{"id":"https://openalex.org/W7131428182","doi":"https://doi.org/10.48550/arxiv.2602.18990","title":"IDSelect: A RL-Based Cost-Aware Selection Agent for Video-based Multi-Modal Person Recognition","display_name":"IDSelect: A RL-Based Cost-Aware Selection Agent for Video-based Multi-Modal Person Recognition","publication_year":2026,"publication_date":"2026-02-22","ids":{"openalex":"https://openalex.org/W7131428182","doi":"https://doi.org/10.48550/arxiv.2602.18990"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.18990","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.18990","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2602.18990","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126718192","display_name":"Yuyang Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Yuyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126732826","display_name":"Yixuan Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Yixuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126787111","display_name":"Kien Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Kien","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041045546","display_name":"Lifeng Zhou","orcid":"https://orcid.org/0000-0001-7927-8504"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Lifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126799822","display_name":"Feng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Feng","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/T12740","display_name":"Gait Recognition and Analysis","score":0.9247000217437744,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12740","display_name":"Gait Recognition and Analysis","score":0.9247000217437744,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.024399999529123306,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.014000000432133675,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7002000212669373},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6054999828338623},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.48399999737739563},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4828000068664551},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4510999917984009},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.41909998655319214},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.41440001130104065},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.412200003862381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573000192642212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7113000154495239},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7002000212669373},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6054999828338623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5188000202178955},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.48399999737739563},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4828000068664551},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.18990","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.18990","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2602.18990","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.18990","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video-based":[0],"person":[1],"recognition":[2,93],"achieves":[3,136],"robust":[4],"identification":[5],"by":[6,18,150,157],"integrating":[7],"face,":[8],"body,":[9],"and":[10,115],"gait.":[11],"However,":[12],"current":[13],"systems":[14],"waste":[15],"computational":[16,96],"resources":[17],"processing":[19],"all":[20],"modalities":[21],"with":[22,87,95,140],"fixed":[23,70],"heavyweight":[24],"ensembles":[25,71],"regardless":[26],"of":[27],"input":[28],"complexity.":[29],"To":[30],"address":[31],"these":[32],"limitations,":[33],"we":[34],"propose":[35],"IDSelect,":[36],"a":[37,79],"reinforcement":[38,85],"learning-based":[39],"cost-aware":[40],"selector":[41,62],"that":[42,59,68],"chooses":[43],"one":[44],"pre-trained":[45],"model":[46,66,112],"per":[47,113],"modality":[48,114],"per-sequence":[49],"to":[50],"optimize":[51],"the":[52,106,109,120],"accuracy-efficiency":[53],"trade-off.":[54],"Our":[55],"key":[56],"insight":[57],"is":[58],"an":[60],"input-conditioned":[61],"can":[63],"discover":[64],"complementary":[65],"choices":[67],"surpass":[69],"while":[72,98,147,159],"using":[73,83],"substantially":[74],"fewer":[75],"resources.":[76],"IDSelect":[77],"trains":[78],"lightweight":[80],"agent":[81],"end-to-end":[82],"actor-critic":[84],"learning":[86],"budget-aware":[88],"optimization.":[89],"The":[90],"reward":[91],"balances":[92],"accuracy":[94,139,149],"cost,":[97],"entropy":[99],"regularization":[100],"prevents":[101],"premature":[102],"convergence.":[103],"At":[104],"inference,":[105],"policy":[107],"selects":[108],"most":[110],"probable":[111],"fuses":[116],"modality-specific":[117],"similarities":[118],"for":[119],"final":[121],"score.":[122],"Extensive":[123],"experiments":[124],"on":[125,133,152],"challenging":[126],"video-based":[127],"datasets":[128],"demonstrate":[129],"IDSelect's":[130],"superior":[131],"efficiency:":[132],"CCVID,":[134],"it":[135,154],"95.9%":[137],"Rank-1":[138],"92.4%":[141],"less":[142],"computation":[143,156],"than":[144],"strong":[145],"baselines":[146],"improving":[148],"1.8%;":[151],"MEVID,":[153],"reduces":[155],"41.3%":[158],"maintaining":[160],"competitive":[161],"performance.":[162]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-02-26T00:00:00"}