{"id":"https://openalex.org/W4415707891","doi":"https://doi.org/10.1109/icme59968.2025.11209578","title":"SLGN: Spatiotemporal Language-Guided Graph Network for Referring Video Segmentation","display_name":"SLGN: Spatiotemporal Language-Guided Graph Network for Referring Video Segmentation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707891","doi":"https://doi.org/10.1109/icme59968.2025.11209578"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5109737165","display_name":"Rongrong Lian","orcid":"https://orcid.org/0009-0005-3262-6651"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Lian","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100416428","display_name":"Xiangdong Li","orcid":"https://orcid.org/0000-0001-6145-2084"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangdong Li","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101514142","display_name":"Zhenkai Wu","orcid":"https://orcid.org/0009-0000-0613-0584"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenkai Wu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076517058","display_name":"Mengting Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengting Ma","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057842914","display_name":"Wayne Zhang","orcid":"https://orcid.org/0000-0002-8415-1062"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.2702564,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9627000093460083,"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":0.9627000093460083,"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":0.013799999840557575,"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":0.00570000009611249,"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/construct","display_name":"Construct (python library)","score":0.6703000068664551},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6539999842643738},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.583899974822998},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.46459999680519104},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4575999975204468},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.414000004529953},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.39879998564720154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7694000005722046},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6703000068664551},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6539999842643738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6338000297546387},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.46459999680519104},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4302999973297119},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.39879998564720154},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.38530001044273376},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3492000102996826},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.32350000739097595},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C5134670","wikidata":"https://www.wikidata.org/wiki/Q1626444","display_name":"Cut","level":4,"score":0.2615000009536743},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320336552","display_name":"Science and Technology Innovation 2025 Major Project of Ningbo","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2194775991","https://openalex.org/W2889986507","https://openalex.org/W2962942822","https://openalex.org/W2963354481","https://openalex.org/W2980088508","https://openalex.org/W2983693499","https://openalex.org/W3034325957","https://openalex.org/W3034578524","https://openalex.org/W3035316078","https://openalex.org/W3104844437","https://openalex.org/W3178075329","https://openalex.org/W3215899623","https://openalex.org/W4200631575","https://openalex.org/W4226024706","https://openalex.org/W4283796148","https://openalex.org/W4285601347","https://openalex.org/W4288052482","https://openalex.org/W4312560592","https://openalex.org/W4312690830","https://openalex.org/W4312815172","https://openalex.org/W4386172486","https://openalex.org/W4390603537","https://openalex.org/W4390872515","https://openalex.org/W4390872914","https://openalex.org/W4390873204","https://openalex.org/W4390873614","https://openalex.org/W4390874496","https://openalex.org/W4393178550","https://openalex.org/W4407179814","https://openalex.org/W4407451533"],"related_works":[],"abstract_inverted_index":{"Referring":[0],"video":[1,78],"segmentation":[2,79],"uses":[3,94],"text":[4,126],"descriptions":[5,127],"to":[6,15,52,80,100,110,131],"identify":[7],"and":[8,66,97,106,128],"segment":[9],"objects.":[10],"This":[11],"requires":[12],"the":[13,23,35,62,82,140],"model":[14,111],"effectively":[16],"perform":[17],"spatiotemporal":[18,113],"modeling":[19],"of":[20,25],"videos":[21],"under":[22],"guidance":[24],"linguistic":[26],"information.":[27],"However,":[28],"previous":[29],"works":[30],"have":[31,42],"not":[32],"explicitly":[33],"considered":[34],"differences":[36],"among":[37],"objects":[38,65,105,130],"in":[39,54,68,153],"videos,":[40,69],"nor":[41],"they":[43],"adequately":[44],"aligned":[45],"language":[46,67],"information":[47],"with":[48],"object-level":[49],"features,":[50],"leading":[51],"misclassifications":[53],"complex":[55],"scenes.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,85,116],"rethink":[61],"relationship":[63],"between":[64,104],"introducing":[70],"a":[71,87,118],"novel":[72],"graph-based":[73],"network":[74],"(SLGN)":[75],"for":[76],"referring":[77],"address":[81],"problem.":[83],"Specifically,":[84],"design":[86,117],"Spatiotemporal":[88],"Graph":[89,120],"Perception":[90,121],"(SGP)":[91],"module":[92,123],"that":[93,124,146],"temporal,":[95],"semantics,":[96],"positional":[98],"priors":[99],"construct":[101,132],"multidimensional":[102],"edges":[103],"employs":[107],"graph":[108],"convolution":[109],"their":[112],"relationships.":[114],"Meanwhile,":[115],"Clue":[119],"(CGP)":[122],"leverages":[125],"potential":[129],"an":[133],"object-word":[134],"graph,":[135],"achieving":[136],"modality":[137],"alignment":[138],"at":[139],"object":[141],"level.":[142],"Experimental":[143],"results":[144],"demonstrate":[145],"our":[147],"method":[148],"outperforms":[149],"recent":[150],"representative":[151],"methods":[152],"performance.":[154]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-30T00:00:00"}