{"id":"https://openalex.org/W7101395189","doi":"https://doi.org/10.26599/cvm.2025.9450418","title":"Exploring a Hierarchical Cross-Attention Transformer for High-Speed Tracking","display_name":"Exploring a Hierarchical Cross-Attention Transformer for High-Speed Tracking","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W7101395189","doi":"https://doi.org/10.26599/cvm.2025.9450418"},"language":"en","primary_location":{"id":"doi:10.26599/cvm.2025.9450418","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450418","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.26599/cvm.2025.9450418","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Chen","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology,Dalian,China,116024"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology,Dalian,China,116024","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ben Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ben Kang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology,Dalian,China,116024"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology,Dalian,China,116024","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiawen Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawen Zhu","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology,Dalian,China,116024"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology,Dalian,China,116024","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dongdong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongdong Li","raw_affiliation_strings":["National University of Defense Technology,National Key Laboratory of Science and Technology on Automatic Target Recognition,Changsha,China,410073"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,National Key Laboratory of Science and Technology on Automatic Target Recognition,Changsha,China,410073","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chunjuan Bo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]},{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunjuan Bo","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian Minzu University,Dalian,China,116600"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian Minzu University,Dalian,China,116600","institution_ids":["https://openalex.org/I4210092944","https://openalex.org/I61565387"]}]},{"author_position":"last","author":{"id":null,"display_name":"Dong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology,Dalian,China,116024"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology,Dalian,China,116024","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45882024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"5","first_page":"1113","last_page":"1132"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9314000010490417,"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":0.9314000010490417,"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":0.017899999395012856,"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/T11448","display_name":"Face recognition and analysis","score":0.003700000001117587,"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/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.7411999702453613},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.6341999769210815},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6201000213623047},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4424999952316284},{"id":"https://openalex.org/keywords/tracking-system","display_name":"Tracking system","score":0.43290001153945923},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.36579999327659607},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.3517000079154968}],"concepts":[{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.7411999702453613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307000160217285},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.6341999769210815},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6201000213623047},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.43290001153945923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4020000100135803},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3517000079154968},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31619998812675476},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3140999972820282},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2922999858856201},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28119999170303345},{"id":"https://openalex.org/C102349902","wikidata":"https://www.wikidata.org/wiki/Q385390","display_name":"Serial port","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25540000200271606},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.26599/cvm.2025.9450418","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450418","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e82b645279d543e2847cacaa88283fb7","is_oa":true,"landing_page_url":"https://doaj.org/article/e82b645279d543e2847cacaa88283fb7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Visual Media, Vol 11, Iss 5, Pp 1113-1132 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.26599/cvm.2025.9450418","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450418","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3447656322","display_name":null,"funder_award_id":"62176041,62102426,U23A20384","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1857884451","https://openalex.org/W1861492603","https://openalex.org/W2117539524","https://openalex.org/W2158592639","https://openalex.org/W2194775991","https://openalex.org/W2408241409","https://openalex.org/W2470394683","https://openalex.org/W2518876086","https://openalex.org/W2557641257","https://openalex.org/W2605173812","https://openalex.org/W2618530766","https://openalex.org/W2794744029","https://openalex.org/W2799058067","https://openalex.org/W2891033863","https://openalex.org/W2898200825","https://openalex.org/W2962766617","https://openalex.org/W2963227409","https://openalex.org/W2963534981","https://openalex.org/W2964423614","https://openalex.org/W2966759264","https://openalex.org/W2998434318","https://openalex.org/W3001584168","https://openalex.org/W3035511673","https://openalex.org/W3035571898","https://openalex.org/W3090155371","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3108519869","https://openalex.org/W3121523901","https://openalex.org/W3127756064","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3167536469","https://openalex.org/W3167762749","https://openalex.org/W3173344965","https://openalex.org/W3181069167","https://openalex.org/W3203857058","https://openalex.org/W3214586131","https://openalex.org/W4214493665","https://openalex.org/W4214588794","https://openalex.org/W4214759957","https://openalex.org/W4246193833","https://openalex.org/W4302275239","https://openalex.org/W4312323989","https://openalex.org/W4312443924","https://openalex.org/W4312671791","https://openalex.org/W4312751983","https://openalex.org/W4312805142","https://openalex.org/W4312969002","https://openalex.org/W4319300771","https://openalex.org/W4320036892"],"related_works":[],"abstract_inverted_index":{"While":[0],"object":[1],"tracking":[2,32,48,60,80],"has":[3],"made":[4],"significantly":[5],"strides":[6],"in":[7,14],"accuracy,":[8],"there":[9],"remains":[10],"a":[11,68,91,131,148],"notable":[12],"gap":[13],"attention":[15],"toward":[16],"speed.":[17],"Most":[18],"trackers":[19],"prioritize":[20],"achieving":[21],"real-time":[22],"speed":[23,111],"on":[24,35,121,135],"powerful":[25],"GPUs,":[26],"yet":[27],"practical":[28],"applications":[29],"demand":[30],"higher":[31],"speeds,":[33],"particularly":[34],"edge":[36,127],"platforms.":[37],"In":[38],"response":[39],"to":[40,83,96],"this":[41],"need,":[42],"we":[43,89,140],"introduce":[44],"HCAT,":[45],"an":[46,143,152],"efficient":[47],"method":[49],"designed":[50],"for":[51,161],"high":[52],"speeds":[53],"across":[54],"diverse":[55],"devices":[56],"while":[57],"maintaining":[58],"superior":[59],"accuracy.":[61],"At":[62],"the":[63,74,78,86,102,106,122,136],"core":[64],"of":[65,77,105],"HCAT":[66,108],"lies":[67],"hierarchical":[69],"cross-attention":[70],"transformer":[71],"that":[72],"mitigates":[73],"serial":[75],"nature":[76],"transformer-based":[79],"model.":[81,107],"Additionally,":[82],"further":[84],"enhance":[85],"tracker's":[87],"speed,":[88],"propose":[90],"feature":[92],"sparsification":[93],"module":[94],"crafted":[95],"sparsify":[97],"template":[98],"features,":[99],"consequently":[100],"reducing":[101],"computational":[103],"load":[104],"demonstrates":[109],"remarkable":[110],"alongside":[112],"competitive":[113],"performance.":[114],"For":[115],"instance,":[116],"it":[117],"attains":[118],"55":[119],"fps":[120],"NVIDIA":[123],"Jetson":[124],"AGX":[125],"Xavier":[126],"device,":[128],"coupled":[129],"with":[130],"76.6%":[132],"AUC":[133],"score":[134],"TrackingNet":[137],"benchmark.":[138],"Furthermore,":[139],"have":[141],"developed":[142],"enhanced":[144],"version,":[145],"HCAT-M,":[146],"integrating":[147],"multi-template":[149],"framework":[150],"and":[151,165],"update":[153],"head.":[154],"This":[155],"variant":[156],"establishes":[157],"new":[158],"state-of-the-art":[159],"performance":[160],"high-speed":[162],"tracking.":[163],"Code":[164],"models":[166],"are":[167],"available":[168],"at":[169],"https://github.com/chenxin-dlut/HCAT.":[170]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-28T00:00:00"}
