{"id":"https://openalex.org/W3016218509","doi":"https://doi.org/10.1109/icassp40776.2020.9054757","title":"Learning Spatio-Temporal Convolutional Network for Real-Time Object Tracking","display_name":"Learning Spatio-Temporal Convolutional Network for Real-Time Object Tracking","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016218509","doi":"https://doi.org/10.1109/icassp40776.2020.9054757","mag":"3016218509"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5038470837","display_name":"Hanzao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hanzao Chen","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036301580","display_name":"Xiaofen Xing","orcid":"https://orcid.org/0000-0002-0016-9055"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofen Xing","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007354180","display_name":"Xiangmin Xu","orcid":"https://orcid.org/0000-0003-4573-5820"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangmin Xu","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038470837"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0977,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36748,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"2153","last_page":"2157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","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/T10331","display_name":"Video Surveillance and Tracking Methods","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9930999875068665,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8131430149078369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7437763810157776},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7118796110153198},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.6911818981170654},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6186152696609497},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.603026270866394},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.577112078666687},{"id":"https://openalex.org/keywords/inter-frame","display_name":"Inter frame","score":0.5114372968673706},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49718835949897766},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4892244338989258},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4598241150379181},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.43955516815185547},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3586893081665039},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3492533266544342},{"id":"https://openalex.org/keywords/reference-frame","display_name":"Reference frame","score":0.3239966034889221},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.18438240885734558},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.15883314609527588}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8131430149078369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7437763810157776},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7118796110153198},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.6911818981170654},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6186152696609497},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.603026270866394},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.577112078666687},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.5114372968673706},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49718835949897766},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4892244338989258},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4598241150379181},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.43955516815185547},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3586893081665039},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3492533266544342},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.3239966034889221},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18438240885734558},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.15883314609527588},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":27,"referenced_works":["https://openalex.org/W28988658","https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W1977709942","https://openalex.org/W2117539524","https://openalex.org/W2138558323","https://openalex.org/W2144516556","https://openalex.org/W2158592639","https://openalex.org/W2194775991","https://openalex.org/W2408241409","https://openalex.org/W2470394683","https://openalex.org/W2557641257","https://openalex.org/W2607661563","https://openalex.org/W2748399257","https://openalex.org/W2799058067","https://openalex.org/W2884585870","https://openalex.org/W2907243782","https://openalex.org/W2917435394","https://openalex.org/W2962864296","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2964253307","https://openalex.org/W2964423614","https://openalex.org/W4249420070","https://openalex.org/W6637373629","https://openalex.org/W6703518758","https://openalex.org/W6753412334"],"related_works":["https://openalex.org/W2120864667","https://openalex.org/W2012200063","https://openalex.org/W4320086059","https://openalex.org/W2120898383","https://openalex.org/W4210734798","https://openalex.org/W2117554142","https://openalex.org/W2405278583","https://openalex.org/W4312249400","https://openalex.org/W2367517378","https://openalex.org/W2985391290"],"abstract_inverted_index":{"Siamese":[0],"series":[1],"of":[2,19,27,38,62,75,101,123,136,157],"tracking":[3,44,193],"networks":[4],"have":[5],"shown":[6],"great":[7],"potentials":[8],"in":[9,66,195],"achieving":[10],"balanced":[11],"accuracy":[12],"and":[13,30,51,121],"beyond":[14],"real-time":[15],"speed.":[16],"However,":[17],"most":[18],"existing":[20],"siamese":[21,184],"trackers":[22],"only":[23],"consider":[24],"appearance":[25],"features":[26,100],"first":[28,102,128],"frame,":[29],"hardly":[31],"benefit":[32],"from":[33],"interframe":[34],"information.":[35],"The":[36],"lack":[37],"latest":[39,67,81,147],"temporal":[40],"transformation":[41],"degrades":[42],"the":[43,63,72,80,99,106,110,113,119,124,127,134,137,146,153,160,169,188],"performance":[45,194],"during":[46],"challenges":[47],"such":[48],"as":[49,133],"deformation":[50,120],"partial":[52],"occlusion.":[53],"In":[54],"this":[55],"paper":[56],"we":[57],"focus":[58],"on":[59],"making":[60],"using":[61,145],"rich":[64],"information":[65],"consecutive":[68],"frames":[69,82,148],"to":[70,88,104,152],"improve":[71],"feature":[73,161],"representation":[74],"initial":[76],"template":[77,114],"frame.":[78],"Specifically,":[79],"after":[83],"3d":[84],"convolution":[85,156],"are":[86],"used":[87,132],"generate":[89],"an":[90],"attention":[91,111],"map,":[92,112],"which":[93],"is":[94,130,140,179],"then":[95],"point-wise":[96],"multiplied":[97],"by":[98],"frame":[103,129],"obtain":[105],"updated":[107],"template.":[108],"With":[109],"can":[115,164],"adaptively":[116],"cope":[117],"with":[118],"occlusion":[122],"target.":[125],"Since":[126],"always":[131],"basis":[135],"template,":[138],"there":[139],"no":[141,174],"cumulative":[142],"error":[143],"when":[144],"for":[149],"attention.":[150],"Due":[151],"shared":[154],"2d":[155],"all":[158],"frames,":[159],"map":[162],"results":[163],"be":[165],"reused":[166],"so":[167],"that":[168],"added":[170],"module":[171,178,189],"has":[172,190],"almost":[173],"time-consuming":[175],"effects.":[176],"This":[177],"easily":[180],"embedded":[181],"into":[182],"different":[183,196],"trackers.":[185],"Through":[186],"verification,":[187],"significantly":[191],"improved":[192],"backbone":[197],"situations.":[198]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}