{"id":"https://openalex.org/W4417098228","doi":"https://doi.org/10.1109/iccv51701.2025.01311","title":"ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition","display_name":"ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417098228","doi":"https://doi.org/10.1109/iccv51701.2025.01311"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.03948","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108798281","display_name":"Sanjoy Kundu","orcid":null},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjoy Kundu","raw_affiliation_strings":["Auburn University Auburn,CSSE Department,Alabama,USA,36849"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auburn University Auburn,CSSE Department,Alabama,USA,36849","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049705556","display_name":"Shanmukha Vellamcheti","orcid":null},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shanmukha Vellamcheti","raw_affiliation_strings":["Auburn University Auburn,CSSE Department,Alabama,USA,36849"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auburn University Auburn,CSSE Department,Alabama,USA,36849","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080710999","display_name":"Sathyanarayanan N. Aakur","orcid":"https://orcid.org/0000-0003-1062-8929"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sathyanarayanan N. Aakur","raw_affiliation_strings":["Auburn University Auburn,CSSE Department,Alabama,USA,36849"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auburn University Auburn,CSSE Department,Alabama,USA,36849","institution_ids":["https://openalex.org/I82497590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34785613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14128","last_page":"14140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.6014999747276306,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.6014999747276306,"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":0.30329999327659607,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.014600000344216824,"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":0.7143999934196472},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5371000170707703},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.51910001039505},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5048999786376953},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49309998750686646},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.47350001335144043},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"Activity recognition","score":0.4334000051021576},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.40400001406669617}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7143999934196472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769000291824341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6488000154495239},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5460000038146973},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5371000170707703},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.51910001039505},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49309998750686646},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.4334000051021576},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3091999888420105},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29260000586509705},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28439998626708984},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.03948","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.03948","pdf_url":"https://arxiv.org/pdf/2504.03948","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},{"id":"doi:10.48550/arxiv.2504.03948","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.03948","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.03948","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.03948","pdf_url":"https://arxiv.org/pdf/2504.03948","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},"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":{"Open-world":[0],"egocentric":[1,134],"activity":[2,78,135,154],"recognition":[3],"poses":[4],"a":[5,29,57,71,120],"fundamental":[6],"challenge":[7],"due":[8],"to":[9,15,55,75,97,104],"its":[10,95],"unconstrained":[11],"nature,":[12],"requiring":[13],"models":[14],"infer":[16],"unseen":[17],"activities":[18],"from":[19],"an":[20],"expansive,":[21],"partially":[22],"observed":[23],"search":[24,32,60,73,99,144],"space.":[25],"We":[26,85],"introduce":[27],"ProbRes,":[28],"Probabilistic":[30],"Residual":[31],"framework":[33],"based":[34],"on":[35,108],"jump-diffusion":[36],"that":[37],"efficiently":[38],"navigates":[39],"this":[40],"space":[41,100],"by":[42],"balancing":[43],"prior-guided":[44],"exploration":[45],"with":[46],"likelihood-driven":[47],"exploitation.":[48],"Our":[49,137],"approach":[50],"integrates":[51],"structured":[52,143],"commonsense":[53],"priors":[54],"construct":[56],"semantically":[58],"coherent":[59],"space,":[61],"adaptively":[62],"refines":[63],"predictions":[64],"using":[65],"Vision-Language":[66],"Models":[67],"(VLMs)":[68],"and":[69,116,129,151],"employs":[70],"stochastic":[72],"mechanism":[74],"locate":[76],"high-likelihood":[77],"labels":[79],"while":[80],"minimizing":[81],"exhaustive":[82],"enumeration":[83],"efficiently.":[84],"systematically":[86],"evaluate":[87],"ProbRes":[88],"across":[89],"multiple":[90],"openness":[91],"levels":[92],"(L0-L3),":[93],"demonstrating":[94],"adaptability":[96],"increasing":[98],"complexity.":[101],"In":[102],"addition":[103],"achieving":[105],"state-of-the-art":[106],"performance":[107],"benchmark":[109],"datasets":[110],"(GTEA":[111],"Gaze,":[112],"GTEA":[113],"Gaze+,":[114],"EPIC-Kitchens,":[115],"Charades-Ego),":[117],"we":[118],"establish":[119],"clear":[121],"taxonomy":[122],"for":[123,133,149],"open-world":[124,153],"recognition,":[125],"delineating":[126],"the":[127,140,147],"challenges":[128],"methodological":[130],"advancements":[131],"necessary":[132],"understanding.":[136],"results":[138],"highlight":[139],"importance":[141],"of":[142],"strategies,":[145],"paving":[146],"way":[148],"scalable":[150],"efficient":[152],"recognition.":[155]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}