{"id":"https://openalex.org/W4401200977","doi":"https://doi.org/10.1109/iccv51701.2025.02197","title":"ViLLa: Video Reasoning Segmentation with Large Language Model","display_name":"ViLLa: Video Reasoning Segmentation with Large Language Model","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4401200977","doi":"https://doi.org/10.1109/iccv51701.2025.02197"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.14500","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086263174","display_name":"Rongkun Zheng","orcid":"https://orcid.org/0000-0002-7860-2023"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Rongkun Zheng","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625026","display_name":"Qi L\u00fc","orcid":"https://orcid.org/0000-0001-6061-5478"},"institutions":[{"id":"https://openalex.org/I4210128556","display_name":"Insta (Germany)","ror":"https://ror.org/03kzw7k63","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210128556"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lu Qi","raw_affiliation_strings":["Insta360"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insta360","institution_ids":["https://openalex.org/I4210128556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329867","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0001-7965-9198"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364925","display_name":"Yi Wang","orcid":"https://orcid.org/0000-0002-2067-5465"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366717","display_name":"Kun Wang","orcid":"https://orcid.org/0000-0003-2513-768X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110017119","display_name":"Yu Qiao","orcid":"https://orcid.org/0009-0000-8500-3902"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hengshuang Zhao","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5816,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.80358699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"23667","last_page":"23677"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965000152587891,"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":0.9965000152587891,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9804999828338623,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.9668999910354614,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7259050607681274},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6236546635627747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5376803278923035},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4789467453956604},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4759354591369629},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.39530515670776367}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7259050607681274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6236546635627747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5376803278923035},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4789467453956604},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4759354591369629},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.39530515670776367}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.14500","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.14500","pdf_url":"https://arxiv.org/pdf/2407.14500","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},{"id":"doi:10.48550/arxiv.2407.14500","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.14500","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.14500","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.14500","pdf_url":"https://arxiv.org/pdf/2407.14500","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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/G5496564920","display_name":null,"funder_award_id":"62422606,62201484","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401200977.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recent":[0],"efforts":[1],"in":[2,27,42,108,168],"video":[3,101,207],"reasoning":[4,72,208],"segmentation":[5,73,209],"(VRS)":[6],"integrate":[7],"large":[8],"language":[9],"models":[10,14],"(LLMs)":[11],"with":[12,74,100],"perception":[13],"to":[15,33,82,165],"localize":[16],"and":[17,35,54,68,111,131,194,198,216],"track":[18],"objects":[19,38],"via":[20],"textual":[21],"instructions,":[22],"achieving":[23],"barely":[24],"satisfactory":[25],"results":[26,188],"simple":[28],"scenarios.":[29,181],"However,":[30],"they":[31],"struggled":[32],"discriminate":[34],"deduce":[36],"the":[37,62,97],"from":[39],"user":[40,98],"queries":[41],"more":[43],"real-world":[44],"scenes":[45],"featured":[46],"by":[47,125],"long":[48,140,152],"durations,":[49],"multiple":[50,87],"objects,":[51],"rapid":[52],"motion,":[53],"heavy":[55],"occlusions.":[56],"In":[57],"this":[58,169],"work,":[59],"we":[60,172],"analyze":[61],"underlying":[63],"causes":[64],"of":[65,139],"these":[66,84],"limitations,":[67],"present":[69],"ViLLa:":[70],"Video":[71],"Large":[75],"Language":[76],"Model.":[77],"Remarkably,":[78],"our":[79,203],"ViLLa":[80,142],"manages":[81],"tackle":[83],"challenges":[85],"through":[86],"core":[88],"innovations:":[89],"(1)":[90],"a":[91,113,145,174],"context":[92],"synthesizer":[93],"that":[94,117,149,202],"dynamically":[95],"encodes":[96],"intent":[99],"contexts":[102],"for":[103,160,211],"accurate":[104],"reasoning,":[105],"resolving":[106],"ambiguities":[107],"complex":[109,122,180],"queries,":[110],"(2)":[112],"hierarchical":[114],"temporal":[115,123,133],"synchronizer":[116],"disentangles":[118],"multi-object":[119,127],"interactions":[120,128],"across":[121],"scenarios":[124],"modelling":[126],"at":[129,221],"local":[130],"global":[132],"scales.":[134],"To":[135],"enable":[136],"efficient":[137],"processing":[138],"videos,":[141],"incorporates":[143],"(3)":[144],"key":[146],"segment":[147],"sampler":[148],"adaptively":[150],"partitions":[151],"videos":[153],"into":[154],"shorter":[155],"but":[156],"semantically":[157],"dense":[158],"segments":[159],"less":[161],"redundancy.":[162],"What's":[163],"more,":[164],"promote":[166],"research":[167],"unexplored":[170],"area,":[171],"construct":[173],"VRS":[175],"benchmark,":[176],"VideoReasonSeg,":[177,190],"featuring":[178],"different":[179],"Our":[182],"model":[183],"also":[184],"exhibits":[185],"impressive":[186],"state-of-the-art":[187],"on":[189],"Ref-YouTube-VOS,":[191],"Ref-DAVIS17,":[192],"MeViS,":[193],"ReVOS.":[195],"Both":[196],"quantitative":[197],"qualitative":[199],"experiments":[200],"demonstrate":[201],"method":[204],"effectively":[205],"enhances":[206],"capabilities":[210],"multimodal":[212],"LLMs.":[213],"The":[214],"code":[215],"dataset":[217],"will":[218],"be":[219],"available":[220],"https://github.com/rkzheng99/ViLLa.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}