{"id":"https://openalex.org/W4413277857","doi":"https://doi.org/10.1109/icip55913.2025.11084490","title":"Audio Visual Segmentation through Text Embeddings","display_name":"Audio Visual Segmentation through Text Embeddings","publication_year":2025,"publication_date":"2025-08-18","ids":{"openalex":"https://openalex.org/W4413277857","doi":"https://doi.org/10.1109/icip55913.2025.11084490"},"language":"en","primary_location":{"id":"doi:10.1109/icip55913.2025.11084490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084490","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/A5106083359","display_name":"Kyung\u2010Bok Lee","orcid":"https://orcid.org/0000-0003-1495-3462"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyungbok Lee","raw_affiliation_strings":["University of Rochester,Department of Computer Science,Rochester,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Computer Science,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101904472","display_name":"You Zhang","orcid":"https://orcid.org/0000-0002-9599-2676"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"You Zhang","raw_affiliation_strings":["University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102749436","display_name":"Zhiyao Duan","orcid":"https://orcid.org/0000-0002-8334-9974"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyao Duan","raw_affiliation_strings":["University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23578683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2510","last_page":"2515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9610000252723694,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9192000031471252,"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":0.7354080677032471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7228096723556519},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5810238122940063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.520818829536438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.480797678232193},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4146125018596649},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4137554168701172},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4043188691139221},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.28719818592071533}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7354080677032471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7228096723556519},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5810238122940063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.520818829536438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.480797678232193},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4146125018596649},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4137554168701172},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4043188691139221},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.28719818592071533}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip55913.2025.11084490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip55913.2025.11084490","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2251512949","https://openalex.org/W2489434015","https://openalex.org/W2962865004","https://openalex.org/W2963115079","https://openalex.org/W2964284374","https://openalex.org/W3170088426","https://openalex.org/W4313123347","https://openalex.org/W4372266552","https://openalex.org/W4386071687","https://openalex.org/W4387969151","https://openalex.org/W4387969495","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4393160420","https://openalex.org/W4394625876","https://openalex.org/W4402727436","https://openalex.org/W4402917127"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W1522196789"],"abstract_inverted_index":{"The":[0,175],"goal":[1],"of":[2,30,41,81,91,117,147],"Audio-Visual":[3],"Segmentation":[4],"(AVS)":[5],"is":[6,178],"to":[7,26,37,58,62,132],"localize":[8],"and":[9,149,171],"segment":[10,63],"the":[11,27,39,46,71,88,113,162],"sounding":[12,64],"source":[13,65,176],"objects":[14],"from":[15,22,127],"video":[16],"frames.":[17],"Research":[18],"on":[19,74,161],"AVS":[20],"suffers":[21],"data":[23,43],"scarcity":[24],"due":[25],"high":[28],"cost":[29],"fine-grained":[31],"manual":[32],"annotations.":[33],"Recent":[34],"works":[35],"attempt":[36],"overcome":[38],"challenge":[40,90],"limited":[42,96],"by":[44,78,165],"leveraging":[45],"vision":[47],"foundation":[48],"model,":[49],"Segment":[50],"Anything":[51],"Model":[52],"(SAM),":[53],"prompting":[54],"it":[55,84],"with":[56,95,112],"audio":[57,110,148],"enhance":[59,133],"its":[60],"ability":[61],"objects.":[66],"While":[67],"this":[68,100],"approach":[69,157],"alleviates":[70],"model\u2019s":[72],"burden":[73],"understanding":[75],"visual":[76,150],"modality":[77],"utilizing":[79,167],"knowledge":[80],"pre-trained":[82,118,168],"SAM,":[83],"does":[85],"not":[86],"address":[87,99],"fundamental":[89],"learning":[92],"audio-visual":[93,134],"correspondence":[94,125],"data.":[97],"To":[98],"limitation,":[101],"we":[102,137],"propose":[103],"AV2T-SAM,":[104],"a":[105,139],"novel":[106,140],"framework":[107],"that":[108],"bridges":[109],"features":[111],"text":[114],"embedding":[115],"space":[116],"text-prompted":[119],"SAM.":[120],"Our":[121,156],"method":[122],"leverages":[123],"multimodal":[124],"learned":[126],"rich":[128],"text-image":[129],"paired":[130],"datasets":[131],"alignment.":[135,174],"Furthermore,":[136],"introduce":[138],"feature,":[141],"fCLIP\u2299fCLAP,":[142],"which":[143],"emphasizes":[144],"shared":[145],"semantics":[146],"modalities":[151],"while":[152],"filtering":[153],"irrelevant":[154],"noise.":[155],"outperforms":[158],"existing":[159],"methods":[160],"AVSBench":[163],"dataset":[164],"effectively":[166],"segmentation":[169],"models":[170],"cross-modal":[172],"semantic":[173],"code":[177],"released":[179],"at":[180],"https://github.com/bok-bok/AV2T-SAM.":[181]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}