"at":[57,169],"scale.":[58],"Given":[59],"target":[61],"video,":[62],"FastQ":[63,174],"can":[64],"automatically":[65],"label":[66,112],"category":[68],"number":[70],"objects":[72],"each":[74],"frame.":[75],"We":[76],"introduce":[77],"novel":[79],"lightweight":[80,137],"detector":[82,95],"named":[83],"FDet":[84,107,120,144,159],"to":[85,110,139,151,178],"improve":[86],"efficiency":[88],"query":[90],"system.":[91],"First,":[92],"difference":[94,100],"filters":[96],"frames":[98],"whose":[99],"less":[102],"than":[103,185],"threshold.":[105],"Second,":[106],"employed":[109],"efficiently":[111],"remaining":[114],"frames.":[115],"reduce":[117],"time,":[119],"detects":[121],"center":[123],"keypoint":[124],"pair":[127],"corners":[129],"from":[130],"feature":[132],"map":[133],"generated":[134],"by":[135],"backbone":[138],"predict":[140],"bounding":[142],"boxes.":[143,153],"completely":[145],"avoid":[146],"complicated":[148],"computation":[149],"related":[150],"anchor":[152],"Compared":[154],"state-of-the-art":[156],"real-time":[157],"detectors,":[158],"achieves":[160,175],"superior":[161],"performance":[162],"29.1%":[164],"AP":[165],"on":[166],"COCO":[167],"benchmark":[168],"25.3ms.":[170],"Experiments":[171],"show":[172],"that":[173],"150":[176],"times":[177,180],"300":[179],"speed-ups":[181],"while":[182],"maintaining":[183],"more":[184],"90%":[186],"accuracy":[187],"queries.":[190]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}