{"id":"https://openalex.org/W4403791582","doi":"https://doi.org/10.1145/3664647.3680926","title":"SelM: Selective Mechanism based Audio-Visual Segmentation","display_name":"SelM: Selective Mechanism based Audio-Visual Segmentation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791582","doi":"https://doi.org/10.1145/3664647.3680926"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680926","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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":"Jiaxu Li","orcid":"https://orcid.org/0009-0003-8907-3459"},"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":"Jiaxu Li","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0003-8907-3459","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101155338","display_name":"Songsong Yu","orcid":"https://orcid.org/0009-0008-6658-1385"},"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":"Songsong Yu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0008-6658-1385","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398548","display_name":"Yifan Wang","orcid":"https://orcid.org/0000-0002-1911-2526"},"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":"Yifan Wang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-1911-2526","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318892","display_name":"Lijun Wang","orcid":"https://orcid.org/0000-0003-2538-8358"},"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":"Lijun Wang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-2538-8358","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, 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, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-6668-9758","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":1.6686,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85708444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3926","last_page":"3935"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.974399983882904,"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":0.7497666478157043},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.6404303312301636},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6293086409568787},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6055516600608826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5036346316337585},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48585793375968933},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4302107095718384},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3519248366355896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3272988796234131},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.15262135863304138}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497666478157043},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6404303312301636},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6293086409568787},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6055516600608826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5036346316337585},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48585793375968933},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4302107095718384},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3519248366355896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3272988796234131},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.15262135863304138},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680926","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2105934661","https://openalex.org/W2117539524","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2910628332","https://openalex.org/W2963115079","https://openalex.org/W2963680395","https://openalex.org/W2982619606","https://openalex.org/W3064840847","https://openalex.org/W3086755561","https://openalex.org/W3092603041","https://openalex.org/W3105352633","https://openalex.org/W3108367559","https://openalex.org/W3170088426","https://openalex.org/W3175515048","https://openalex.org/W3206008172","https://openalex.org/W3208827570","https://openalex.org/W3212492847","https://openalex.org/W4205335327","https://openalex.org/W4221145950","https://openalex.org/W4221167476","https://openalex.org/W4225453213","https://openalex.org/W4226206782","https://openalex.org/W4283461773","https://openalex.org/W4286796718","https://openalex.org/W4294311190","https://openalex.org/W4313123347","https://openalex.org/W4386083012","https://openalex.org/W4390872864","https://openalex.org/W4393159092","https://openalex.org/W4393160420","https://openalex.org/W4403386295"],"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/W1522196789"],"abstract_inverted_index":{"Audio-Visual":[0,206],"Segmentation":[1,208],"(AVS)":[2],"aims":[3],"to":[4,11,22,86,102,131,137,158],"segment":[5],"sound-producing":[6],"objects":[7,39],"in":[8,32,40,145,199,203],"videos":[9],"according":[10],"associated":[12],"audio":[13,33,81,124,164,191],"cues,":[14],"where":[15,79],"both":[16],"modalities":[17,50],"are":[18,83],"affected":[19],"by":[20,185],"noise":[21,61,112],"different":[23],"extents,":[24],"such":[25],"as":[26],"the":[27,35,68,142,187,204],"blending":[28],"of":[29,37,58],"background":[30],"noises":[31],"or":[34,62],"presence":[36],"distracted":[38],"video.":[41],"Most":[42],"existing":[43,143],"methods":[44],"focus":[45],"on":[46,123],"learning":[47],"interactions":[48,66,162],"between":[49,163,190],"at":[51,215],"high":[52],"semantic":[53],"levels":[54],"but":[55],"is":[56,129],"incapable":[57],"filtering":[59],"low-level":[60],"achieving":[63,168],"fine-grained":[64,170],"representational":[65],"during":[67],"early":[69,146],"feature":[70,116],"extraction":[71],"phase.":[72],"Consequently,":[73],"they":[74],"struggle":[75],"with":[76],"illusion":[77],"issues,":[78],"nonexistent":[80],"cues":[82],"erroneously":[84],"linked":[85],"visual":[87,126,166,193],"objects.":[88],"In":[89],"this":[90],"paper,":[91],"we":[92,173],"present":[93],"SelM,":[94],"a":[95,152,175],"novel":[96],"architecture":[97],"that":[98],"leverages":[99],"selective":[100],"mechanisms":[101],"counteract":[103],"these":[104],"illusions.":[105],"SelM":[106,150,195],"employs":[107],"State":[108],"Space":[109],"model":[110],"for":[111,178],"reduction":[113],"and":[114,125,165,192],"robust":[115],"selection.":[117],"By":[118],"imposing":[119],"additional":[120],"bidirectional":[121],"constraints":[122],"embeddings,":[127],"it":[128],"able":[130],"precisely":[132],"identify":[133],"crucial":[134],"features":[135],"corresponding":[136],"sound-emitting":[138],"targets.":[139],"To":[140],"fill":[141],"gap":[144],"fusion":[147],"within":[148],"AVS,":[149],"introduces":[151],"dual":[153],"alignment":[154],"mechanism":[155],"specifically":[156],"engineered":[157],"facilitate":[159],"intricate":[160],"spatio-temporal":[161],"streams,":[167],"more":[169],"representations.":[171],"Moreover,":[172],"develop":[174],"cross-level":[176],"decoder":[177],"layered":[179],"reasoning,":[180],"significantly":[181],"enhancing":[182],"segmentation":[183],"precision":[184],"exploring":[186],"complex":[188],"relationships":[189],"information.":[194],"achieves":[196],"state-of-the-art":[197],"performance":[198],"AVS":[200],"tasks,":[201],"especially":[202],"challenging":[205],"Semantic":[207],"subset.":[209],"The":[210],"code":[211],"can":[212],"be":[213],"found":[214],"https://github.com/Cyyzpoi/SelM.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
