{"id":"https://openalex.org/W4414360158","doi":"https://doi.org/10.24963/ijcai.2025/180","title":"Denoise-then-Retrieve: Text-Conditioned Video Denoising for Video Moment Retrieval","display_name":"Denoise-then-Retrieve: Text-Conditioned Video Denoising for Video Moment Retrieval","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360158","doi":"https://doi.org/10.24963/ijcai.2025/180"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/180","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5083386240","display_name":"Weijia Liu","orcid":"https://orcid.org/0000-0002-0089-234X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weijia Liu","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012384188","display_name":"Jiuxin Cao","orcid":"https://orcid.org/0000-0002-2448-6717"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiuxin Cao","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039119622","display_name":"Bo Miao","orcid":"https://orcid.org/0000-0002-3025-4429"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Bo Miao","raw_affiliation_strings":["The University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091270095","display_name":"Zhiheng Fu","orcid":"https://orcid.org/0000-0002-3818-5659"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiheng Fu","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076214561","display_name":"Xuelin Zhu","orcid":"https://orcid.org/0000-0001-7676-2843"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xuelin Zhu","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018527272","display_name":"Jiawei Ge","orcid":"https://orcid.org/0000-0001-7268-7815"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiawei Ge","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461575","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0001-5209-9063"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086025266","display_name":"Mehwish Nasim","orcid":"https://orcid.org/0000-0003-0683-9125"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mehwish Nasim","raw_affiliation_strings":["The University of Western Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Western Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089986388","display_name":"Ajmal Mian","orcid":"https://orcid.org/0000-0002-5206-3842"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ajmal Mian","raw_affiliation_strings":["The University of Western Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Western Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":2,"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":"1612","last_page":"1620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9994000196456909,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9994000196456909,"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":0.9988999962806702,"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":0.9984999895095825,"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/encode","display_name":"ENCODE","score":0.7328000068664551},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6800000071525574},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6261000037193298},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.6168000102043152},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5023999810218811},{"id":"https://openalex.org/keywords/video-denoising","display_name":"Video denoising","score":0.49300000071525574},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4083999991416931},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.34209999442100525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766000032424927},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.7328000068664551},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6800000071525574},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6261000037193298},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.6168000102043152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.595300018787384},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5170000195503235},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5023999810218811},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.49300000071525574},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4083999991416931},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.33869999647140503},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C2778598663","wikidata":"https://www.wikidata.org/wiki/Q1407599","display_name":"Video content analysis","level":4,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2025/180","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/b1654000-3282-4aaf-9c39-4dcc60ed8d51","is_oa":false,"landing_page_url":"https://admin.research-repository.uwa.edu.au/en/publications/b1654000-3282-4aaf-9c39-4dcc60ed8d51","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Liu, W, Cao, J, Miao, B, Fu, Z, Zhu, X, Ge, J, Liu, B, Nasim, M & Mian, A 2025, Denoise-then-Retrieve : Text-Conditioned Video Denoising for Video Moment Retrieval. in J Kwok (ed.), Proceedings of the 34th International Joint Conference on Artificial Intelligence, IJCAI 2025. IJCAI International Joint Conference on Artificial Intelligence, International Joint Conferences on Artificial Intelligence, pp. 1612-1620, 34th Internationa Joint Conference on Artificial Intelligence, IJCAI 2025, Montreal, Canada, 16/08/25. https://doi.org/10.24963/ijcai.2025/180","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"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":{"Current":[0],"text-driven":[1],"Video":[2],"Moment":[3],"Retrieval":[4],"(VMR)":[5],"methods":[6,138],"encode":[7],"all":[8,140],"video":[9,84,95,122],"clips,":[10],"including":[11],"irrelevant":[12],"ones,":[13],"disrupting":[14],"multimodal":[15,43,83],"alignment":[16],"and":[17,35,58,66,76,97,130,148],"hindering":[18],"optimization.":[19],"To":[20],"this":[21,46],"end,":[22],"we":[23,48,113],"propose":[24],"a":[25,78,89],"denoise-then-retrieve":[26,144],"paradigm":[27,145],"that":[28,133],"explicitly":[29],"filters":[30],"text-irrelevant":[31],"clips":[32,75],"from":[33,93],"videos":[34],"then":[36],"retrieves":[37],"the":[38,50,101],"target":[39],"moment":[40],"using":[41,117],"purified":[42,94,121],"representations.":[44,85],"Following":[45],"paradigm,":[47],"introduce":[49],"Denoise-then-Retrieve":[51],"Network":[52],"(DRNet),":[53],"comprising":[54],"Text-Conditioned":[55],"Denoising":[56],"(TCD)":[57],"Text-Reconstruction":[59],"Feedback":[60],"(TRF)":[61],"modules.":[62],"TCD":[63],"integrates":[64],"cross-attention":[65],"structured":[67],"state":[68],"space":[69],"blocks":[70],"to":[71,81,157],"dynamically":[72],"identify":[73],"noisy":[74],"produce":[77],"noise":[79],"mask":[80],"purify":[82],"TRF":[86],"further":[87],"distills":[88],"single":[90],"query":[91],"embedding":[92],"representations":[96,123],"aligns":[98],"it":[99],"with":[100],"text":[102,118],"embedding,":[103],"serving":[104],"as":[105],"auxiliary":[106],"supervision":[107],"for":[108,124],"denoising":[109],"during":[110],"training.":[111],"Finally,":[112],"perform":[114],"conditional":[115],"retrieval":[116],"embeddings":[119],"on":[120,128,139],"accurate":[125],"VMR.":[126],"Experiments":[127],"Charades-STA":[129],"QVHighlights":[131],"demonstrate":[132],"our":[134,143],"approach":[135],"surpasses":[136],"state-of-the-art":[137],"metrics.":[141],"Furthermore,":[142],"is":[146],"adaptable":[147],"can":[149],"be":[150],"seamlessly":[151],"integrated":[152],"into":[153],"advanced":[154],"VMR":[155],"models":[156],"boost":[158],"performance.":[159]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}