{"id":"https://openalex.org/W4409327211","doi":"https://doi.org/10.1109/tmm.2025.3557637","title":"Exploiting EfficientSAM and Temporal Coherence for Audio-Visual Segmentation","display_name":"Exploiting EfficientSAM and Temporal Coherence for Audio-Visual Segmentation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409327211","doi":"https://doi.org/10.1109/tmm.2025.3557637"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3557637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3557637","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","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":null,"display_name":"Yue Zhu","orcid":"https://orcid.org/0009-0009-7473-3155"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yue Zhu","raw_affiliation_strings":["ReLER, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0009-0009-7473-3155","affiliations":[{"raw_affiliation_string":"ReLER, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377498","display_name":"Kun Li","orcid":"https://orcid.org/0000-0001-5083-2145"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Li","raw_affiliation_strings":["ReLER, CCAI, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5083-2145","affiliations":[{"raw_affiliation_string":"ReLER, CCAI, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020316185","display_name":"Zongxin Yang","orcid":"https://orcid.org/0000-0001-8783-8313"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zongxin Yang","raw_affiliation_strings":["Department of Biomedical Informatics, Harvard Medical School, Harvard University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8783-8313","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Harvard Medical School, Harvard University, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4146,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.95990706,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"2999","last_page":"3008"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9979000091552734,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9757000207901001,"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/computer-science","display_name":"Computer science","score":0.8684722781181335},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5813121199607849},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5700773000717163},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4774097204208374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4717859923839569},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46334561705589294},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4120270907878876},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37904635071754456},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.25831615924835205},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.23301351070404053},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.20753136277198792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8684722781181335},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5813121199607849},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5700773000717163},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4774097204208374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4717859923839569},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46334561705589294},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4120270907878876},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37904635071754456},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.25831615924835205},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.23301351070404053},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.20753136277198792},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3557637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3557637","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5586867142","display_name":null,"funder_award_id":"U2336212","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7235758038","display_name":null,"funder_award_id":"226-2022-00051","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2526050071","https://openalex.org/W2619697695","https://openalex.org/W2931433835","https://openalex.org/W2962914239","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963680395","https://openalex.org/W2964109005","https://openalex.org/W2986131686","https://openalex.org/W2990113535","https://openalex.org/W2997909293","https://openalex.org/W3021321555","https://openalex.org/W3048939150","https://openalex.org/W3093287838","https://openalex.org/W3108367559","https://openalex.org/W3118120400","https://openalex.org/W3138516171","https://openalex.org/W3170088426","https://openalex.org/W3170630188","https://openalex.org/W3175335326","https://openalex.org/W3175514052","https://openalex.org/W3175515048","https://openalex.org/W3176201273","https://openalex.org/W3212509912","https://openalex.org/W4205474609","https://openalex.org/W4226206782","https://openalex.org/W4304086152","https://openalex.org/W4310255405","https://openalex.org/W4385481295","https://openalex.org/W4385767885","https://openalex.org/W4386075532","https://openalex.org/W4387197080","https://openalex.org/W4387969181","https://openalex.org/W4387969495","https://openalex.org/W4390190100","https://openalex.org/W4390872864","https://openalex.org/W4390874575","https://openalex.org/W4391216149","https://openalex.org/W4393159092","https://openalex.org/W4393159433","https://openalex.org/W4393160420","https://openalex.org/W4394625876","https://openalex.org/W4399146361","https://openalex.org/W4402716319","https://openalex.org/W4402727760","https://openalex.org/W4402916446","https://openalex.org/W4403386295","https://openalex.org/W4403758862","https://openalex.org/W4407005368","https://openalex.org/W4407151317","https://openalex.org/W4408634392","https://openalex.org/W6631190155","https://openalex.org/W6729831399","https://openalex.org/W6782657842","https://openalex.org/W6783539077","https://openalex.org/W6803674551","https://openalex.org/W6804185262","https://openalex.org/W6809915981","https://openalex.org/W6840058269","https://openalex.org/W6848208918","https://openalex.org/W6850480200","https://openalex.org/W6852276098","https://openalex.org/W6852501939","https://openalex.org/W6852629184","https://openalex.org/W6852779002","https://openalex.org/W6852789751","https://openalex.org/W6852820501","https://openalex.org/W6853270349","https://openalex.org/W6854362512","https://openalex.org/W6854713258","https://openalex.org/W6856617293"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}