{"id":"https://openalex.org/W7224414723","doi":"https://doi.org/10.18653/2026.emnlp-main.238","title":"Learning to Reason Before Masking for Referring Audio-Visual Segmentation","display_name":"Learning to Reason Before Masking for Referring Audio-Visual Segmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7224414723","doi":"https://doi.org/10.18653/2026.emnlp-main.238"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.238","doi":"https://doi.org/10.18653/2026.emnlp-main.238","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.238","pdf_url":"https://aclanthology.org/2026.emnlp-main.238.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.238.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160145584","display_name":"Zhixuan Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":"CN","type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixuan Wu","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology , Beijing University of Posts and Telecommunications ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology , Beijing University of Posts and Telecommunications ,","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128453277","display_name":"Ye Ni","orcid":"https://orcid.org/0009-0002-4411-3325","observed_orcids":["https://orcid.org/0009-0002-4411-3325"]},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Ni","raw_affiliation_strings":["Southeast University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University ,","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160077408","display_name":"Yiming Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I119045251","display_name":"Huaqiao University","ror":"https://ror.org/03frdh605","country_code":"CN","type":"education","lineage":["https://openalex.org/I119045251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Chen","raw_affiliation_strings":["Huaqiao University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huaqiao University","institution_ids":["https://openalex.org/I119045251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133870799","display_name":"Wenyuan Gu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":"CN","type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyuan Gu","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology , Beijing University of Posts and Telecommunications ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology , Beijing University of Posts and Telecommunications ,","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160096879","display_name":"Bo Cheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":"CN","type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Cheng","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology , Beijing University of Posts and Telecommunications ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology , Beijing University of Posts and Telecommunications ,","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81083506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5446","last_page":"5464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0,"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/implicit-references","display_name":"implicit references","score":0.7139999866485596},{"id":"https://openalex.org/keywords/multi-hop-reasoning","display_name":"multi-hop reasoning","score":0.7379999756813049},{"id":"https://openalex.org/keywords/multimodal-reasoning","display_name":"multimodal reasoning","score":0.4259999990463257},{"id":"https://openalex.org/keywords/crossmodal-correspondences","display_name":"cross-modal correspondence","score":0.6460000276565552}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6478999853134155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5946999788284302},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5888000130653381},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5392000079154968},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40389999747276306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/2026.emnlp-main.238","doi":"https://doi.org/10.18653/2026.emnlp-main.238","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.238","pdf_url":"https://aclanthology.org/2026.emnlp-main.238.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-main.238","doi":"https://doi.org/10.18653/2026.emnlp-main.238","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.238","pdf_url":"https://aclanthology.org/2026.emnlp-main.238.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2218334274","display_name":null,"funder_award_id":"Grant No. 62372058","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G482571221","display_name":null,"funder_award_id":"62372058","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224414723.pdf","grobid_xml":"https://content.openalex.org/works/W7224414723.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W4388718054","https://openalex.org/W4404330874","https://openalex.org/W4415037432","https://openalex.org/W4415255153","https://openalex.org/W4416074917","https://openalex.org/W4417095222","https://openalex.org/W6948487963","https://openalex.org/W6967068517","https://openalex.org/W7147655908"],"related_works":["https://openalex.org/W7222951474","https://openalex.org/W7128073538","https://openalex.org/W7223566715","https://openalex.org/W6968250076","https://openalex.org/W7166865432","https://openalex.org/W4402112298","https://openalex.org/W4385823492","https://openalex.org/W7169850685","https://openalex.org/W2912290468","https://openalex.org/W6979246345"],"abstract_inverted_index":{"Existing":[0],"referring":[1,72,167],"Audio-Visual":[2],"Segmentation":[3],"(Ref-AVS)":[4],"benchmarks":[5],"primarily":[6],"focus":[7],"on":[8,92],"explicit":[9],"expressions":[10],"whose":[11],"referents":[12],"can":[13],"be":[14],"resolved":[15],"through":[16],"direct":[17,99],"visual,":[18],"acoustic,":[19],"or":[20],"linguistic":[21],"correspondence.Consequently,":[22],"they":[23],"provide":[24],"limited":[25],"coverage":[26],"of":[27,88,153],"implicit":[28],"references":[29,143],"that":[30,47,123,135],"require":[31],"multi-step":[32],"reasoning":[33,79,83,86],"over":[34],"multimodal":[35,74,109,164],"evidence.To":[36],"bridge":[37],"this":[38],"gap,":[39],"we":[40,117],"introduce":[41],"Reasoning":[42],"Ref-AVS,":[43],"a":[44,66,105],"new":[45],"task":[46],"requires":[48],"models":[49,91],"to":[50,155],"infer":[51],"the":[52,151,161],"referred":[53],"object":[54,76],"from":[55],"audio-visual-language":[56],"cues":[57],"before":[58,157],"generating":[59],"its":[60],"segmentation":[61,139],"mask.We":[62],"further":[63],"construct":[64],"ReAVS,":[65],"comprehensive":[67],"dataset":[68],"with":[69],"manually":[70],"annotated":[71],"expressions,":[73],"cues,":[75],"masks,":[77],"and":[78,111,130,144,166],"chains,":[80],"covering":[81],"diverse":[82,85],"spanning":[84],"patterns.Evaluations":[87],"representative":[89],"Ref-AVS":[90],"ReAVS":[93],"reveal":[94],"substantial":[95],"performance":[96,140],"degradation":[97],"when":[98],"cross-modal":[100],"correspondence":[101],"is":[102],"insufficient,":[103],"exposing":[104],"clear":[106],"gap":[107,162],"between":[108,163],"recognition":[110,165],"referent":[112],"reasoning.Motivated":[113],"by":[114],"these":[115],"challenges,":[116],"propose":[118],"Re2Seg,":[119],"an":[120],"omni-modal":[121],"framework":[122],"performs":[124],"object-centric":[125],"evidence":[126],"encoding,":[127],"multi-hop":[128],"reasoning,":[129],"reasoningconditioned":[131],"mask":[132],"decoding.Experiments":[133],"demonstrate":[134],"Re2Seg":[136],"achieves":[137],"stronger":[138],"under":[141],"reasoningintensive":[142],"provides":[145],"interpretable":[146],"object-inference":[147],"traces.These":[148],"results":[149],"highlight":[150],"importance":[152],"learning":[154],"reason":[156],"masking":[158],"for":[159],"bridging":[160],"segmentation.":[168]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-30T00:00:00"}