{"id":"https://openalex.org/W4211088651","doi":"https://doi.org/10.1109/tip.2022.3148876","title":"Siamese Implicit Region Proposal Network With Compound Attention for Visual Tracking","display_name":"Siamese Implicit Region Proposal Network With Compound Attention for Visual Tracking","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4211088651","doi":"https://doi.org/10.1109/tip.2022.3148876","pmid":"https://pubmed.ncbi.nlm.nih.gov/35139020"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2022.3148876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3148876","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sixian Chan","orcid":"https://orcid.org/0000-0001-8916-1174"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sixian Chan","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jian Tao","orcid":"https://orcid.org/0000-0002-1809-5138"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Tao","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaolong Zhou","orcid":"https://orcid.org/0000-0003-0732-5169"},"institutions":[{"id":"https://openalex.org/I4210123686","display_name":"Quzhou University","ror":"https://ror.org/024nfx323","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210123686"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Zhou","raw_affiliation_strings":["College of Electrical and Information Engineering, Quzhou University, Quzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering, Quzhou University, Quzhou, China","institution_ids":["https://openalex.org/I4210123686"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cong Bai","orcid":"https://orcid.org/0000-0002-6177-3862"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Bai","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaoqin Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I146620803","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324","country_code":"CN","type":"education","lineage":["https://openalex.org/I146620803"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqin Zhang","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China","institution_ids":["https://openalex.org/I146620803"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55712492"],"apc_list":null,"apc_paid":null,"fwci":3.5729,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.94124525,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"1882","last_page":"1894"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.8988000154495239,"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":0.8988000154495239,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.02070000022649765,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T14413","display_name":"Advanced Technologies in Various Fields","score":0.014600000344216824,"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/discriminative-model","display_name":"Discriminative model","score":0.7892000079154968},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.7641000151634216},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.571399986743927},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4844000041484833},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47839999198913574},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4571000039577484},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4519999921321869},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4438999891281128},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.4142000079154968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980999946594238},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7892000079154968},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.7641000151634216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7190999984741211},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.571399986743927},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.515999972820282},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47839999198913574},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4438999891281128},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.4142000079154968},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.30550000071525574},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.25209999084472656}],"mesh":[{"descriptor_ui":"D001288","descriptor_name":"Attention","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001288","descriptor_name":"Attention","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001288","descriptor_name":"Attention","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2022.3148876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3148876","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:35139020","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35139020","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G133414184","display_name":null,"funder_award_id":"U2033210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3645213774","display_name":null,"funder_award_id":"61876168","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3796144338","display_name":null,"funder_