{"id":"https://openalex.org/W4408930345","doi":"https://doi.org/10.1145/3726529","title":"Beyond Visual Cues: Synchronously Exploring Target-Centric Semantics for Vision-Language Tracking","display_name":"Beyond Visual Cues: Synchronously Exploring Target-Centric Semantics for Vision-Language Tracking","publication_year":2025,"publication_date":"2025-03-28","ids":{"openalex":"https://openalex.org/W4408930345","doi":"https://doi.org/10.1145/3726529"},"language":"en","primary_location":{"id":"doi:10.1145/3726529","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3726529","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5018527272","display_name":"Jiawei Ge","orcid":"https://orcid.org/0000-0001-7268-7815"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiawei Ge","raw_affiliation_strings":["School of Cyber Science and Engineering, Southeast University, Nanjing, China","School of Cyber Science and Engineering, Southeast University, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012384188","display_name":"Jiuxin Cao","orcid":"https://orcid.org/0000-0002-2448-6717"},"institutions":[{"id":"https://openalex.org/I4210155350","display_name":"Purple Mountain Laboratories","ror":"https://ror.org/04zcbk583","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210155350"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiuxin Cao","raw_affiliation_strings":["School of Cyber Science and Engineering, Southeast University, Nanjing, China and Purple Mountain Laboratories, Nanjing, China","School of Cyber Science and Engineering, Southeast University, China and Purple Mountain Laboratories, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China and Purple Mountain Laboratories, Nanjing, China","institution_ids":["https://openalex.org/I4210155350"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, China and Purple Mountain Laboratories, China","institution_ids":["https://openalex.org/I4210155350","https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008100554","display_name":"Xiangmei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangmei Chen","raw_affiliation_strings":["School of Cyber Science and Engineering, Southeast University, Nanjing, China","School of Cyber Science and Engineering, Southeast University, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076214561","display_name":"Xuelin Zhu","orcid":"https://orcid.org/0000-0001-7676-2843"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelin Zhu","raw_affiliation_strings":["School of Cyber Science and Engineering, Southeast University, Nanjing, China","School of Cyber Science and Engineering, Southeast University, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747522","display_name":"Weijia Liu","orcid":"https://orcid.org/0000-0003-2634-7283"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijia Liu","raw_affiliation_strings":["School of Cyber Science and Engineering, Southeast University, Nanjing, China","School of Cyber Science and Engineering, Southeast University, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102824119","display_name":"Chang Liu","orcid":"https://orcid.org/0009-0005-3136-0484"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Liu","raw_affiliation_strings":["School of Cyber Science and Engineering, Southeast University, Nanjing, China","School of Cyber Science and Engineering, Southeast University, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042411401","display_name":"Kun Wang","orcid":"https://orcid.org/0000-0002-6735-7667"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["School of Cyber Science and Engineering, Southeast University, Nanjing, China","School of Cyber Science and Engineering, Southeast University, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100461575","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0001-5209-9063"},"institutions":[{"id":"https://openalex.org/I4210155350","display_name":"Purple Mountain Laboratories","ror":"https://ror.org/04zcbk583","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210155350"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China and Purple Mountain Laboratories, Nanjing, China","School of Computer Science and Engineering, Southeast University, China and Purple Mountain Laboratories, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China and Purple Mountain Laboratories, Nanjing, China","institution_ids":["https://openalex.org/I4210155350"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, China and Purple Mountain