{"id":"https://openalex.org/W7137938445","doi":"https://doi.org/10.48550/arxiv.2603.13719","title":"Sparse-Dense Mixture of Experts Adapter for Multi-Modal Tracking","display_name":"Sparse-Dense Mixture of Experts Adapter for Multi-Modal Tracking","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137938445","doi":"https://doi.org/10.48550/arxiv.2603.13719"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.13719","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13719","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.13719","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038904514","display_name":"Yabin Zhu","orcid":"https://orcid.org/0000-0002-1000-2750"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yabin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129737023","display_name":"Jianqi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jianqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129694609","display_name":"Chenglong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chenglong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129712232","display_name":"Jiaxiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiaxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088326953","display_name":"Chenjie Gu","orcid":"https://orcid.org/0000-0002-1339-4534"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Chengjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129698799","display_name":"Jin Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.7950000166893005,"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":0.7950000166893005,"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":0.01730000041425228,"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/T10860","display_name":"Speech and Audio Processing","score":0.016699999570846558,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/adapter","display_name":"Adapter (computing)","score":0.7791000008583069},{"id":"https://openalex.org/keywords/hypergraph","display_name":"Hypergraph","score":0.6901999711990356},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6682999730110168},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.508899986743927},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.3982999920845032},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.36820000410079956},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.3573000133037567}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.7791000008583069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577000260353088},{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.6901999711990356},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6682999730110168},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.483599990606308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4634000062942505},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3982999920845032},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31310001015663147},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.13719","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13719","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.13719","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13719","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.6232065558433533}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Parameter-efficient":[0],"fine-tuning":[1],"(PEFT)":[2],"techniques,":[3],"such":[4],"as":[5,86],"prompts":[6],"and":[7,31,93,103,163,220],"adapters,":[8],"are":[9,171],"widely":[10],"used":[11],"in":[12,127],"multi-modal":[13,47,73,88,133,191,210],"tracking":[14,74,125,211],"because":[15],"they":[16],"alleviate":[17],"issues":[18],"of":[19,66,99,123,189],"full-model":[20],"fine-tuning,":[21],"including":[22,213],"time":[23],"inefficiency,":[24],"high":[25],"resource":[26],"consumption,":[27],"parameter":[28],"storage":[29],"burden,":[30],"catastrophic":[32],"forgetting.":[33],"However,":[34],"due":[35],"to":[36,44,90,120,178,182],"cross-modal":[37,117,151],"heterogeneity,":[38],"most":[39],"existing":[40,124],"PEFT-based":[41,72],"methods":[42,126],"struggle":[43],"effectively":[45],"represent":[46],"features":[48,170],"within":[49],"a":[50,62,76,100,104,137],"unified":[51,77],"framework":[52,70],"with":[53,204],"shared":[54,94,116],"parameters.":[55],"To":[56],"address":[57],"this":[58],"problem,":[59],"we":[60,81,135],"propose":[61],"novel":[63],"Sparse-Dense":[64],"Mixture":[65],"Experts":[67],"Adapter":[68],"(SDMoEA)":[69],"for":[71,150],"under":[75],"model":[78,91,183],"structure.":[79],"Specifically,":[80],"design":[82],"an":[83],"SDMoE":[84,97],"module":[85],"the":[87,107,113,156,175,197],"adapter":[89],"modality-specific":[92,110],"information":[95],"efficiently.":[96],"consists":[98],"sparse":[101],"MoE":[102],"dense-shared":[105],"MoE:":[106],"former":[108],"captures":[109],"information,":[111],"while":[112],"latter":[114],"models":[115],"information.":[118,192],"Furthermore,":[119],"overcome":[121],"limitations":[122],"modeling":[128],"high-order":[129,164,184],"correlations":[130],"during":[131],"multi-level":[132,190],"fusion,":[134],"introduce":[136],"Gram-based":[138],"Semantic":[139],"Alignment":[140],"Hypergraph":[141],"Fusion":[142],"(GSAHF)":[143],"module.":[144],"It":[145],"first":[146],"employs":[147],"Gram":[148],"matrices":[149],"semantic":[152,161],"alignment,":[153],"ensuring":[154],"that":[155,196],"constructed":[157],"hypergraph":[158,176],"accurately":[159],"reflects":[160],"similarity":[162],"dependencies":[165],"between":[166],"modalities.":[167],"The":[168],"aligned":[169],"then":[172],"integrated":[173],"into":[174],"structure":[177],"exploit":[179],"its":[180],"ability":[181],"relationships,":[185],"enabling":[186],"deep":[187],"fusion":[188],"Extensive":[193],"experiments":[194],"demonstrate":[195],"proposed":[198],"method":[199],"achieves":[200],"superior":[201],"performance":[202],"compared":[203],"other":[205],"PEFT":[206],"approaches":[207],"on":[208],"several":[209],"benchmarks,":[212],"LasHeR,":[214],"RGBT234,":[215],"VTUAV,":[216],"VisEvent,":[217],"COESOT,":[218],"DepthTrack,":[219],"VOT-RGBD2022.":[221]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-18T00:00:00"}