{"id":"https://openalex.org/W7124444548","doi":"https://doi.org/10.1109/tce.2025.3650288","title":"MAViS: A Multi-Agent Approach for Training-Free Referring Video Object Segmentation","display_name":"MAViS: A Multi-Agent Approach for Training-Free Referring Video Object Segmentation","publication_year":2026,"publication_date":"2026-01-16","ids":{"openalex":"https://openalex.org/W7124444548","doi":"https://doi.org/10.1109/tce.2025.3650288"},"language":null,"primary_location":{"id":"doi:10.1109/tce.2025.3650288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2025.3650288","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"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 Consumer Electronics","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/A5123248978","display_name":"Tai Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tai Peng","raw_affiliation_strings":["Graduate Institute of Networking and Multimedia, National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0001-1850-929X","affiliations":[{"raw_affiliation_string":"Graduate Institute of Networking and Multimedia, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123226820","display_name":"Chu-Song Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chu-Song Chen","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-2959-2471","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":9.8969,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94756296,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"72","issue":"1","first_page":"283","last_page":"290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9519000053405762,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9519000053405762,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.010099999606609344,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.006800000090152025,"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":0.6583999991416931},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.6155999898910522},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5799999833106995},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5789999961853027},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5687000155448914},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.49410000443458557},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4343000054359436},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4142000079154968},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3982999920845032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8349999785423279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7224000096321106},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6583999991416931},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6155999898910522},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5799999833106995},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5789999961853027},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5687000155448914},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45809999108314514},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3982999920845032},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3961000144481659},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3919999897480011},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.33090001344680786},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3082999885082245},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2888000011444092},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.26600000262260437},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.2624000012874603}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tce.2025.3650288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2025.3650288","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"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 Consumer Electronics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4654035568","display_name":null,"funder_award_id":"NSTC 112-2221-E-002-182-MY3","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"},{"id":"https://openalex.org/G7470315604","display_name":null,"funder_award_id":"112-2221-E-002-132-MY3","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"},{"id":"https://openalex.org/G8880298762","display_name":null,"funder_award_id":"114L900902","funder_id":"https://openalex.org/F4320323900","funder_display_name":"National Taiwan University"}],"funders":[{"id":"https://openalex.org/F4320323900","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2157331557","https://openalex.org/W2963354481","https://openalex.org/W2983693499","https://openalex.org/W3010010212","https://openalex.org/W3033114334","https://openalex.org/W3096609285","https://openalex.org/W3104844437","https://openalex.org/W3215899623","https://openalex.org/W4226024706","https://openalex.org/W4307504011","https://openalex.org/W4315473428","https://openalex.org/W4386076148","https://openalex.org/W4387068153","https://openalex.org/W4389519620","https://openalex.org/W4390872868","https://openalex.org/W4390872914","https://openalex.org/W4390873204","https://openalex.org/W4390873614","https://openalex.org/W4390873747","https://openalex.org/W4390874496","https://openalex.org/W4390874575","https://openalex.org/W4400032968","https://openalex.org/W4401362547","https://openalex.org/W4402727770","https://openalex.org/W4402754134","https://openalex.org/W4402754173","https://openalex.org/W4402961691","https://openalex.org/W4404601423","https://openalex.org/W4404612908","https://openalex.org/W4404769790","https://openalex.org/W4404783405","https://openalex.org/W4409368119","https://openalex.org/W4410706693","https://openalex.org/W4413146469","https://openalex.org/W4413147076","https://openalex.org/W4413155707","https://openalex.org/W4415798953","https://openalex.org/W7133196460","https://openalex.org/W7133197087"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"introduce":[4],"a":[5,54,63,68,95],"simple":[6],"but":[7],"effective":[8],"training-free":[9,114],"pipeline":[10],"for":[11,28,85],"handling":[12],"the":[13,45,86],"task":[14,46],"of":[15],"text-to-video":[16],"object":[17],"segmentation.":[18],"Our":[19],"approach":[20],"leverages":[21],"open-source":[22],"Multimodal":[23],"Large":[24],"Language":[25],"Models":[26],"(MLLMs)":[27],"segmenting":[29],"objects":[30],"in":[31],"videos":[32],"based":[33],"on":[34],"language":[35],"descriptions.":[36],"We":[37],"design":[38],"three":[39],"multimodal":[40],"reasoning":[41,52],"agents":[42],"that":[43,112],"decompose":[44],"into":[47],"semantic,":[48],"temporal,":[49],"and":[50,77,105],"spatial":[51],"stages:":[53],"Video":[55],"Summarization":[56],"Agent":[57,66,81],"to":[58,73,94],"provide":[59],"concise":[60],"semantic":[61],"context,":[62],"Keyframe":[64],"Selection":[65],"employing":[67],"Binary-Logit":[69],"Frame":[70],"Scoring":[71],"mechanism":[72],"identify":[74],"informative":[75],"frames,":[76],"an":[78],"Object":[79],"Grounding":[80],"predicting":[82],"bounding":[83],"boxes":[84],"described":[87],"objects.":[88],"Finally,":[89],"by":[90],"providing":[91],"high-quality":[92],"prompts":[93],"semantic-free":[96],"segmentation":[97,107],"tool,":[98],"our":[99,113],"method":[100,115],"effectively":[101],"handles":[102],"spatiotemporal":[103],"variations":[104],"reduces":[106,117],"errors.":[108],"Extensive":[109],"experiments":[110],"show":[111],"significantly":[116],"resource":[118],"requirements":[119],"while":[120],"achieving":[121],"comparable":[122],"or":[123],"even":[124],"better":[125],"performance":[126],"than":[127],"supervised":[128],"fine-tuning":[129],"approaches.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-01-17T00:00:00"}