{"id":"https://openalex.org/W4414871258","doi":"https://doi.org/10.1109/tcsvt.2025.3618119","title":"LTCA: Long-Range Temporal Context Attention for Referring Video Object Segmentation","display_name":"LTCA: Long-Range Temporal Context Attention for Referring Video Object Segmentation","publication_year":2025,"publication_date":"2025-10-06","ids":{"openalex":"https://openalex.org/W4414871258","doi":"https://doi.org/10.1109/tcsvt.2025.3618119"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3618119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3618119","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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/A5035332982","display_name":"Cilin Yan","orcid":"https://orcid.org/0000-0001-9754-129X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cilin Yan","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9754-129X","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779751","display_name":"Jingyun Wang","orcid":"https://orcid.org/0000-0002-9073-2349"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyun Wang","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011488839","display_name":"Guoliang Kang","orcid":"https://orcid.org/0000-0003-1978-2025"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Kang","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1978-2025","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75681206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"36","issue":"3","first_page":"2968","last_page":"2979"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9973000288009644,"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":0.9918000102043152,"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/context","display_name":"Context (archaeology)","score":0.6381000280380249},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5824000239372253},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5810999870300293},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.5577999949455261},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5543000102043152},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5418000221252441},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.47530001401901245},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.42989999055862427},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4088999927043915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8118000030517578},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6381000280380249},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5824000239372253},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5810999870300293},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.5577999949455261},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5543000102043152},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5418000221252441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5012999773025513},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.47530001401901245},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.42989999055862427},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.35249999165534973},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.34369999170303345},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3382999897003174},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3248000144958496},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3077000081539154},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.3050000071525574},{"id":"https://openalex.org/C2781368080","wikidata":"https://www.wikidata.org/wiki/Q501688","display_name":"Context awareness","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3618119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3618119","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W2006354339","https://openalex.org/W2114766326","https://openalex.org/W2167292325","https://openalex.org/W2251512949","https://openalex.org/W2302548814","https://openalex.org/W2566724781","https://openalex.org/W2737682710","https://openalex.org/W2798556392","https://openalex.org/W2894964039","https://openalex.org/W2912290468","https://openalex.org/W2961553857","https://openalex.org/W2962942822","https://openalex.org/W2963109634","https://openalex.org/W2963125010","https://openalex.org/W2963150697","https://openalex.org/W2963225012","https://openalex.org/W2963354481","https://openalex.org/W2963840672","https://openalex.org/W2965373594","https://openalex.org/W2974686944","https://openalex.org/W2976669726","https://openalex.org/W2980088508","https://openalex.org/W2982723417","https://openalex.org/W2983693499","https://openalex.org/W3004019157","https://openalex.org/W3014545861","https://openalex.org/W3096719817","https://openalex.org/W3104844437","https://openalex.org/W3178075329","https://openalex.org/W3196651696","https://openalex.org/W3202509201","https://openalex.org/W3204647170","https://openalex.org/W3211329537","https://openalex.org/W3215899623","https://openalex.org/W4200631575","https://openalex.org/W4226024706","https://openalex.org/W4283796148","https://openalex.org/W4293732316","https://openalex.org/W4304084115","https://openalex.org/W4307504011","https://openalex.org/W4309368547","https://openalex.org/W4312294051","https://openalex.org/W4312690830","https://openalex.org/W4312815172","https://openalex.org/W4312981390","https://openalex.org/W4313007081","https://openalex.org/W4313054169","https://openalex.org/W4320489250","https://openalex.org/W4361983876","https://openalex.org/W4379928661","https://openalex.org/W4379984073","https://openalex.org/W4385245566","https://openalex.org/W4386076180","https://openalex.org/W4389473983","https://openalex.org/W4390872626","https://openalex.org/W4390872762","https://openalex.org/W4390872868","https://openalex.org/W4390872914","https://openalex.org/W4390873429","https://openalex.org/W4390874496","https://openalex.org/W4391021462","https://openalex.org/W4391428214","https://openalex.org/W4393178550","https://openalex.org/W4394842360","https://openalex.org/W4399213100","https://openalex.org/W4399649615","https://openalex.org/W4399944027","https://openalex.org/W4400032968","https://openalex.org/W4401357939","https://openalex.org/W4402727649","https://openalex.org/W4409366257","https://openalex.org/W4411245222","https://openalex.org/W7133193597","https://openalex.org/W7133232210"],"related_works":[],"abstract_inverted_index":{"Referring":[0],"Video":[1],"Segmentation":[2],"(RVOS)":[3],"aims":[4],"to":[5,15,19,32,54,65,99,123,137,151,161,163,175,185,192],"segment":[6],"objects":[7],"in":[8,146],"videos":[9,31],"given":[10],"linguistic":[11],"expressions.":[12],"The":[13,234],"key":[14],"solving":[16],"RVOS":[17],"is":[18,236],"extract":[20],"long-range":[21,93],"temporal":[22,60,94],"context":[23,95,102,112,140,197],"information":[24,103,113,141],"from":[25,114,171],"the":[26,34,47,75,81,110,125,177,189,195,223],"interactions":[27],"of":[28,37,59,83,149,167,218],"expressions":[29],"and":[30,72,74,127,142,220,228],"depict":[33],"dynamic":[35],"attributes":[36],"each":[38,159],"object.":[39],"Previous":[40],"works":[41],"either":[42],"adopt":[43],"attention":[44,53,96,134,145],"across":[45,135],"all":[46,188],"frames":[48,136],"or":[49],"stack":[50,119,148],"dense":[51],"local":[52,121,139],"achieve":[55],"a":[56,67,131,147,153,164,172,182],"global":[57,101,111,154,173,183,196],"view":[58],"context.":[61],"However,":[62],"they":[63],"fail":[64],"strike":[66],"good":[68],"balance":[69,124],"between":[70],"locality":[71,126],"globality,":[73],"computation":[76],"complexity":[77],"significantly":[78],"increases":[79],"with":[80,187],"increase":[82],"video":[84,209],"length.":[85],"In":[86],"this":[87],"paper,":[88],"we":[89,108,118,157,180],"propose":[90],"an":[91,216],"effective":[92],"(LTCA)":[97],"mechanism":[98],"aggregate":[100,109,138],"into":[104],"object":[105],"features.":[106],"Specifically,":[107],"two":[115],"aspects.":[116],"Firstly,":[117],"sparse":[120],"attentions":[122],"globality.":[128,178],"We":[129],"design":[130,181],"dilated":[132],"window":[133],"perform":[143],"such":[144],"layers":[150],"enable":[152,158],"view.":[155],"Further,":[156],"query":[160,184],"attend":[162],"small":[165],"group":[166],"keys":[168],"randomly":[169],"selected":[170],"pool":[174],"enhance":[176],"Secondly,":[179],"interact":[186],"other":[190],"queries":[191],"directly":[193],"encode":[194],"information.":[198],"Experiments":[199],"show":[200],"our":[201,213],"method":[202,214],"achieves":[203],"new":[204],"state-of-the-art":[205],"on":[206,222],"four":[207],"referring":[208],"segmentation":[210],"benchmarks.":[211],"Notably,":[212],"shows":[215],"improvement":[217],"11.3%":[219],"8.3%":[221],"MeViS":[224],"<italic":[225,229],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[226,230],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">val<sup>u</sup></i>":[227],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">val</i>":[231],"datasets":[232],"respectively.":[233],"code":[235],"available":[237],"at":[238],"https://github.com/cilinyan/LTCA.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}