{"id":"https://openalex.org/W7138076397","doi":"https://doi.org/10.1609/aaai.v40i16.38373","title":"Think Before You Segment: An Object-aware Reasoning Agent for Referring Audio-Visual Segmentation","display_name":"Think Before You Segment: An Object-aware Reasoning Agent for Referring Audio-Visual Segmentation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138076397","doi":"https://doi.org/10.1609/aaai.v40i16.38373"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i16.38373","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38373","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i16.38373","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047303316","display_name":"Jinxing Zhou","orcid":"https://orcid.org/0000-0001-6402-7593"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":true,"raw_author_name":"Jinxing Zhou","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125193553","display_name":"Yanghao Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yanghao Zhou","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129691854","display_name":"Mingfei Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Mingfei Han","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129700066","display_name":"Tong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Tong Wang","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129732420","display_name":"Xiaojun Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Xiaojun Chang","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence\nUniversity of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence\nUniversity of Science and Technology of China","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009362997","display_name":"Hisham Cholakkal","orcid":"https://orcid.org/0000-0002-8230-9065"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Hisham Cholakkal","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129650926","display_name":"Rao Muhammad Anwer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Rao Muhammad Anwer","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5047303316"],"corresponding_institution_ids":["https://openalex.org/I4210113480"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38059701,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"16","first_page":"13665","last_page":"13673"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7328000068664551,"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":0.7328000068664551,"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":0.0681999996304512,"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/T11309","display_name":"Music and Audio Processing","score":0.057500001043081284,"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/object","display_name":"Object (grammar)","score":0.6503000259399414},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6444000005722046},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6255999803543091},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6222000122070312},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6202999949455261},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5863999724388123},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3456000089645386},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.3061999976634979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047000169754028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6995000243186951},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6503000259399414},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6444000005722046},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6255999803543091},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6222000122070312},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6202999949455261},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5863999724388123},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3806999921798706},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3456000089645386},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.28999999165534973},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2632000148296356},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25699999928474426},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i16.38373","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38373","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i16.38373","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38373","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7207036018371582}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Referring":[0],"Audio-Visual":[1],"Segmentation":[2],"(Ref-AVS)":[3],"aims":[4],"to":[5,28],"segment":[6],"target":[7],"objects":[8],"in":[9],"audible":[10],"videos":[11],"based":[12],"on":[13,21,140,166],"given":[14],"reference":[15,50],"expressions.":[16],"Prior":[17],"works":[18],"typically":[19],"rely":[20],"learning":[22],"latent":[23],"embeddings":[24],"via":[25],"multimodal":[26,75,92],"fusion":[27],"prompt":[29,128],"a":[30,45,60,91,147],"tunable":[31],"SAM/SAM2":[32],"decoder":[33],"for":[34,114,129,156],"segmentation,":[35],"which":[36,55,133],"requires":[37],"strong":[38],"pixel-level":[39,141],"supervision":[40],"and":[41,81,101,131,136,153,170],"lacks":[42],"interpretability.":[43],"From":[44],"novel":[46],"perspective":[47],"of":[48,96],"explicit":[49,110,127],"understanding,":[51],"we":[52,87,144],"propose":[53,89],"TGS-Agent,":[54],"decomposes":[56],"the":[57,64,71],"task":[58],"into":[59],"Think-Ground-Segment":[61],"process,":[62],"mimicking":[63],"human":[65],"reasoning":[66,97],"procedure":[67],"by":[68,78,121],"first":[69,88],"identifying":[70],"referred":[72],"object":[73,118],"through":[74],"analysis,":[76],"followed":[77],"coarse-grained":[79],"grounding":[80,135],"precise":[82],"segmentation.":[83],"To":[84],"this":[85],"end,":[86],"Ref-Thinker,":[90],"language":[93],"model":[94,159],"capable":[95],"over":[98],"textual,":[99],"visual,":[100],"auditory":[102],"cues.":[103],"We":[104],"construct":[105],"an":[106,126],"instruction-tuning":[107],"dataset":[108],"with":[109,150],"object-aware":[111],"think-answer":[112],"chains":[113],"Ref-Thinker":[115,122],"fine-tuning.":[116],"The":[117],"description":[119],"inferred":[120],"is":[123],"used":[124],"as":[125],"Grounding-DINO":[130],"SAM2,":[132],"perform":[134],"segmentation":[137],"without":[138],"relying":[139],"supervision.":[142],"Additionally,":[143],"introduce":[145],"R2-AVSBench,":[146],"new":[148],"benchmark":[149],"linguistically":[151],"diverse":[152],"reasoning-intensive":[154],"references":[155],"better":[157],"evaluating":[158],"generalization.":[160],"Our":[161],"approach":[162],"achieves":[163],"state-of-the-art":[164],"results":[165],"both":[167],"standard":[168],"Ref-AVSBench":[169],"proposed":[171],"R2-AVSBench.":[172]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}
