{"id":"https://openalex.org/W4406841274","doi":"https://doi.org/10.1109/iccv51701.2025.01861","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","display_name":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4406841274","doi":"https://doi.org/10.1109/iccv51701.2025.01861"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01861","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/2501.14607","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101518959","display_name":"Tianming Liang","orcid":"https://orcid.org/0000-0003-0558-954X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianming Liang","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062991951","display_name":"Kun-Yu Lin","orcid":"https://orcid.org/0000-0002-0013-3730"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun-Yu Lin","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091202600","display_name":"Chaolei Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaolei Tan","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461783","display_name":"Jianguo Zhang","orcid":"https://orcid.org/0000-0001-9317-0268"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianguo Zhang","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108050904","display_name":"Wei\u2010Shi Zheng","orcid":"https://orcid.org/0000-0001-8327-0003"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Shi Zheng","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043114248","display_name":"Jianfang Hu","orcid":"https://orcid.org/0000-0002-4016-9885"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian-Fang Hu","raw_affiliation_strings":["Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101518959"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00949512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20009","last_page":"20019"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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":0.9991999864578247,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987999796867371,"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":0.9976999759674072,"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":0.6863332986831665},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6184384226799011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6164436936378479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5517845749855042},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5408217906951904},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.43813079595565796},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10650315880775452}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6863332986831665},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6184384226799011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6164436936378479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5517845749855042},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5408217906951904},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.43813079595565796},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10650315880775452},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01861","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:2501.14607","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.14607","pdf_url":"https://arxiv.org/pdf/2501.14607","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.14607","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.14607","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.14607","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.14607","pdf_url":"https://arxiv.org/pdf/2501.14607","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G173065042","display_name":null,"funder_award_id":"2023B1212060026","funder_id":"https://openalex.org/F4320329883","funder_display_name":"Guangdong Province Key Laboratory of Information Security Technology"},{"id":"https://openalex.org/G1730722784","display_name":null,"funder_award_id":"2023B1515040025","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1951972270","display_name":null,"funder_award_id":"U22A2095","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8705560045","display_name":null,"funder_award_id":"U22A2095,6247072922","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329883","display_name":"Guangdong Province Key Laboratory of Information Security Technology","ror":null},{"id":"https://openalex.org/F4320337144","display_name":"National Supercomputing Center, Korea Institute of Science and Technology Information","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4406841274.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","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":{"Referring":[0],"video":[1,12],"object":[2,138],"segmentation":[3],"(RVOS)":[4],"aims":[5],"to":[6,100,123,136],"segment":[7],"target":[8],"objects":[9],"throughout":[10],"a":[11,15,43,57,91,129],"based":[13],"on":[14,147,161],"text":[16,118],"description.":[17],"This":[18],"is":[19,72,134],"challenging":[20],"as":[21],"it":[22],"involves":[23],"deep":[24],"vision-language":[25,64],"understanding,":[26],"pixel-level":[27,76],"dense":[28,77],"prediction":[29,99,104],"and":[30,71,79],"spatiotemporal":[31,81],"reasoning.":[32,82],"Despite":[33],"notable":[34],"progress":[35],"in":[36],"recent":[37],"years,":[38],"existing":[39],"methods":[40,157],"still":[41],"exhibit":[42],"noticeable":[44],"gap":[45],"when":[46],"considering":[47],"all":[48],"these":[49],"aspects.":[50],"In":[51,83],"this":[52],"work,":[53],"we":[54],"propose":[55],"\\textbf{ReferDINO},":[56],"strong":[58],"RVOS":[59],"model":[60,142],"that":[61,96,114,151],"inherits":[62],"region-level":[63],"alignment":[65],"from":[66],"foundational":[67],"visual":[68],"grounding":[69],"models,":[70],"further":[73],"endowed":[74],"with":[75,163],"perception":[78],"cross-modal":[80],"detail,":[84],"ReferDINO":[85,153],"integrates":[86],"two":[87],"key":[88],"components:":[89],"1)":[90],"grounding-guided":[92],"deformable":[93],"mask":[94,103],"decoder":[95],"utilizes":[97],"location":[98],"progressively":[101],"guide":[102],"through":[105],"differentiable":[106],"deformation":[107],"mechanisms;":[108],"2)":[109],"an":[110],"object-consistent":[111],"temporal":[112],"enhancer":[113],"injects":[115],"pretrained":[116],"time-varying":[117],"features":[119],"into":[120],"inter-frame":[121],"interaction":[122],"capture":[124],"object-aware":[125],"dynamic":[126],"changes.":[127],"Moreover,":[128],"confidence-aware":[130],"query":[131],"pruning":[132],"strategy":[133],"designed":[135],"accelerate":[137],"decoding":[139],"without":[140],"compromising":[141],"performance.":[143],"Extensive":[144],"experimental":[145],"results":[146],"five":[148],"benchmarks":[149],"demonstrate":[150],"our":[152],"significantly":[154],"outperforms":[155],"previous":[156],"(e.g.,":[158],"+3.9%":[159],"(\\mathcal{J}&\\mathcal{F})":[160],"Ref-YouTube-VOS)":[162],"real-time":[164],"inference":[165],"speed":[166],"(51":[167],"FPS).":[168]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}