award_id":"61922064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G491842903","display_name":null,"funder_award_id":"61976192","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5370040448","display_name":null,"funder_award_id":"92048301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7332861050","display_name":null,"funder_award_id":"61906168","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7555114670","display_name":null,"funder_award_id":"U20A20196","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8847732984","display_name":null,"funder_award_id":"LR21F020002","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1925950967","https://openalex.org/W1977995219","https://openalex.org/W2022603014","https://openalex.org/W2089961441","https://openalex.org/W2117539524","https://openalex.org/W2132083787","https://openalex.org/W2147800946","https://openalex.org/W2154889144","https://openalex.org/W2194775991","https://openalex.org/W2470394683","https://openalex.org/W2474309084","https://openalex.org/W2557641257","https://openalex.org/W2592463526","https://openalex.org/W2752782242","https://openalex.org/W2776035257","https://openalex.org/W2790194629","https://openalex.org/W2794744029","https://openalex.org/W2797812763","https://openalex.org/W2799058067","https://openalex.org/W2888456413","https://openalex.org/W2891033863","https://openalex.org/W2894176037","https://openalex.org/W2898200825","https://openalex.org/W2937749627","https://openalex.org/W2955747520","https://openalex.org/W2963091558","https://openalex.org/W2963179609","https://openalex.org/W2963227409","https://openalex.org/W2963471260","https://openalex.org/W2963534981","https://openalex.org/W2963854930","https://openalex.org/W2963899050","https://openalex.org/W2964423614","https://openalex.org/W2966759264","https://openalex.org/W2967622921","https://openalex.org/W2990211277","https://openalex.org/W2998027361","https://openalex.org/W2998237070","https://openalex.org/W2998434318","https://openalex.org/W3001584168","https://openalex.org/W3035211844","https://openalex.org/W3035257046","https://openalex.org/W3035460038","https://openalex.org/W3035511673","https://openalex.org/W3035571898","https://openalex.org/W3102817716","https://openalex.org/W3108519869","https://openalex.org/W3127178541","https://openalex.org/W3168663926","https://openalex.org/W3175891031","https://openalex.org/W3214586131","https://openalex.org/W6620707391","https://openalex.org/W6714138976","https://openalex.org/W6759215614","https://openalex.org/W6771274092","https://openalex.org/W6776662004","https://openalex.org/W6788922626"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"siamese-based":[1],"trackers":[2,9],"have":[3],"achieved":[4],"significant":[5],"successes.":[6],"However,":[7],"those":[8],"are":[10,70],"restricted":[11],"by":[12,53,93],"the":[13,21,25,73,84,116,125,130,139,143,147,151,160,165,169,176,201],"difficulty":[14],"of":[15,66,96,124,129,142,150,168,211],"learning":[16],"consistent":[17],"feature":[18,64,86],"representation":[19],"with":[20,38],"object.":[22,131,170],"To":[23,81],"address":[24],"above":[26],"challenge,":[27],"this":[28,82],"paper":[29],"proposes":[30],"a":[31,55,102,107,121],"novel":[32,56],"siamese":[33],"implicit":[34,46],"region":[35,47],"proposal":[36,48],"network":[37],"compound":[39,103],"attention":[40,104,111,134,155],"for":[41,137],"visual":[42],"tracking.":[43],"First,":[44],"an":[45,208],"(IRP)":[49],"module":[50,61,105,118],"is":[51,112,135,156],"designed":[52],"combining":[54],"pixel-wise":[57],"correlation":[58],"method.":[59],"This":[60],"can":[62,90,204],"aggregate":[63,159],"information":[65,141,162],"different":[67,99],"regions":[68],"that":[69,175,200],"similar":[71],"to":[72,114,119,145,158,163],"pre-defined":[74],"anchor":[75],"boxes":[76],"in":[77,214],"Region":[78],"Proposal":[79],"Network.":[80],"end,":[83],"adaptive":[85],"receptive":[87],"fields":[88],"then":[89],"be":[91,205],"obtained":[92,197],"linear":[94],"fusion":[95],"features":[97],"from":[98],"regions.":[100],"Second,":[101],"including":[106,187],"channel":[108,133],"and":[109,127,193],"non-local":[110,154],"raised":[113],"assist":[115],"IRP":[117],"perform":[120],"better":[122],"perception":[123],"scale":[126],"shape":[128],"The":[132],"applied":[136],"mining":[138],"discriminative":[140],"object":[144],"handle":[146],"background":[148],"clutters":[149],"template,":[152],"while":[153],"trained":[157],"contextual":[161],"learn":[164],"semantic":[166],"range":[167],"Finally,":[171],"experimental":[172],"results":[173,198],"demonstrate":[174,199],"proposed":[177,202],"tracker":[178],"achieves":[179],"state-of-the-art":[180],"performance":[181],"on":[182],"six":[183],"challenging":[184],"benchmark":[185],"tests,":[186],"VOT-2018,":[188],"VOT-2019,":[189],"OTB-100,":[190],"GOT-10k,":[191],"LaSOT,":[192],"TrackingNet.":[194],"Further,":[195],"our":[196],"approach":[203],"run":[206],"at":[207],"average":[209],"speed":[210],"72":[212],"FPS":[213],"real":[215],"time.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2022-02-13T00:00:00"}