{"id":"https://openalex.org/W4408859120","doi":"https://doi.org/10.1109/access.2025.3555167","title":"Open-Vocabulary Action Localization With Iterative Visual Prompting","display_name":"Open-Vocabulary Action Localization With Iterative Visual Prompting","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408859120","doi":"https://doi.org/10.1109/access.2025.3555167"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3555167","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3555167","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3555167","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087791577","display_name":"Naoki Wake","orcid":"https://orcid.org/0000-0001-8278-2373"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naoki Wake","raw_affiliation_strings":["Applied Robotics Research, Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8278-2373","affiliations":[{"raw_affiliation_string":"Applied Robotics Research, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011238975","display_name":"Atsushi Kanehira","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atsushi Kanehira","raw_affiliation_strings":["Applied Robotics Research, Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0009-0005-0157-7500","affiliations":[{"raw_affiliation_string":"Applied Robotics Research, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035650290","display_name":"Kazuhiro Sasabuchi","orcid":"https://orcid.org/0000-0002-5408-3089"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kazuhiro Sasabuchi","raw_affiliation_strings":["Applied Robotics Research, Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5408-3089","affiliations":[{"raw_affiliation_string":"Applied Robotics Research, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047085140","display_name":"Jun Takamatsu","orcid":"https://orcid.org/0000-0001-7457-2878"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Takamatsu","raw_affiliation_strings":["Applied Robotics Research, Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7457-2878","affiliations":[{"raw_affiliation_string":"Applied Robotics Research, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210116723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016258462","display_name":"Katsushi Ikeuchi","orcid":"https://orcid.org/0000-0001-9758-9357"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katsushi Ikeuchi","raw_affiliation_strings":["Applied Robotics Research, Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9758-9357","affiliations":[{"raw_affiliation_string":"Applied Robotics Research, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210116723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.5295,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59869969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"13","issue":null,"first_page":"56908","last_page":"56917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9909999966621399,"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":0.9909999966621399,"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":0.978600025177002,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9779000282287598,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/computer-science","display_name":"Computer science","score":0.7630289793014526},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6665158271789551},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5327496528625488},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4840778410434723},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.473732590675354},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3693746328353882},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3320053219795227},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1256508231163025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630289793014526},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6665158271789551},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5327496528625488},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4840778410434723},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.473732590675354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3693746328353882},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3320053219795227},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1256508231163025},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3555167","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3555167","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:35aa2e90b4dd4338ba3d27b8c2930b58","is_oa":true,"landing_page_url":"https://doaj.org/article/35aa2e90b4dd4338ba3d27b8c2930b58","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 56908-56917 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3555167","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3555167","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1564419424","https://openalex.org/W2099614498","https://openalex.org/W2471143248","https://openalex.org/W2597958930","https://openalex.org/W2625366777","https://openalex.org/W2950534130","https://openalex.org/W2951866553","https://openalex.org/W2962677524","https://openalex.org/W2962876901","https://openalex.org/W2963247196","https://openalex.org/W2963722382","https://openalex.org/W2964214371","https://openalex.org/W2964216549","https://openalex.org/W2964274041","https://openalex.org/W2965102465","https://openalex.org/W2983918066","https://openalex.org/W2995113766","https://openalex.org/W2997706915","https://openalex.org/W3021013305","https://openalex.org/W3047062112","https://openalex.org/W3114148117","https://openalex.org/W3120214499","https://openalex.org/W3128626728","https://openalex.org/W3128894241","https://openalex.org/W3135889196","https://openalex.org/W3174569083","https://openalex.org/W3174700686","https://openalex.org/W3206798507","https://openalex.org/W4211008118","https://openalex.org/W4220879577","https://openalex.org/W4312322722","https://openalex.org/W4312508181","https://openalex.org/W4313194685","https://openalex.org/W4385800691","https://openalex.org/W4386076085","https://openalex.org/W4386076331","https://openalex.org/W4386320380","https://openalex.org/W4390874578","https://openalex.org/W4391547487","https://openalex.org/W4393148288","https://openalex.org/W4396594800","https://openalex.org/W4400527535","https://openalex.org/W4401194599","https://openalex.org/W4402733565","https://openalex.org/W4403277141","https://openalex.org/W6726711304","https://openalex.org/W6744281239","https://openalex.org/W6751638542","https://openalex.org/W6755131278","https://openalex.org/W6783470697","https://openalex.org/W6785234230","https://openalex.org/W6791353385","https://openalex.org/W6810515469","https://openalex.org/W6849948229","https://openalex.org/W6850826453","https://openalex.org/W6861319346","https://openalex.org/W6865118152","https://openalex.org/W6867851394","https://openalex.org/W6870220196","https://openalex.org/W6870988953"],"related_works":["https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W2900827440","https://openalex.org/W3167549738","https://openalex.org/W2381983017"],"abstract_inverted_index":{"Video":[0],"action":[1,144],"localization":[2],"aims":[3],"to":[4,58,95,103,125,141],"find":[5],"the":[6,51,97,104,109,114,118,121,149],"timings":[7],"of":[8,108,151],"specific":[9],"actions":[10],"from":[11,50],"a":[12,29,36,85,93,154],"long":[13,60],"video.":[14],"Although":[15],"existing":[16],"learning-based":[17],"approaches":[18],"have":[19],"been":[20],"successful,":[21],"they":[22],"require":[23],"annotating":[24],"videos,":[25],"which":[26],"comes":[27],"with":[28,88],"considerable":[30],"labor":[31],"cost.":[32],"This":[33],"paper":[34],"proposes":[35],"training-free,":[37],"open-vocabulary":[38],"approach":[39],"based":[40],"on":[41],"emerging":[42],"off-the-shelf":[43],"vision-language":[44],"models":[45],"(VLMs).":[46],"The":[47],"challenge":[48],"stems":[49],"fact":[52],"that":[53,99,132],"VLMs":[54,152],"are":[55],"neither":[56],"designed":[57],"process":[59],"videos":[61],"nor":[62],"tailored":[63],"for":[64,157],"finding":[65],"actions.":[66],"We":[67,130],"overcome":[68],"these":[69],"problems":[70],"by":[71],"extending":[72],"an":[73],"iterative":[74],"visual":[75],"prompting":[76],"technique.":[77],"Specifically,":[78],"we":[79],"sample":[80],"video":[81],"frames":[82,98],"and":[83,106],"create":[84],"concatenated":[86],"image":[87],"frame":[89],"index":[90],"labels,":[91],"allowing":[92],"VLM":[94],"identify":[96],"most":[100],"likely":[101],"correspond":[102],"start":[105],"end":[107],"action.":[110],"By":[111],"iteratively":[112],"narrowing":[113],"sampling":[115],"window":[116],"around":[117],"selected":[119],"frames,":[120],"estimation":[122],"gradually":[123],"converges":[124],"more":[126],"precise":[127],"temporal":[128],"boundaries.":[129],"demonstrate":[131],"this":[133],"technique":[134],"yields":[135],"reasonable":[136],"performance,":[137],"achieving":[138],"results":[139,147],"comparable":[140],"state-of-the-art":[142],"zero-shot":[143],"localization.":[145],"These":[146],"support":[148],"use":[150],"as":[153],"practical":[155],"tool":[156],"understanding":[158],"videos.":[159],"Sample":[160],"code":[161],"is":[162],"available":[163],"at":[164],"(https://microsoft.github.io/VLM-Video-Action-Localization/).":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}