{"id":"https://openalex.org/W4415707715","doi":"https://doi.org/10.1109/icme59968.2025.11210115","title":"FDAVS: Exploring Frequency-Driven Modality Enhancement in Audio-Visual Segmentation","display_name":"FDAVS: Exploring Frequency-Driven Modality Enhancement in Audio-Visual Segmentation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707715","doi":"https://doi.org/10.1109/icme59968.2025.11210115"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5069389660","display_name":"Mengyuan Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mengyuan Zhu","raw_affiliation_strings":["Dalian University of Technology,School of Information and Communication Engineering,China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Information and Communication Engineering,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048521072","display_name":"Yunzhi Zhuge","orcid":"https://orcid.org/0000-0002-4288-4516"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunzhi Zhuge","raw_affiliation_strings":["Dalian University of Technology,School of Information and Communication Engineering,China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Information and Communication Engineering,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039302902","display_name":"Shaogang Gong","orcid":"https://orcid.org/0000-0001-8156-2299"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sitong Gong","raw_affiliation_strings":["Dalian University of Technology,School of Information and Communication Engineering,China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Information and Communication Engineering,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087681764","display_name":"Lu Zhang","orcid":"https://orcid.org/0000-0003-4648-4437"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Zhang","raw_affiliation_strings":["Dalian University of Technology,School of Information and Communication Engineering,China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Information and Communication Engineering,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006986293","display_name":"Huchuan Lu","orcid":"https://orcid.org/0000-0002-6668-9758"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huchuan Lu","raw_affiliation_strings":["Dalian University of Technology,School of Information and Communication Engineering,China"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Information and Communication Engineering,China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069389660"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39171075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.6610000133514404,"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":0.6610000133514404,"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":0.16689999401569366,"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/T12032","display_name":"Multisensory perception and integration","score":0.03180000185966492,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6306999921798706},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5751000046730042},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.574400007724762},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5109000205993652},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.44209998846054077},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.41040000319480896},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4002000093460083},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3937000036239624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833999991416931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.696399986743927},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6306999921798706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6186000108718872},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5751000046730042},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.574400007724762},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5109000205993652},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.44209998846054077},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36570000648498535},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3603000044822693},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.35359999537467957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.27639999985694885}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1844944916","https://openalex.org/W2194775991","https://openalex.org/W2619697695","https://openalex.org/W3034304805","https://openalex.org/W3175515048","https://openalex.org/W4312815172","https://openalex.org/W4313123347","https://openalex.org/W4385767885","https://openalex.org/W4387969495","https://openalex.org/W4390872864","https://openalex.org/W4393160420","https://openalex.org/W4399146361","https://openalex.org/W4400410003","https://openalex.org/W4402703118","https://openalex.org/W4402753794","https://openalex.org/W4403386295","https://openalex.org/W4404002448","https://openalex.org/W4407638717","https://openalex.org/W4413146469","https://openalex.org/W4413472233"],"related_works":[],"abstract_inverted_index":{"Audio-Visual":[0],"Segmentation":[1],"(AVS)":[2],"aims":[3],"to":[4,35,51,106],"identify":[5],"and":[6,40,57,74,78,103],"delineate":[7],"sounding":[8],"objects":[9],"within":[10,84],"a":[11],"video":[12],"stream":[13],"guided":[14],"by":[15],"auditory":[16],"cues.":[17],"Existing":[18],"research":[19],"focuses":[20],"on":[21,114],"audio-visual":[22],"interactions":[23],"in":[24],"the":[25,30,76,85,100,108,115,119,134],"spatial":[26,56],"domain":[27],"while":[28,88],"overlooking":[29],"intrinsic":[31],"frequency-domain":[32],"information,":[33],"leading":[34],"insufficient":[36],"multimodal":[37,61,111],"feature":[38],"integration":[39],"alignment.":[41],"In":[42],"response,":[43],"we":[44,66,93],"introduce":[45],"FDAVS,":[46],"which":[47,72],"incorporates":[48],"frequency-driven":[49,137],"designs":[50],"achieve":[52],"synergistic":[53],"utilization":[54],"of":[55,60,81,110,121,136],"frequency":[58,112],"information":[59,113],"features.":[62,123],"To":[63],"begin":[64],"with,":[65],"propose":[67],"Frequency-Oriented":[68],"Audio":[69],"Integration":[70],"(FOAI),":[71],"decouples":[73],"optimizes":[75],"high-":[77],"low-frequency":[79],"components":[80],"visual":[82,116],"features":[83],"image":[86],"encoder":[87],"integrating":[89],"audio":[90],"signals.":[91],"Subsequently,":[92],"employ":[94],"Frequency-Based":[95],"Cross-modal":[96],"Fusion":[97],"(FBCF)":[98],"between":[99],"pixel":[101],"decoder":[102,105],"mask":[104],"enhance":[107],"guidance":[109],"modality,":[117],"increasing":[118],"consistency":[120],"audiovisual":[122],"FDAVS":[124],"achieves":[125],"state-of-the-art":[126],"segmentation":[127],"performance":[128],"across":[129],"three":[130],"AVS":[131],"benchmarks,":[132],"highlighting":[133],"effectiveness":[135],"modality":[138],"enhancement.":[139]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}