{"id":"https://openalex.org/W7166863711","doi":"https://doi.org/10.1016/j.knosys.2026.116562","title":"Towards unified scene understanding in audio-visual semantic segmentation","display_name":"Towards unified scene understanding in audio-visual semantic segmentation","publication_year":2026,"publication_date":"2026-07-01","ids":{"openalex":"https://openalex.org/W7166863711","doi":"https://doi.org/10.1016/j.knosys.2026.116562"},"language":"en","primary_location":{"id":"doi:10.1016/j.knosys.2026.116562","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.116562","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122563476","display_name":"Danjie Han","orcid":null},"institutions":[{"id":"https://openalex.org/I7726996","display_name":"Henan University of Economic and Law","ror":"https://ror.org/000jtc944","country_code":"CN","type":"education","lineage":["https://openalex.org/I7726996"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danjie Han","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Henan Finance University, Zhengzhou, 450046, China"],"raw_orcid":"https://orcid.org/0009-0009-2283-9089","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Henan Finance University, Zhengzhou, 450046, China","institution_ids":["https://openalex.org/I7726996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076922285","display_name":"Changsen Yuan","orcid":"https://orcid.org/0000-0001-5802-7503"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsen Yuan","raw_affiliation_strings":["College of Computer Science, Beijing University of Technology, Beijing, 100124, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Beijing University of Technology, Beijing, 100124, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779843","display_name":"Xuefeng Chen","orcid":"https://orcid.org/0000-0002-0130-3172"},"institutions":[{"id":"https://openalex.org/I4210159750","display_name":"Beijing Automotive Group (China)","ror":"https://ror.org/05tq31x39","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159750"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Chen","raw_affiliation_strings":["Inkeverse Group Limited, Beijing, 100102, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inkeverse Group Limited, Beijing, 100102, China","institution_ids":["https://openalex.org/I4210159750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003513358","display_name":"Xuan Zhao","orcid":"https://orcid.org/0009-0001-8271-3236"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Zhao","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, 100081, China"],"raw_orcid":"https://orcid.org/0009-0001-8271-3236","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063010018","display_name":"Cunhan Guo","orcid":"https://orcid.org/0000-0002-4546-3928"},"institutions":[{"id":"https://openalex.org/I64449678","display_name":"Putian University","ror":"https://ror.org/00jmsxk74","country_code":"CN","type":"education","lineage":["https://openalex.org/I64449678"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cunhan Guo","raw_affiliation_strings":["College of Computer and Data Science, Putian University, Putian, 351100, China"],"raw_orcid":"https://orcid.org/0000-0002-4546-3928","affiliations":[{"raw_affiliation_string":"College of Computer and Data Science, Putian University, Putian, 351100, China","institution_ids":["https://openalex.org/I64449678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125193553","display_name":"Yanghao Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanghao Zhou","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, 100081, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5063010018"],"corresponding_institution_ids":["https://openalex.org/I64449678"],"apc_list":{"value":3130,"currency":"USD","value_usd":3130},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88722003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"350","issue":null,"first_page":"116562","last_page":"116562"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.6333000063896179,"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":0.6333000063896179,"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":0.14910000562667847,"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":0.05079999938607216,"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":0.5652999877929688},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5573999881744385},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5483999848365784},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43950000405311584},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.40869998931884766},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.37540000677108765},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.3659999966621399},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.3628000020980835},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.35830000042915344},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.32499998807907104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7626000046730042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6421999931335449},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5652999877929688},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5573999881744385},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5483999848365784},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.397599995136261},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3659999966621399},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25999999046325684},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.knosys.2026.116562","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.116562","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4601139426231384}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W3175515048","https://openalex.org/W4309660795","https://openalex.org/W4312349930","https://openalex.org/W4312815172","https://openalex.org/W4313123347","https://openalex.org/W4385767885","https://openalex.org/W4387969151","https://openalex.org/W4390872378","https://openalex.org/W4390872864","https://openalex.org/W4393159092","https://openalex.org/W4393159433","https://openalex.org/W4393160420","https://openalex.org/W4399146361","https://openalex.org/W4401074024","https://openalex.org/W4402111965","https://openalex.org/W4402727638","https://openalex.org/W4402727889","https://openalex.org/W4402753794","https://openalex.org/W4403386295","https://openalex.org/W4403791579","https://openalex.org/W4403791582","https://openalex.org/W4405695539","https://openalex.org/W4406062792","https://openalex.org/W4407354906","https://openalex.org/W4409364991","https://openalex.org/W4409795848","https://openalex.org/W4409882601","https://openalex.org/W4413144530","https://openalex.org/W4413472233","https://openalex.org/W4417248874","https://openalex.org/W7160028320"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-03T06:15:21.484131","created_date":"2026-07-02T00:00:00"}
