{"id":"https://openalex.org/W7162955105","doi":"https://doi.org/10.1145/3770854.3780181","title":"Vistar: Enhancing the Perception Capability of LLMs under Imprecise IMU-Text Alignment","display_name":"Vistar: Enhancing the Perception Capability of LLMs under Imprecise IMU-Text Alignment","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7162955105","doi":"https://doi.org/10.1145/3770854.3780181"},"language":"en","primary_location":{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-171985","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-171985","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},"type":"article","indexed_in":[],"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/A5137511409","display_name":"Yatong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chen, Yatong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103386678","display_name":"Can Hu","orcid":"https://orcid.org/0009-0007-0713-4393"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Chenzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137482263","display_name":"Bowen He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Bowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137485326","display_name":"Ruijie Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ruijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137504423","display_name":"Xiaomin Ouyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyang, Xiaomin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137476256","display_name":"Shengzhong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shengzhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137505374","display_name":"Jianxin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jianxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137504117","display_name":"Fan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137488333","display_name":"Guihai Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Guihai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5137511409"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94905123,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8216999769210815,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8216999769210815,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.026499999687075615,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.01979999989271164,"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/inertial-measurement-unit","display_name":"Inertial measurement unit","score":0.8733999729156494},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5896999835968018},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5609999895095825},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5156000256538391},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4571000039577484},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4334000051021576},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.420199990272522},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41839998960494995}],"concepts":[{"id":"https://openalex.org/C79061980","wikidata":"https://www.wikidata.org/wiki/Q941680","display_name":"Inertial measurement unit","level":2,"score":0.8733999729156494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7026000022888184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6432999968528748},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5896999835968018},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5609999895095825},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5156000256538391},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4799000024795532},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46320000290870667},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4334000051021576},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.420199990272522},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2915000021457672},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2671999931335449},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C151233233","wikidata":"https://www.wikidata.org/wiki/Q47574","display_name":"Units of measurement","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-171985","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-171985","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.48189425468444824}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"Vistar,":[3],"a":[4,56,139],"novel":[5],"self-supervised":[6],"framework":[7],"for":[8,16],"inertial":[9],"measurement":[10],"unit":[11],"(IMU)":[12],"signal":[13,78],"perception":[14,79,193],"designed":[15],"large":[17],"language":[18,38,98],"models":[19,45],"(LLMs).":[20],"Unlike":[21],"visual":[22,62],"data,":[23],"IMU":[24,54,66,77,104,130,159,192],"signals":[25],"are":[26],"high-frequency":[27],"time":[28],"series":[29],"with":[30,36,53,188],"low":[31],"interpretability,":[32],"making":[33],"manual":[34],"annotation":[35],"natural":[37],"particularly":[39],"challenging.":[40],"Even":[41],"when":[42],"using":[43],"vision-language":[44],"(VLMs)":[46],"to":[47,74,102,125,143,177,196],"describe":[48],"events":[49],"in":[50,179,191],"videos":[51],"synchronized":[52],"signals,":[55],"semantic":[57],"gap":[58],"remains":[59],"between":[60,82,129],"high-level":[61],"semantics":[63],"and":[64,86,97,114,131,182],"low-level":[65],"vibrations.":[67],"The":[68],"core":[69],"idea":[70],"of":[71,156],"Vistar":[72,93,136,169],"is":[73],"achieve":[75,126],"accurate":[76],"through":[80],"collaborations":[81],"offline":[83,91],"cross-modal":[84,108],"alignment":[85,128],"online":[87,134],"retrieval-augmented":[88,140],"generation.":[89],"During":[90],"training,":[92],"uses":[94],"pretrained":[95],"vision":[96],"encoders":[99,105],"as":[100],"anchors":[101],"learn":[103],"via":[106],"hierarchical":[107],"contrastive":[109],"learning,":[110],"establishing":[111],"both":[112],"inter-":[113],"intra-sample":[115],"alignment.":[116],"Given":[117],"that":[118,168],"the":[119,184],"enhanced":[120],"training":[121],"strategy":[122],"still":[123],"fails":[124],"precise":[127],"text,":[132],"during":[133],"inference,":[135],"further":[137],"employs":[138],"generation":[141],"mechanism":[142],"generate":[144],"distilled":[145],"textual":[146],"descriptions":[147],"from":[148],"similar":[149],"text":[150,186],"filtered":[151],"based":[152],"on":[153,163],"structural":[154],"relations":[155],"their":[157],"paired":[158],"samples.":[160],"Extensive":[161],"evaluations":[162],"three":[164],"multimodal":[165],"datasets":[166],"demonstrate":[167],"consistently":[170],"outperforms":[171],"state-of-the-art":[172],"(SOTA)":[173],"baselines":[174],"by":[175,194],"up":[176,195],"57.45%":[178],"IMU-to-text":[180],"retrieval":[181],"improves":[183],"generated":[185],"similarity":[187],"ground":[189],"truths":[190],"31.90%.":[197]},"counts_by_year":[],"updated_date":"2026-06-01T06:18:37.096963","created_date":"2026-06-01T00:00:00"}