{"id":"https://openalex.org/W7138163334","doi":"https://doi.org/10.1609/aaai.v40i9.37714","title":"AURORA: Augmented Understanding via Structured Reasoning and Reinforcement Learning for Reference Audio-Visual Segmentation","display_name":"AURORA: Augmented Understanding via Structured Reasoning and Reinforcement Learning for Reference Audio-Visual Segmentation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138163334","doi":"https://doi.org/10.1609/aaai.v40i9.37714"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i9.37714","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37714","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37714/41676","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37714/41676","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129748370","display_name":"Ziyang Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Luo","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129647552","display_name":"Nian Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nian Liu","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129669747","display_name":"Fahad Shahbaz Khan","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":"Fahad Shahbaz Khan","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence"],"raw_orcid":null,"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/A5129734226","display_name":"Junwei Han","orcid":null},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]},{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I99418890","display_name":"Northwestern Polytechnic University","ror":"https://ror.org/05wn69s11","country_code":"US","type":"education","lineage":["https://openalex.org/I99418890"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Junwei Han","raw_affiliation_strings":["Northwestern Polytechnical University\nChongqing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University\nChongqing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I10535382","https://openalex.org/I17145004","https://openalex.org/I99418890"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"40","issue":"9","first_page":"7716","last_page":"7724"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.3725999891757965,"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/T10860","display_name":"Speech and Audio Processing","score":0.3725999891757965,"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":0.1712000072002411,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07050000131130219,"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/segmentation","display_name":"Segmentation","score":0.6118999719619751},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5961999893188477},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.5421000123023987},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.45339998602867126},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42579999566078186},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.38989999890327454},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.37229999899864197},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3504999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7856000065803528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6812000274658203},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6118999719619751},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5961999893188477},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.5421000123023987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46790000796318054},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.45339998602867126},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28119999170303345},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i9.37714","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37714","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37714/41676","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.v40i9.37714","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37714","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37714/41676","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138163334.pdf","grobid_xml":"https://content.openalex.org/works/W7138163334.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reference":[0],"Audio-Visual":[1],"Segmentation":[2],"(Ref-AVS)":[3],"tasks":[4],"challenge":[5],"models":[6],"to":[7,27,54,73,90,123,140,159],"precisely":[8],"locate":[9],"sounding":[10],"objects":[11],"by":[12,131],"integrating":[13],"visual,":[14],"auditory,":[15],"and":[16,37,58,82,156],"textual":[17],"cues.":[18],"Existing":[19],"methods":[20],"often":[21],"lack":[22],"genuine":[23,56,105],"semantic":[24],"understanding,":[25],"tending":[26],"memorize":[28],"fixed":[29],"reasoning":[30,36,57,80,94,106,128],"patterns.":[31],"Furthermore,":[32],"jointly":[33],"training":[34,113],"for":[35],"segmentation":[38,86,98],"can":[39],"compromise":[40],"pixel-level":[41],"precision.":[42],"To":[43,100],"address":[44],"these":[45,93],"issues,":[46],"we":[47,108],"introduce":[48,83],"AURORA,":[49],"a":[50,67,78,84,110,116],"novel":[51,85],"framework":[52],"designed":[53],"enhance":[55,124],"language":[59],"comprehension":[60],"in":[61,143],"reference":[62],"audio-visual":[63],"segmentation.":[64,161],"We":[65],"employ":[66],"structured":[68],"Chain-of-Thought":[69],"(CoT)":[70],"prompting":[71],"mechanism":[72],"guide":[74],"the":[75,103,125],"model":[76],"through":[77],"step-by-step":[79],"process":[81],"feature":[87],"distillation":[88],"loss":[89],"effectively":[91,158],"integrate":[92],"abilities":[95],"without":[96],"sacrificing":[97],"performance.":[99],"further":[101,111],"cultivate":[102],"model's":[104],"capabilities,":[107],"devise":[109],"two-stage":[112],"strategy:":[114],"first,":[115],"``corrective":[117],"reflective-style":[118],"training\"":[119],"stage":[120],"utilizes":[121],"self-correction":[122],"quality":[126],"of":[127],"paths,":[129],"followed":[130],"reinforcement":[132],"learning":[133],"via":[134],"Group":[135],"Reward":[136],"Policy":[137],"Optimization":[138],"(GRPO)":[139],"bolster":[141],"robustness":[142],"challenging":[144],"scenarios.":[145],"Experiments":[146],"demonstrate":[147],"that":[148],"AURORA":[149],"achieves":[150],"state-of-the-art":[151],"performance":[152],"on":[153],"Ref-AVS":[154],"benchmarks":[155],"generalizes":[157],"unreferenced":[160]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}