{"id":"https://openalex.org/W3162188794","doi":"https://doi.org/10.1109/icpr48806.2021.9412715","title":"Video Object Detection Using Object's Motion Context and Spatio-Temporal Feature Aggregation","display_name":"Video Object Detection Using Object's Motion Context and Spatio-Temporal Feature Aggregation","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3162188794","doi":"https://doi.org/10.1109/icpr48806.2021.9412715","mag":"3162188794"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/A5034676531","display_name":"Jaekyum Kim","orcid":"https://orcid.org/0000-0001-6603-0083"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaekyum Kim","raw_affiliation_strings":["Dept. of Electrical Engineering, Hanyang University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, Hanyang University, Seoul, Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082024481","display_name":"Junho Koh","orcid":"https://orcid.org/0000-0003-2318-9128"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junho Koh","raw_affiliation_strings":["Dept. of Electrical Engineering, Hanyang University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, Hanyang University, Seoul, Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080216224","display_name":"Byeongwon Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I134353371","display_name":"SK Group (South Korea)","ror":"https://ror.org/03696td91","country_code":"KR","type":"company","lineage":["https://openalex.org/I134353371"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeongwon Lee","raw_affiliation_strings":["T3K Vision AI Product Center of Excellence, SK Telecom, Seongnam, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T3K Vision AI Product Center of Excellence, SK Telecom, Seongnam, Korea","institution_ids":["https://openalex.org/I134353371"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111370827","display_name":"Seungji Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I134353371","display_name":"SK Group (South Korea)","ror":"https://ror.org/03696td91","country_code":"KR","type":"company","lineage":["https://openalex.org/I134353371"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungji Yang","raw_affiliation_strings":["T3K Vision AI Product Center of Excellence, SK Telecom, Seongnam, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T3K Vision AI Product Center of Excellence, SK Telecom, Seongnam, Korea","institution_ids":["https://openalex.org/I134353371"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102839991","display_name":"Jun Won Choi","orcid":"https://orcid.org/0000-0002-3733-0148"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jun Won Choi","raw_affiliation_strings":["Hanyang University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University, Seoul, Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6792,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.70768213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1604","last_page":"1610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","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/T10331","display_name":"Video Surveillance and Tracking Methods","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":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7286555171012878},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7218600511550903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6852011680603027},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6292890310287476},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6008701324462891},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5993046760559082},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5131590962409973},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5101759433746338},{"id":"https://openalex.org/keywords/object-class-detection","display_name":"Object-class detection","score":0.410098135471344},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.328769326210022},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3074191212654114},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08599594235420227},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.06768274307250977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7286555171012878},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7218600511550903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6852011680603027},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6292890310287476},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6008701324462891},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5993046760559082},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5131590962409973},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5101759433746338},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.410098135471344},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.328769326210022},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3074191212654114},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08599594235420227},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.06768274307250977},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7220967885","display_name":null,"funder_award_id":"2020R1A2C2012146","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7335664070","display_name":null,"funder_award_id":"2020-0-01373","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320321142","display_name":"Hanyang