{"id":"https://openalex.org/W4413344259","doi":"https://doi.org/10.1109/tpami.2025.3600507","title":"MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation","display_name":"MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation","publication_year":2025,"publication_date":"2025-08-19","ids":{"openalex":"https://openalex.org/W4413344259","doi":"https://doi.org/10.1109/tpami.2025.3600507","pmid":"https://pubmed.ncbi.nlm.nih.gov/40828703"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3600507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3600507","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.10945","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036631624","display_name":"Henghui Ding","orcid":"https://orcid.org/0000-0003-4868-6526"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Henghui Ding","raw_affiliation_strings":["Institute of Big Data, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","Fudan University, China"],"affiliations":[{"raw_affiliation_string":"Institute of Big Data, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353160","display_name":"Chang Liu","orcid":"https://orcid.org/0000-0001-6980-7791"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Chang Liu","raw_affiliation_strings":["MoE Key Laboratory of Interdisciplinary Research of Computation and Economics, Shanghai University of Finance and Economics, Shanghai, China","School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Interdisciplinary Research of Computation and Economics, Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]},{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085200012","display_name":"Shuting He","orcid":"https://orcid.org/0000-0002-1582-5684"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Shuting He","raw_affiliation_strings":["MoE Key Laboratory of Interdisciplinary Research of Computation and Economics, Shanghai University of Finance and Economics, Shanghai, China","School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Interdisciplinary Research of Computation and Economics, Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]},{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090152810","display_name":"Kaining Ying","orcid":"https://orcid.org/0000-0003-2596-1847"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaining Ying","raw_affiliation_strings":["Institute of Big Data, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","Fudan University, China"],"affiliations":[{"raw_affiliation_string":"Institute of Big Data, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055287990","display_name":"Xudong Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xudong Jiang","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005626854","display_name":"Chen Change Loy","orcid":"https://orcid.org/0000-0001-5345-1591"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Change Loy","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100644845","display_name":"Yu-Gang Jiang","orcid":"https://orcid.org/0000-0002-8781-6955"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China","Fudan University, China"],"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5036631624"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":4.8723,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95491616,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"47","issue":"12","first_page":"11400","last_page":"11416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9883000254631042,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9883000254631042,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9824000000953674,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9484000205993652,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7010239362716675},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.681471586227417},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6477409601211548},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5994809865951538},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5378045439720154},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5089082717895508},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.49252089858055115},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4807269871234894},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4437265992164612},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.43155261874198914}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7010239362716675},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.681471586227417},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6477409601211548},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5994809865951538},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5378045439720154},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5089082717895508},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.49252089858055115},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4807269871234894},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4437265992164612},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.43155261874198914},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2025.3600507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3600507","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40828703","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40828703","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2512.10945","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.10945","pdf_url":"https://arxiv.org/pdf/2512.10945","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.10945","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.10945","pdf_url":"https://arxiv.org/pdf/2512.10945","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3671822789","display_name":null,"funder_award_id":"62472104","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7344333925","display_name":null,"funder_award_id":"25ZR1402138","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4413344259.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2392243736","https://openalex.org/W86652014","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W4379231730","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2328518092","https://openalex.org/W4389858081","https://openalex.org/W1522196789"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,56,90,193],"large-scale":[4],"multi-modal":[5],"dataset":[6,91,191],"for":[7,83,148,183],"referring":[8,30,124,138,152],"motion":[9,65,77,80,95,153,169,200],"expression":[10,154],"video":[11,31,85,125,132,145,171,202,207],"segmentation,":[12],"focusing":[13],"on":[14,23,36],"segmenting":[15],"and":[16,39,69,79,100,143,162,178],"tracking":[17,140],"target":[18,50],"objects":[19,38,104],"in":[20,44,55,66,97,105,167,205],"videos":[21,68,107],"based":[22],"language":[24,41],"description":[25],"of":[26,64,75,108,164,199],"objects'":[27],"motions.":[28],"Existing":[29],"segmentation":[32,127,134],"datasets":[33,60],"often":[34],"focus":[35],"salient":[37],"use":[40],"expressions":[42,78,96],"rich":[43],"static":[45],"attributes,":[46],"potentially":[47],"allowing":[48],"the":[49,62,73,149,176,197],"object":[51,126,133],"to":[52],"be":[53],"identified":[54],"single":[57],"frame.":[58],"Such":[59],"underemphasize":[61],"role":[63],"both":[67,98],"languages.":[70],"To":[71],"explore":[72],"feasibility":[74],"using":[76],"reasoning":[81],"clues":[82],"pixel-level":[84],"understanding,":[86],"we":[87],"introduce":[88],"MeViS,":[89,121],"containing":[92],"33,072":[93],"human-annotated":[94],"text":[99],"audio,":[101],"covering":[102],"8,171":[103],"2,006":[106],"complex":[109,206],"scenarios.":[110],"We":[111,173],"benchmark":[112],"15":[113],"existing":[114,165],"methods":[115,147,166],"across":[116],"4":[117,144],"tasks":[118],"supported":[119],"by":[120],"including":[122],"6":[123],"(RVOS)":[128],"methods,":[129,136,142],"3":[130],"audio-guided":[131],"(AVOS)":[135],"2":[137],"multi-object":[139],"(RMOT)":[141],"captioning":[146],"newly":[150],"introduced":[151],"generation":[155],"(RMEG)":[156],"task.":[157],"The":[158],"results":[159],"demonstrate":[160],"weaknesses":[161],"limitations":[163],"addressing":[168],"expression-guided":[170,201],"understanding.":[172],"further":[174],"analyze":[175],"challenges":[177],"propose":[179],"an":[180],"approach":[181],"LMPM++":[182],"RVOS/AVOS/RMOT":[184],"that":[185,195],"achieves":[186],"new":[187],"state-of-the-art":[188],"results.":[189],"Our":[190],"provides":[192],"platform":[194],"facilitates":[196],"development":[198],"understanding":[203],"algorithms":[204],"scenes.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-08-20T00:00:00"}
