{"id":"https://openalex.org/W4415428949","doi":"https://doi.org/10.3233/faia250846","title":"Planner-Refiner: Dynamic Space-Time Refinement for Vision-Language Alignment in Videos","display_name":"Planner-Refiner: Dynamic Space-Time Refinement for Vision-Language Alignment in Videos","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428949","doi":"https://doi.org/10.3233/faia250846"},"language":null,"primary_location":{"id":"doi:10.3233/faia250846","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250846","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia250846","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050515475","display_name":"Tuyen Tran","orcid":"https://orcid.org/0009-0002-8161-7637"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tuyen Tran","raw_affiliation_strings":["Applied Artificial Intelligence Institute, Deakin University, Australia"],"raw_orcid":"https://orcid.org/0009-0002-8161-7637","affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Institute, Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079045166","display_name":"Thao Minh Le","orcid":"https://orcid.org/0000-0002-8089-9962"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Thao Minh Le","raw_affiliation_strings":["Applied Artificial Intelligence Institute, Deakin University, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8089-9962","affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Institute, Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Quang-Hung Le","orcid":"https://orcid.org/0000-0003-4727-6859"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Quang-Hung Le","raw_affiliation_strings":["Applied Artificial Intelligence Institute, Deakin University, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4727-6859","affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Institute, Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085471517","display_name":"Truyen Tran","orcid":"https://orcid.org/0000-0001-6531-8907"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Truyen Tran","raw_affiliation_strings":["Applied Artificial Intelligence Institute, Deakin University, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6531-8907","affiliations":[{"raw_affiliation_string":"Applied Artificial Intelligence Institute, Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149704539"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62286625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9796000123023987,"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":0.9796000123023987,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9531999826431274,"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":0.9178000092506409,"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/semantic-gap","display_name":"Semantic gap","score":0.5577999949455261},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5047000050544739},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5004000067710876},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47769999504089355},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4683000147342682},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4675999879837036},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4512999951839447},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.4259999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8172000050544739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5920000076293945},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.5577999949455261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5094000101089478},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5047000050544739},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5004000067710876},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47769999504089355},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4675999879837036},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40799999237060547},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C2779525943","wikidata":"https://www.wikidata.org/wiki/Q1187300","display_name":"Grammaticality","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia250846","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250846","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia250846","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250846","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"alignment":[1,109,118],"in":[2],"video":[3],"must":[4],"address":[5],"the":[6,35,154],"complexity":[7],"of":[8],"language,":[9],"evolving":[10],"interacting":[11],"entities,":[12],"their":[13],"action":[14],"chains,":[15],"and":[16,21,75,124],"semantic":[17,36,49],"gaps":[18,50],"between":[19],"language":[20,47,57,129],"vision.":[22],"This":[23],"work":[24],"introduces":[25],"Planner-Refiner,":[26],"a":[27,134],"framework":[28],"to":[29,138],"overcome":[30],"these":[31,94,151],"challenges.":[32],"Planner-Refiner":[33],"bridges":[34],"gap":[37],"by":[38,46,59],"iteratively":[39],"refining":[40],"visual":[41,79,98],"elements\u2019":[42],"space-time":[43],"representation,":[44],"guided":[45],"until":[48],"are":[51],"minimal.":[52],"A":[53,90],"Planner":[54],"module":[55],"schedules":[56],"guidance":[58],"decomposing":[60],"complex":[61,159],"linguistic":[62],"prompts":[63],"into":[64,105],"short":[65,72],"sentence":[66],"chains.":[67],"The":[68,101],"Refiner":[69],"processes":[70],"each":[71],"sentence\u2014a":[73],"noun-phrase":[74],"verb-phrase":[76],"pair\u2014to":[77],"direct":[78],"tokens\u2019":[80],"self-attention":[81],"across":[82],"space":[83],"then":[84],"time,":[85],"achieving":[86],"efficient":[87],"single-step":[88],"refinement.":[89],"recurrent":[91],"system":[92],"chains":[93],"steps,":[95],"maintaining":[96],"refined":[97],"token":[99],"representations.":[100],"final":[102],"representation":[103],"feeds":[104],"task-specific":[106],"heads":[107],"for":[108,158],"generation.":[110],"We":[111,131],"demonstrate":[112],"Planner-Refiner\u2019s":[113],"effectiveness":[114],"on":[115,150],"two":[116],"video-language":[117],"tasks:":[119],"Referring":[120],"Video":[121],"Object":[122],"Segmentation":[123],"Temporal":[125],"Grounding":[126],"with":[127,142],"varying":[128],"complexity.":[130],"further":[132],"introduce":[133],"new":[135],"MeViS-X":[136],"benchmark":[137],"assess":[139],"models\u2019":[140],"capability":[141],"long":[143],"queries.":[144],"Superior":[145],"performance":[146],"versus":[147],"state-of-the-art":[148],"methods":[149],"benchmarks":[152],"shows":[153],"approach\u2019s":[155],"potential,":[156],"especially":[157],"prompts.":[160]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-24T00:00:00"}