{"id":"https://openalex.org/W7162463907","doi":"https://doi.org/10.48550/arxiv.2605.25110","title":"Uncertainty-DTW for Sequences and Visual Tokens","display_name":"Uncertainty-DTW for Sequences and Visual Tokens","publication_year":2026,"publication_date":"2026-05-24","ids":{"openalex":"https://openalex.org/W7162463907","doi":"https://doi.org/10.48550/arxiv.2605.25110"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.25110","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25110","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.2605.25110","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137029140","display_name":"Lei Wang","orcid":"https://orcid.org/0009-0004-3391-093X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137014119","display_name":"Syuan-Hao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Syuan-Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137055114","display_name":"Yongsheng Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Yongsheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137013801","display_name":"Piotr Koniusz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koniusz, Piotr","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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9521999955177307,"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"}},"topics":[{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9521999955177307,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.010300000198185444,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.00419999985024333,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.7074000239372253},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5817999839782715},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5454000234603882},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4918000102043152},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4348999857902527},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4108000099658966},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.3840000033378601},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.38190001249313354},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.36910000443458557}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7074000239372253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.666100025177002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6549999713897705},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5817999839782715},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5454000234603882},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4918000102043152},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4198000133037567},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3562000095844269},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3427000045776367},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3382999897003174},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3370000123977661},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3059000074863434},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3005000054836273},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.2517000138759613},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.25110","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25110","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.2605.25110","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25110","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":{"Aligning":[0],"structured":[1,72,152,234],"data":[2],"is":[3,125],"a":[4,60,84,93,101,111,120,166,186,225],"fundamental":[5],"problem":[6],"in":[7],"computer":[8],"vision":[9],"and":[10,23,35,44,50,70,87,109,129,174,191,210,228],"machine":[11],"learning,":[12],"underlying":[13],"tasks":[14],"such":[15],"as":[16,131,165,224],"time":[17],"series":[18],"analysis,":[19],"human":[20],"action":[21],"recognition,":[22],"visual":[24,149,157],"representation":[25],"learning.":[26],"Existing":[27],"alignment":[28,75,90,122,223],"methods,":[29],"including":[30],"Dynamic":[31],"Time":[32],"Warping":[33],"(DTW)":[34],"its":[36],"differentiable":[37],"variants,":[38],"rely":[39],"on":[40],"deterministic":[41],"similarity":[42],"measures":[43],"are":[45],"therefore":[46],"sensitive":[47],"to":[48,127,147],"heterogeneous":[49],"noisy":[51],"features.":[52],"In":[53],"this":[54,142],"work,":[55],"we":[56],"introduce":[57],"uncertainty-aware":[58,222],"alignment,":[59,177,189],"probabilistic":[61,121],"framework":[62,143,198,230],"that":[63,105,114,124,212],"models":[64],"pairwise":[65],"correspondences":[66],"with":[67,216],"heteroscedastic":[68],"uncertainty":[69,132,161,173,192,214],"performs":[71],"matching":[73,103,153],"along":[74],"paths.":[76],"Our":[77],"formulation,":[78],"uncertainty-DTW":[79],"(uDTW),":[80],"assigns":[81],"each":[82,89],"correspondence":[83],"Normal":[85],"distribution":[86],"parametrizes":[88],"path":[91],"by":[92],"Maximum":[94],"Likelihood":[95],"Estimate":[96],"objective":[97],"consisting":[98],"of":[99,137,156],"(i)":[100],"precision-weighted":[102],"term":[104],"suppresses":[106],"unreliable":[107],"features,":[108],"(ii)":[110],"log-variance":[112],"regularization":[113],"prevents":[115],"degenerate":[116],"solutions.":[117],"This":[118,184],"yields":[119],"mechanism":[123],"robust":[126],"noise":[128],"interpretable,":[130],"directly":[133],"reflects":[134],"the":[135,176,196],"reliability":[136],"matches.":[138],"We":[139,194],"further":[140],"generalize":[141],"from":[144,233],"temporal":[145],"sequences":[146],"tokenized":[148],"representations,":[150],"enabling":[151],"over":[154,207],"sets":[155],"tokens.":[158],"The":[159,202],"learned":[160,213],"can":[162],"be":[163],"interpreted":[164],"reverse-attention:":[167],"semantically":[168],"relevant":[169],"regions":[170,180],"exhibit":[171],"low":[172],"dominate":[175],"while":[178],"ambiguous/noisy":[179],"have":[181],"high":[182],"uncertainty.":[183],"provides":[185],"connection":[187],"between":[188],"attention,":[190],"modeling.":[193],"evaluate":[195],"proposed":[197],"across":[199],"diverse":[200],"domains.":[201],"results":[203],"demonstrate":[204],"consistent":[205],"improvements":[206],"state-of-the-art":[208],"methods":[209],"show":[211],"correlates":[215],"semantic":[217],"importance.":[218],"These":[219],"findings":[220],"establish":[221],"general,":[226],"robust,":[227],"interpretable":[229],"for":[231],"learning":[232],"data.":[235]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-27T00:00:00"}