University","ror":"https://ror.org/046865y68"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W764651262","https://openalex.org/W1485009520","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1923332106","https://openalex.org/W2064675550","https://openalex.org/W2102605133","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2282391807","https://openalex.org/W2565639579","https://openalex.org/W2601564443","https://openalex.org/W2612445135","https://openalex.org/W2613718673","https://openalex.org/W2770156722","https://openalex.org/W2792075695","https://openalex.org/W2898044248","https://openalex.org/W2950800384","https://openalex.org/W2962855257","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963625188","https://openalex.org/W2964086649","https://openalex.org/W2964286567","https://openalex.org/W2983827899","https://openalex.org/W2990578161","https://openalex.org/W2994810768","https://openalex.org/W3106250896","https://openalex.org/W3161192763","https://openalex.org/W4292542982","https://openalex.org/W4293437100","https://openalex.org/W4297775537","https://openalex.org/W6714138976","https://openalex.org/W6746472748","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2901758161","https://openalex.org/W4205668735","https://openalex.org/W3204852000","https://openalex.org/W3209429418","https://openalex.org/W4297540035","https://openalex.org/W4312834249","https://openalex.org/W2582431195","https://openalex.org/W2997780656","https://openalex.org/W3126664501","https://openalex.org/W4366374902"],"abstract_inverted_index":{"The":[0,182],"deep":[1],"learning":[2],"technique":[3],"has":[4,64],"recently":[5],"led":[6],"to":[7,40,158,174,188,199,224],"significant":[8,257],"improvement":[9],"in":[10,44,58,81,85,203,234],"object":[11,17,34,60,69,87,98,211,218,245,270],"detection":[12,18,35,70,88,99,246],"accuracy.":[13],"In":[14,90,156],"many":[15],"applications,":[16],"is":[19,142,186],"performed":[20],"on":[21,196,242],"video":[22,46,97,210,248,269],"data":[23],"consisting":[24],"of":[25,28,178,230],"a":[26,95],"sequence":[27,84],"two-dimensional":[29],"(2D)":[30],"image":[31,53,83,119,206],"frames.":[32],"Numerous":[33],"schemes":[36],"have":[37,213],"been":[38,65,214],"designed":[39],"detect":[41],"objects":[42],"independently":[43],"each":[45],"frame.":[47,207],"Though":[48],"temporal":[49,79,192],"information":[50],"within":[51],"adjacent":[52,110,130],"frames":[54,111,131,171],"can":[55,72],"be":[56,73],"exploited":[57],"subsequent":[59],"tracking":[61],"stage,":[62],"it":[63],"shown":[66],"that":[67,101,252],"the":[68,78,82,86,104,109,113,118,124,135,139,146,160,163,176,179,191,200,204,228,243,261,266],"accuracy":[71],"significantly":[74],"improved":[75],"by":[76,144],"exploiting":[77],"structure":[80],"stage.":[89],"this":[91],"paper,":[92],"we":[93],"propose":[94],"novel":[96],"method":[100],"exploits":[102],"both":[103],"motion":[105,140,161],"context":[106],"inferred":[107],"from":[108,247],"and":[112,134,264],"spatio-temporal":[114],"features":[115],"aggregated":[116,173],"over":[117,128,260],"sequence.":[120],"First,":[121],"correlation":[122,148],"between":[123],"spatial":[125,164],"feature":[126,165,180,193,201],"maps":[127,149,166,194],"two":[129],"are":[132,172],"computed":[133],"embedding":[136],"vector,":[137],"representing":[138],"context,":[141,162],"obtained":[143],"encoding":[145],"N":[147],"using":[150],"long":[151],"short":[152],"term":[153],"memory":[154],"(LSTM).":[155],"addition":[157],"utilizing":[159],"for":[167,216],"(":[168],"N+1)":[169],"consecutive":[170],"boost":[175],"quality":[177],"map.":[181],"gated":[183],"attention":[184],"network":[185,255],"employed":[187],"selectively":[189],"combine":[190],"based":[195],"their":[197],"relevance":[198],"map":[202],"present":[205],"While":[208],"most":[209],"detectors":[212,226],"developed":[215],"two-stage":[217],"detectors,":[219],"our":[220,253],"proposed":[221,254],"idea":[222],"applies":[223],"one-stage":[225,268],"with":[227],"advantage":[229],"low":[231],"computational":[232],"complexity":[233],"practical":[235],"real-time":[236],"applications.":[237],"Our":[238],"numerical":[239],"evaluation":[240],"conducted":[241],"ImageNet":[244],"(VID)":[249],"dataset":[250],"demonstrates":[251],"achieves":[256],"performance":[258],"gain":[259],"baseline":[262],"algorithms":[263],"outperforms":[265],"existing":[267],"detectors.":[271]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}