{"id":"https://openalex.org/W4415540593","doi":"https://doi.org/10.1145/3746027.3755282","title":"Explicit Context Reasoning with Supervision for Visual Tracking","display_name":"Explicit Context Reasoning with Supervision for Visual Tracking","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540593","doi":"https://doi.org/10.1145/3746027.3755282"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755282","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":null,"display_name":"Fansheng Zeng","orcid":"https://orcid.org/0009-0003-0805-7853"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fansheng Zeng","raw_affiliation_strings":["Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0009-0003-0805-7853","affiliations":[{"raw_affiliation_string":"Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058101262","display_name":"Bineng Zhong","orcid":"https://orcid.org/0000-0003-3423-1539"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bineng Zhong","raw_affiliation_strings":["Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0000-0003-3423-1539","affiliations":[{"raw_affiliation_string":"Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046492947","display_name":"Haiying Xia","orcid":"https://orcid.org/0000-0001-8711-1851"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiying Xia","raw_affiliation_strings":["Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0000-0001-8711-1851","affiliations":[{"raw_affiliation_string":"Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107908583","display_name":"Yufei Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Tan","raw_affiliation_strings":["Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0009-0003-3472-842X","affiliations":[{"raw_affiliation_string":"Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102797916","display_name":"Xiantao Hu","orcid":"https://orcid.org/0009-0007-1541-1717"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiantao Hu","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0007-1541-1717","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046443025","display_name":"Liangtao Shi","orcid":"https://orcid.org/0009-0003-5934-8837"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangtao Shi","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-5934-8837","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025660318","display_name":"Shuxiang Song","orcid":"https://orcid.org/0000-0003-0280-2640"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuxiang Song","raw_affiliation_strings":["Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0000-0003-0280-2640","affiliations":[{"raw_affiliation_string":"Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28971934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8067","last_page":"8076"},"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":0.9993000030517578,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9962999820709229,"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/context","display_name":"Context (archaeology)","score":0.593999981880188},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5378000140190125},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4763999879360199},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4659000039100647},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46399998664855957},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4474000036716461},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4383000135421753},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.3905999958515167},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.3887999951839447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547000050544739},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.593999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.579800009727478},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5378000140190125},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46399998664855957},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4474000036716461},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4383000135421753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4092999994754791},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.3582000136375427},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C71611378","wikidata":"https://www.wikidata.org/wiki/Q5165191","display_name":"Contextual design","level":3,"score":0.3343000113964081},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25189998745918274},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755282","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5864722049","display_name":null,"funder_award_id":"U23A20383,62472109,62466051,62402252","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":24,"referenced_works":["https://openalex.org/W2470394683","https://openalex.org/W2557641257","https://openalex.org/W2794744029","https://openalex.org/W2799058067","https://openalex.org/W2891033863","https://openalex.org/W2962766617","https://openalex.org/W3090155371","https://openalex.org/W3108519869","https://openalex.org/W3174225630","https://openalex.org/W3181069167","https://openalex.org/W3214586131","https://openalex.org/W4214759957","https://openalex.org/W4312751983","https://openalex.org/W4312805142","https://openalex.org/W4323338406","https://openalex.org/W4380884766","https://openalex.org/W4382119472","https://openalex.org/W4386066081","https://openalex.org/W4393147957","https://openalex.org/W4393154017","https://openalex.org/W4393159185","https://openalex.org/W4396598146","https://openalex.org/W4402704627","https://openalex.org/W4409128969"],"related_works":[],"abstract_inverted_index":{"Contextual":[0],"reasoning":[1,57,71,80,110,127],"with":[2],"constraints":[3],"is":[4,192],"crucial":[5],"for":[6,13],"enhancing":[7,93],"temporal":[8,79,94,171],"consistency":[9],"in":[10,124,169],"cross-frame":[11],"modeling":[12],"visual":[14],"tracking.":[15],"However,":[16],"mainstream":[17],"tracking":[18],"algorithms":[19],"typically":[20],"associate":[21],"context":[22,56,126],"by":[23],"merely":[24],"stacking":[25],"historical":[26,89],"information":[27,148],"without":[28],"explicitly":[29,52],"supervising":[30],"the":[31,40,84,109,113,117,125,140,144,163],"association":[32,167],"process,":[33],"making":[34],"it":[35],"difficult":[36],"to":[37,107,138,160],"effectively":[38,161],"model":[39],"target's":[41],"evolving":[42],"dynamics.":[43],"To":[44],"alleviate":[45,162],"this":[46],"problem,":[47],"we":[48],"propose":[49],"RSTrack,":[50],"which":[51],"models":[53],"and":[54,121,151],"supervises":[55],"via":[58],"three":[59,157],"core":[60,141],"mechanisms.":[61],"1)":[62],"Context":[63],"Reasoning":[64],"Mechanism":[65],":":[66,100,133],"Constructs":[67],"a":[68,78,135],"target":[69,90,103,119],"state":[70],"pipeline,":[72,111],"converting":[73],"unconstrained":[74],"contextual":[75,154,166],"associations":[76],"into":[77],"process":[81],"that":[82,176],"predicts":[83],"current":[85],"representation":[86],"based":[87],"on":[88,181],"states,":[91],"thereby":[92],"consistency.":[95],"2)":[96],"Forward":[97],"Supervision":[98],"Strategy":[99],"Utilizes":[101],"true":[102,118],"features":[104,142],"as":[105],"anchors":[106],"constrain":[108],"guiding":[112],"predicted":[114],"output":[115],"toward":[116],"distribution":[120],"suppressing":[122],"drift":[123],"process.":[128],"3)":[129],"Efficient":[130],"State":[131],"Modeling":[132],"Employs":[134],"compression-reconstruction":[136],"mechanism":[137],"extract":[139],"of":[143,165],"target,":[145],"removing":[146],"redundant":[147],"across":[149],"frames":[150],"preventing":[152],"ineffective":[153],"associations.":[155],"These":[156],"mechanisms":[158],"collaborate":[159],"issue":[164],"divergence":[168],"traditional":[170],"modeling.":[172],"Experimental":[173],"results":[174],"show":[175],"RSTrack":[177],"achieves":[178],"state-of-the-art":[179],"performance":[180],"multiple":[182],"benchmark":[183],"datasets":[184],"while":[185],"maintaining":[186],"real-time":[187],"running":[188],"speeds.":[189],"Our":[190],"code":[191],"available":[193],"at":[194],"https://github.com/GXNU-ZhongLab/RSTrack.":[195]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}