{"id":"https://openalex.org/W4416840777","doi":"https://doi.org/10.1109/iccv51701.2025.02054","title":"Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval Via Uncertainty Minimization","display_name":"Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval Via Uncertainty Minimization","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416840777","doi":"https://doi.org/10.1109/iccv51701.2025.02054"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02054","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.15504","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056361720","display_name":"Bingqing Zhang","orcid":"https://orcid.org/0000-0001-8909-8857"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Bingqing Zhang","raw_affiliation_strings":["The University of Queensland,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland,Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110703680","display_name":"Zhuo Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhuo Cao","raw_affiliation_strings":["The University of Queensland,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland,Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069395028","display_name":"Heming Du","orcid":"https://orcid.org/0000-0002-7391-0449"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Heming Du","raw_affiliation_strings":["The University of Queensland,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland,Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018588825","display_name":"Yang Li","orcid":"https://orcid.org/0000-0002-4268-4004"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["CSIRO Data61,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSIRO Data61,Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019766244","display_name":"Xue Li","orcid":"https://orcid.org/0000-0001-7089-8045"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xue Li","raw_affiliation_strings":["The University of Queensland,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland,Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039989215","display_name":"Jiajun Liu","orcid":"https://orcid.org/0000-0001-8160-1796"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiajun Liu","raw_affiliation_strings":["CSIRO Data61,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSIRO Data61,Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115602108","display_name":"Sen Wang","orcid":"https://orcid.org/0009-0005-2988-4510"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sen Wang","raw_affiliation_strings":["The University of Queensland,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland,Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"22120","last_page":"22130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9735999703407288,"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":0.9735999703407288,"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/T11439","display_name":"Video Analysis and Summarization","score":0.012299999594688416,"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":0.00430000014603138,"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/ambiguity","display_name":"Ambiguity","score":0.6654999852180481},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5551999807357788},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5317999720573425},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4115999937057495},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.37290000915527344},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.33559998869895935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764999866485596},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6654999852180481},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5551999807357788},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5317999720573425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41499999165534973},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40610000491142273},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40459999442100525},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3792000114917755},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02054","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:2507.15504","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15504","pdf_url":"https://arxiv.org/pdf/2507.15504","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.15504","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.15504","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":"pmh:oai:arXiv.org:2507.15504","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15504","pdf_url":"https://arxiv.org/pdf/2507.15504","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":"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":{"Despite":[0],"recent":[1],"advances,":[2],"Text-to-video":[3],"retrieval":[4,123],"(TVR)":[5],"is":[6],"still":[7],"hindered":[8],"by":[9,34,59,112],"multiple":[10,128],"inherent":[11],"uncertainties,":[12,54],"such":[13],"as":[14],"ambiguous":[15],"textual":[16],"queries,":[17,120],"indistinct":[18],"text-video":[19],"mappings,":[20],"and":[21,80,98],"low-quality":[22],"video":[23],"frames.":[24],"Although":[25],"interactive":[26,141,153],"systems":[27],"have":[28],"emerged":[29],"to":[30],"address":[31],"these":[32,53,113],"challenges":[33],"refining":[35],"user":[36,119],"intent":[37],"through":[38],"clarifying":[39,109],"questions,":[40],"current":[41],"methods":[42],"typically":[43],"rely":[44],"on":[45,127,143],"heuristic":[46],"or":[47],"ad-hoc":[48],"strategies":[49],"without":[50],"explicitly":[51,72],"quantifying":[52],"limiting":[55],"their":[56],"effectiveness.":[57],"Motivated":[58],"this":[60],"gap,":[61],"we":[62],"propose":[63],"UMIVR,":[64],"an":[65,149],"Uncertainty-Minimizing":[66],"Interactive":[67],"Text-to-Video":[68],"Retrieval":[69],"framework":[70],"that":[71],"quantifies":[73],"three":[74],"critical":[75],"uncertainties-text":[76],"ambiguity,":[77],"mapping":[78],"uncertainty,":[79],"frame":[81],"uncertainty-via":[82],"principled,":[83],"training-free":[84],"metrics:":[85],"semantic":[86],"entropy-based":[87],"Text":[88],"Ambiguity":[89],"Score":[90,96],"(TAS),":[91],"Jensen-Shannon":[92],"divergence-based":[93],"Mapping":[94],"Uncertainty":[95],"(MUS),":[97],"a":[99],"Temporal":[100],"Quality-based":[101],"Frame":[102],"Sampler":[103],"(TQFS).":[104],"By":[105],"adaptively":[106],"generating":[107],"targeted":[108],"questions":[110],"guided":[111],"uncertainty":[114],"measures,":[115],"UMIVR":[116],"iteratively":[117],"refines":[118],"significantly":[121],"reducing":[122],"ambiguity.":[124],"Extensive":[125],"experiments":[126],"benchmarks":[129],"validate":[130],"UMIVR's":[131],"effectiveness,":[132],"achieving":[133],"notable":[134],"gains":[135],"in":[136],"Recall@1":[137],"(69.2\\%":[138],"after":[139],"10":[140],"rounds)":[142],"the":[144],"MSR-VTT-1k":[145],"dataset,":[146],"thereby":[147],"establishing":[148],"uncertainty-minimizing":[150],"foundation":[151],"for":[152],"TVR.":[154]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