Laboratories, China","institution_ids":["https://openalex.org/I4210155350","https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5018527272"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":8.5265,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.97627487,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"21","issue":"5","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9983999729156494,"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":0.9983999729156494,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9961000084877014,"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":0.9825000166893005,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8935060501098633},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6214469075202942},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5540049076080322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4380587339401245},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39894920587539673},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22790521383285522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8935060501098633},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6214469075202942},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5540049076080322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4380587339401245},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39894920587539673},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22790521383285522}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726529","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3726529","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2176857478","display_name":null,"funder_award_id":"62472092, 62172089, 62106045","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3522319323","display_name":null,"funder_award_id":"BK20241751","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2105824230","https://openalex.org/W2752782242","https://openalex.org/W2794744029","https://openalex.org/W2898200825","https://openalex.org/W2911392513","https://openalex.org/W2990187711","https://openalex.org/W3106542916","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3159231306","https://openalex.org/W3209828932","https://openalex.org/W4223989014","https://openalex.org/W4225616409","https://openalex.org/W4226077544","https://openalex.org/W4312509508","https://openalex.org/W4312532041","https://openalex.org/W4312567319","https://openalex.org/W4312961069","https://openalex.org/W4376226279","https://openalex.org/W4385569741","https://openalex.org/W4386075643","https://openalex.org/W4387724661","https://openalex.org/W4393147448","https://openalex.org/W4396505919","https://openalex.org/W4397026509","https://openalex.org/W4400975126","https://openalex.org/W4401163825","https://openalex.org/W4402592965","https://openalex.org/W4402754169","https://openalex.org/W4403791254","https://openalex.org/W4403792529","https://openalex.org/W6739901393","https://openalex.org/W6839144149","https://openalex.org/W6852835101"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Single":[0],"object":[1],"tracking":[2,56],"aims":[3],"to":[4,26,49,159,177],"locate":[5],"one":[6],"specific":[7],"target":[8],"in":[9],"video":[10],"sequences,":[11],"given":[12],"its":[13],"initial":[14],"state.":[15],"Classical":[16],"trackers":[17,62],"rely":[18],"solely":[19],"on":[20,81,185],"visual":[21,166],"cues,":[22],"restricting":[23],"their":[24],"ability":[25],"handle":[27],"challenges":[28],"such":[29,77],"as":[30,42,72,78],"appearance":[31],"variations,":[32],"ambiguity,":[33],"and":[34,54,91,137,150,167,191],"distractions.":[35],"Hence,":[36],"Vision-Language":[37,60],"Tracking":[38],"(VLT)":[39],"has":[40],"emerged":[41],"a":[43,105],"promising":[44],"approach,":[45],"incorporating":[46],"language":[47],"descriptions":[48],"directly":[50],"provide":[51],"high-level":[52],"semantics":[53,112,163],"enhance":[55],"performance.":[57],"However,":[58],"current":[59],"(VL)":[61],"have":[63],"not":[64],"fully":[65],"exploited":[66],"the":[67,92,118,132,138,146,153,157,173,189],"power":[68],"of":[69,94,128,193],"multi-modal":[70,100,147,180],"learning,":[71],"they":[73],"suffer":[74],"from":[75,164],"limitations":[76],"heavily":[79],"relying":[80],"off-the-shelf":[82],"backbones":[83],"for":[84,98,113,124],"feature":[85,148],"extraction,":[86],"ineffective":[87],"asynchronous":[88],"fusion":[89],"designs,":[90],"absence":[93],"VL-related":[95],"loss":[96,176],"functions":[97],"optimizing":[99],"representation.":[101],"Consequently,":[102],"we":[103,116,171],"present":[104],"novel":[106,130],"tracker":[107,158],"that":[108],"progressively":[109],"explores":[110],"target-centric":[111],"VLT.":[114],"Specifically,":[115],"propose":[117],"first":[119],"Synchronous":[120],"Learning":[121],"Backbone":[122],"(SLB)":[123],"VLT,":[125],"which":[126],"consists":[127],"two":[129],"modules:":[131],"Target":[133],"Enhance":[134],"Module":[135,140],"(TEM)":[136],"Semantic-Aware":[139],"(SAM).":[141],"These":[142],"modules":[143],"together":[144],"ensure":[145],"extraction":[149],"interaction":[151],"at":[152],"same":[154],"pace,":[155],"facilitating":[156],"synchronously":[160],"perceive":[161],"target-related":[162],"both":[165],"textual":[168],"modalities.":[169],"Moreover,":[170],"devise":[172],"dense":[174],"matching":[175],"further":[178],"strengthen":[179],"representation":[181],"learning.":[182],"Extensive":[183],"experiments":[184],"VLT":[186],"datasets":[187],"demonstrate":[188],"superiority":[190],"effectiveness":[192],"our":[194],"methods.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}