{"id":"https://openalex.org/W4414930161","doi":"https://doi.org/10.1109/iccv51701.2025.02096","title":"Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation","display_name":"Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414930161","doi":"https://doi.org/10.1109/iccv51701.2025.02096"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02096","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/2507.22886","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090152810","display_name":"Kaining Ying","orcid":"https://orcid.org/0000-0003-2596-1847"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaining Ying","raw_affiliation_strings":["Fudan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036631624","display_name":"Henghui Ding","orcid":"https://orcid.org/0000-0003-4868-6526"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Henghui Ding","raw_affiliation_strings":["Fudan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119891860","display_name":"Guangquan Jie","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangquan Jie","raw_affiliation_strings":["Fudan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Fudan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"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":"22575","last_page":"22585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9842000007629395,"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/T12031","display_name":"Speech and dialogue systems","score":0.9758999943733215,"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/segmentation","display_name":"Segmentation","score":0.7615000009536743},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5680000185966492},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3910999894142151},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.3653999865055084},{"id":"https://openalex.org/keywords/inclusion","display_name":"Inclusion (mineral)","score":0.33160001039505005},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.32910001277923584}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7615000009536743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7477999925613403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.61080002784729},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5680000185966492},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37119999527931213},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C109359841","wikidata":"https://www.wikidata.org/wiki/Q728944","display_name":"Inclusion (mineral)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3163999915122986},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2721000015735626}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02096","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:2507.22886","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.22886","pdf_url":"https://arxiv.org/pdf/2507.22886","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.2507.22886","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.22886","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:2507.22886","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.22886","pdf_url":"https://arxiv.org/pdf/2507.22886","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":[{"id":"https://openalex.org/G3234540041","display_name":null,"funder_award_id":"62472104","funder_id":"https://openalex.org/F4320333688","funder_display_name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320333688","display_name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Referring":[0,40],"audio-visual":[1],"segmentation":[2],"(RAVS)":[3],"has":[4],"recently":[5],"seen":[6],"significant":[7],"advancements,":[8],"yet":[9],"challenges":[10,112],"remain":[11],"in":[12,34,99,122],"integrating":[13],"multimodal":[14,52,66,114],"information":[15],"and":[16,19,30,50,74,89,96,116,131,145],"deeply":[17],"understanding":[18,81,118],"reasoning":[20,95,115],"about":[21],"audiovisual":[22,120],"content.":[23],"To":[24],"extend":[25],"the":[26,91,111],"boundaries":[27],"of":[28,65,93,113,119],"RAVS":[29],"facilitate":[31],"future":[32],"research":[33],"this":[35],"field,":[36],"we":[37,102],"propose":[38],"Omnimodal":[39,104],"Audio-Visual":[41],"Segmentation":[42,106],"(OmniAVS),":[43],"a":[44],"new":[45],"dataset":[46],"containing":[47],"2,104":[48],"videos":[49],"61,095":[51],"referring":[53],"expressions.":[54,100],"OmniAVS":[55,144],"stands":[56],"out":[57],"with":[58],"three":[59],"key":[60],"innovations:":[61],"(1)":[62],"8":[63],"types":[64],"expressions":[67],"that":[68,138],"flexibly":[69],"combine":[70],"text,":[71],"speech,":[72],"sound,":[73],"visual":[75],"cues;":[76],"(2)":[77],"an":[78],"emphasis":[79],"on":[80,143,149],"audio":[82],"content":[83,121],"beyond":[84],"just":[85],"detecting":[86],"their":[87],"presence;":[88],"(3)":[90],"inclusion":[92],"complex":[94,129],"world":[97],"knowledge":[98],"Furthermore,":[101],"introduce":[103],"Instructed":[105],"Assistant":[107],"(OISA),":[108],"to":[109,127],"address":[110],"fine-grained":[117],"OmniAVS.":[123],"OISA":[124,139],"uses":[125],"MLLM":[126],"comprehend":[128],"cues":[130],"perform":[132],"reasoning-based":[133],"segmentation.":[134],"Extensive":[135],"experiments":[136],"show":[137],"outperforms":[140],"existing":[141],"methods":[142],"achieves":[146],"competitive":[147],"results":[148],"other":[150],"related":[151],"tasks.":[152]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}