{"id":"https://openalex.org/W7163162425","doi":"https://doi.org/10.1109/tip.2026.3697653","title":"Event-Aware Instructed Assistant for Referring Video Segmentation","display_name":"Event-Aware Instructed Assistant for Referring Video Segmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7163162425","doi":"https://doi.org/10.1109/tip.2026.3697653","pmid":"https://pubmed.ncbi.nlm.nih.gov/42228656"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3697653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3697653","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100329175","display_name":"Jinyu Liu","orcid":"https://orcid.org/0000-0002-1799-019X"},"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":"Jinyu Liu","raw_affiliation_strings":["Institute of Big Data, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-6658-1175","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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137620540","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":false,"raw_author_name":"Henghui Ding","raw_affiliation_strings":["Institute of Big Data, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4868-6526","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"]}]},{"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/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"],"is_corresponding":false,"raw_author_name":"Shuting He","raw_affiliation_strings":["Shanghai University of Finance and Economics, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101686143","display_name":"Yan Jiang","orcid":"https://orcid.org/0009-0006-1219-7770"},"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"],"raw_orcid":"https://orcid.org/0000-0002-1907-8567","affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69588742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"6055","last_page":"6067"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.5866000056266785,"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":0.5866000056266785,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.0763000026345253,"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":0.06620000302791595,"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/image-segmentation","display_name":"Image segmentation","score":0.5497999787330627},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5271000266075134},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4074999988079071},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.37439998984336853},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3334999978542328},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33340001106262207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7186999917030334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.694599986076355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6820999979972839},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5497999787330627},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5271000266075134},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4074999988079071},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.37439998984336853},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.2603999972343445},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2533000111579895},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3697653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3697653","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:42228656","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42228656","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"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"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"referring":[1,183],"video":[2,8,22,44,64,78,98,129,184],"segmentation":[3,185],"methods":[4],"often":[5,95],"treat":[6],"a":[7,10,21,30,63,66,97,105,109,128,139],"as":[9],"single":[11],"event":[12,107],"consisting":[13],"of":[14,68,142],"multiple":[15,25],"images,":[16],"overlooking":[17],"the":[18,32,39,43,89,143,152,182],"fact":[19],"that":[20,91],"typically":[23],"contains":[24],"distinct":[26],"events.":[27],"Under":[28],"such":[29],"mechanism,":[31],"model":[33],"needs":[34],"to":[35,51,61,65,126,137,154],"directly":[36],"understand":[37,76],"all":[38],"complex":[40,77],"content":[41,79],"in":[42,80,157,180],"and":[45,53,75,188],"text,":[46],"which":[47,121,150],"can":[48],"easily":[49],"lead":[50],"confusion":[52],"hallucinations.":[54],"To":[55],"address":[56],"this":[57],"issue,":[58],"we":[59,146],"propose":[60,147],"decompose":[62],"set":[67],"simple":[69,131],"events":[70],"by":[71,160],"learnable":[72],"Event":[73,124],"Query,":[74],"an":[81,115],"event-by-event,":[82],"easy-to-understand":[83],"manner.":[84],"This":[85],"is":[86],"based":[87],"on":[88,172],"observation":[90],"natural":[92],"language":[93],"expressions":[94],"divide":[96],"into":[99,130],"distinct,":[100],"text-related":[101],"segments,":[102],"each":[103],"representing":[104],"separate":[106],"within":[108],"compound":[110],"event.":[111],"We":[112],"introduce":[113],"EVIS,":[114],"Event-Aware":[116],"Video":[117],"Instructed":[118],"Segmentation":[119],"Assistant,":[120],"utilizes":[122],"text-guided":[123],"Queries":[125],"partition":[127],"events,":[132],"extracting":[133],"event-aware":[134],"visual-text":[135],"features":[136,164],"achieve":[138],"hierarchical":[140],"understanding":[141],"video.":[144],"Additionally,":[145],"Object-Pixel-Hybrid":[148],"Learning,":[149],"enables":[151],"MLLMs":[153],"track":[155],"targets":[156],"long-term":[158],"videos":[159],"integrating":[161],"fine-grained":[162],"pixel":[163],"with":[165],"prior":[166],"object":[167],"queries.":[168],"Extensive":[169],"experimental":[170],"results":[171],"5":[173],"public":[174],"benchmarks":[175],"demonstrate":[176],"EVIS's":[177],"strong":[178],"performance":[179],"addressing":[181],"task.":[186],"Code":[187],"trained":[189],"models":[190],"will":[191],"be":[192],"publicly":[193],"released.":[194]},"counts_by_year":[],"updated_date":"2026-06-11T06:19:23.411458","created_date":"2026-06-03T00:00:00"}