{"id":"https://openalex.org/W7214366018","doi":"https://doi.org/10.48550/arxiv.2609.29121","title":"Less is More: Encoder-only Audio-Visual Segmentation","display_name":"Less is More: Encoder-only Audio-Visual Segmentation","publication_year":2026,"publication_date":"2026-09-24","ids":{"openalex":"https://openalex.org/W7214366018","doi":"https://doi.org/10.48550/arxiv.2609.29121"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.29121","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29121","pdf_url":"https://arxiv.org/pdf/2609.29121","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.29121","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114412356","display_name":"Ilpo Viertola","orcid":"https://orcid.org/0009-0006-2361-8067","observed_orcids":["https://orcid.org/0009-0006-2361-8067"]},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Viertola, Ilpo","raw_affiliation_strings":["Tampere University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008909874","display_name":"Vladimir Iashin","orcid":"https://orcid.org/0000-0001-8879-587X","observed_orcids":["https://orcid.org/0000-0001-8879-587X"]},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Iashin, Vladimir","raw_affiliation_strings":["Tampere University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132692723","display_name":"Sophie T\u00f6tterstr\u00f6m","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"T\u00f6tterstr\u00f6m, Sophie","raw_affiliation_strings":["Tampere University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088180438","display_name":"Esa Rahtu","orcid":"https://orcid.org/0000-0001-8767-0864","observed_orcids":["https://orcid.org/0000-0001-8767-0864"]},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Rahtu, Esa","raw_affiliation_strings":["Tampere University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"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/T11309","display_name":"Music and Audio Processing","score":0.5151000022888184,"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":0.5151000022888184,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.3495999872684479,"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/T10860","display_name":"Speech and Audio Processing","score":0.05130000039935112,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer-based-segmentation","display_name":"transformer-based segmentation","score":0.4869999885559082},{"id":"https://openalex.org/keywords/model-redundancy","display_name":"model redundancy","score":0.3540000021457672},{"id":"https://openalex.org/keywords/real-time-video-processing","display_name":"real-time video processing","score":0.7379999756813049}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8252000212669373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6934000253677368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6917999982833862},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6351000070571899},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.6309999823570251},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6098999977111816},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.5220000147819519},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2808000147342682}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.29121","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29121","pdf_url":"https://arxiv.org/pdf/2609.29121","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2609.29121","doi":"https://doi.org/10.48550/arxiv.2609.29121","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.29121","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.29121","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29121","pdf_url":"https://arxiv.org/pdf/2609.29121","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214366018.pdf","grobid_xml":"https://content.openalex.org/works/W7214366018.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4406489090","https://openalex.org/W4400254188","https://openalex.org/W4407374920","https://openalex.org/W7160948131","https://openalex.org/W7172032785","https://openalex.org/W4376632581","https://openalex.org/W7160337146","https://openalex.org/W4393160420","https://openalex.org/W4394625876","https://openalex.org/W4387969495"],"abstract_inverted_index":{"Audio-Visual":[0,51],"Semantic":[1],"Segmentation":[2,52],"(AVSS)":[3],"aims":[4],"to":[5,41,58],"identify,":[6],"segment,":[7],"and":[8,72,87,99,108,114],"classify":[9],"sound-emitting":[10],"objects":[11],"in":[12,74],"video":[13],"frames.":[14],"Previous":[15],"Transformer-based":[16],"AVSS":[17,82,94],"approaches":[18],"largely":[19],"inherit":[20],"design":[21],"principles":[22],"from":[23],"image":[24,32],"segmentation":[25,33,43],"models.":[26],"Recent":[27],"studies":[28],"show":[29],"that":[30,38,93],"these":[31],"models":[34,68],"contain":[35],"redundant":[36],"components":[37],"contribute":[39],"little":[40],"the":[42],"performance.":[44],"Following":[45],"this":[46],"insight,":[47],"we":[48,79],"propose":[49],"Encoder-only":[50],"(EASE).":[53],"EASE":[54],"runs":[55],"at":[56,69,118],"up":[57],"365":[59],"FPS,":[60],"3x":[61],"faster":[62],"than":[63],"prior":[64],"State-of-the-Art":[65],"(SotA)":[66],"AVS":[67],"comparable":[70],"accuracy,":[71],"trains":[73],"under":[75],"11":[76],"GPU-hours.":[77],"Furthermore,":[78],"achieve":[80],"SotA":[81],"performance":[83],"across":[84],"different":[85],"backbones":[86],"input":[88],"resolutions.":[89],"Our":[90],"results":[91],"demonstrate":[92],"can":[95],"be":[96],"both":[97],"simpler":[98],"faster,":[100],"providing":[101],"a":[102],"scalable":[103],"foundation":[104],"for":[105],"future":[106],"research":[107],"real-time":[109],"applications.":[110],"Code,":[111],"model":[112],"weights,":[113],"samples":[115],"are":[116],"available":[117],"https://ease-avs.notion.site":[119]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-26T00:00:00"}