{"id":"https://openalex.org/W4413277988","doi":"https://doi.org/10.1109/icip55913.2025.11084533","title":"Clip-Ae: Clip-Assisted Cross-View Audio-Visual Enhancement for Unsupervised Temporal Action Localization","display_name":"Clip-Ae: Clip-Assisted Cross-View Audio-Visual Enhancement for Unsupervised Temporal Action Localization","publication_year":2025,"publication_date":"2025-08-18","ids":{"openalex":"https://openalex.org/W4413277988","doi":"https://doi.org/10.1109/icip55913.2025.11084533"},"language":"en","primary_location":{"id":"doi:10.1109/icip55913.2025.11084533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP)","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/A5101640515","display_name":"Rui Xia","orcid":"https://orcid.org/0000-0002-6899-6735"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xia","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014629661","display_name":"Dan Jiang","orcid":"https://orcid.org/0000-0003-4735-479X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Jiang","raw_affiliation_strings":["Tsinghua University,School of Vehicle and Mobility,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Vehicle and Mobility,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406666","display_name":"Quan Zhang","orcid":"https://orcid.org/0000-0001-7778-4243"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Zhang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078138280","display_name":"Ke Zhang","orcid":"https://orcid.org/0000-0003-1354-4886"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Zhang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101456902","display_name":"Chun Yuan","orcid":"https://orcid.org/0000-0002-3590-6676"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Yuan","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23599623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2014","last_page":"2018"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9779999852180481,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9728000164031982,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/audio-visual","display_name":"Audio visual","score":0.7488341927528381},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.743360698223114},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5679295659065247},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47428780794143677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45495831966400146},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41566604375839233},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.15059897303581238}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7488341927528381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743360698223114},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5679295659065247},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47428780794143677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45495831966400146},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41566604375839233},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.15059897303581238},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip55913.2025.11084533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2962709777","https://openalex.org/W2984619425","https://openalex.org/W3035524964","https://openalex.org/W3109715102","https://openalex.org/W4292971825","https://openalex.org/W4320921197","https://openalex.org/W4386066210","https://openalex.org/W4386076071","https://openalex.org/W4390873021","https://openalex.org/W4393154133","https://openalex.org/W4402660085","https://openalex.org/W4409346508","https://openalex.org/W4409364989","https://openalex.org/W4409365836"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Temporal":[0],"Action":[1],"Localization":[2],"(TAL)":[3],"has":[4,37],"garnered":[5],"significant":[6],"attention":[7],"in":[8],"information":[9,63],"retrieval.":[10],"Existing":[11],"supervised":[12,15],"or":[13],"weakly":[14],"methods":[16,42],"heavily":[17],"rely":[18],"on":[19,53,60,100,133],"labeled":[20],"temporal":[21,33],"boundaries":[22],"and":[23,29,91],"action":[24,34],"categories,":[25],"which":[26],"are":[27],"labor-intensive":[28],"time-consuming.":[30],"Consequently,":[31],"unsupervised":[32],"localization":[35],"(UTAL)":[36],"gained":[38],"popularity.":[39],"However,":[40],"current":[41],"face":[43],"two":[44,134],"main":[45],"challenges:":[46],"1)":[47],"Classification":[48],"pre-trained":[49],"features":[50],"overly":[51],"focus":[52,99],"highly":[54,101],"discriminative":[55,102],"regions;":[56,103],"2)":[57],"Solely":[58],"relying":[59],"visual":[61,87],"modality":[62],"makes":[64],"it":[65],"difficult":[66],"to":[67,96,109,123],"determine":[68],"contextual":[69,112],"boundaries.":[70],"To":[71],"address":[72],"these":[73],"issues,":[74],"we":[75,85,104,116],"propose":[76],"a":[77,118],"CLIP-assisted":[78],"cross-view":[79,120],"audio-visual":[80],"enhanced":[81],"UTAL":[82],"method.":[83],"Specifically,":[84],"introduce":[86,117],"language":[88],"pre-training":[89],"(VLP)":[90],"classification":[92],"pre-training-based":[93],"collaborative":[94],"enhancement":[95,127],"avoid":[97],"excessive":[98],"also":[105],"incorporate":[106],"audio":[107],"perception":[108],"provide":[110],"richer":[111],"boundary":[113],"information.":[114],"Finally,":[115],"self-supervised":[119],"learning":[121],"paradigm":[122],"achieve":[124],"multi-view":[125],"perceptual":[126],"without":[128],"additional":[129],"annotations.":[130],"Extensive":[131],"experiments":[132],"public":[135],"datasets":[136],"demonstrate":[137],"our":[138],"model\u2019s":[139],"superiority":[140],"over":[141],"several":[142],"state-of-the-art":[143],"competitors.":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}