{"id":"https://openalex.org/W7164809780","doi":"https://doi.org/10.1145/3805622.3810836","title":"Locate Core, Refine Path: A Training-Free Closed-Loop Paradigm for Referring Video Object Segmentation","display_name":"Locate Core, Refine Path: A Training-Free Closed-Loop Paradigm for Referring Video Object Segmentation","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164809780","doi":"https://doi.org/10.1145/3805622.3810836"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810836","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810836","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810836","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101395803","display_name":"Jizhe Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jizhe Yu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0008-8365-2317","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454575","display_name":"Haitao Zhang","orcid":"https://orcid.org/0000-0001-5949-6483"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0004-0232-5084","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004616750","display_name":"Xiya Bu","orcid":"https://orcid.org/0009-0008-8324-2422"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiya Bu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0008-8324-2422","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138627988","display_name":"Yuhang Duan","orcid":"https://orcid.org/0009-0007-7667-3956"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Duan","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0007-7667-3956","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005151695","display_name":"Xiaoshuai Wu","orcid":"https://orcid.org/0000-0001-6241-3546"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Wu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0007-6350-3608","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002476102","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0001-8013-4372"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-8013-4372","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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":0.93411769,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1568","last_page":"1572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.25440001487731934,"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":0.25440001487731934,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.2282000035047531,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.188400000333786,"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/object","display_name":"Object (grammar)","score":0.6517000198364258},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6439999938011169},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6294000148773193},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6284999847412109},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5724999904632568},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48510000109672546},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.46700000762939453},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4577000141143799},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4530999958515167},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41260001063346863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.652899980545044},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6517000198364258},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6439999938011169},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6294000148773193},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6284999847412109},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5724999904632568},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5430999994277954},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48510000109672546},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.46700000762939453},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4530999958515167},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.38519999384880066},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.3578999936580658},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3529999852180481},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.2745000123977661},{"id":"https://openalex.org/C93058836","wikidata":"https://www.wikidata.org/wiki/Q1453572","display_name":"Chain code","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.26420000195503235}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810836","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810836","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810836","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810836","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2470139095","https://openalex.org/W2962942822","https://openalex.org/W3104844437","https://openalex.org/W4226024706","https://openalex.org/W4312396403","https://openalex.org/W4390872868","https://openalex.org/W4390872914","https://openalex.org/W4390873614","https://openalex.org/W4392903908","https://openalex.org/W4392904293","https://openalex.org/W4392904373","https://openalex.org/W4402727770","https://openalex.org/W4402753899","https://openalex.org/W4402754134","https://openalex.org/W4402754173","https://openalex.org/W4408354047","https://openalex.org/W4409129254","https://openalex.org/W4409368119","https://openalex.org/W4413146091","https://openalex.org/W4413146469","https://openalex.org/W4413147705","https://openalex.org/W4413156002","https://openalex.org/W7084032685","https://openalex.org/W7133238033","https://openalex.org/W7160070739","https://openalex.org/W7160136676"],"related_works":[],"abstract_inverted_index":{"Referring":[0],"video":[1,13],"object":[2,11],"segmentation":[3],"(RVOS)":[4],"aims":[5],"to":[6,67,117],"dynamically":[7],"segment":[8],"a":[9,17,32,79],"target":[10],"across":[12],"sequences":[14],"based":[15],"on":[16,36],"given":[18],"natural":[19],"language":[20,39],"expression.":[21],"Although":[22],"recent":[23],"decoupled":[24],"methods":[25],"surpass":[26],"end-to-end":[27],"models,":[28],"they":[29],"suffer":[30],"from":[31],"critical":[33],"trade-off:":[34],"relying":[35],"fine-tuned":[37],"large":[38],"models":[40],"for":[41],"key":[42],"frame":[43,95],"selection":[44,96],"incurs":[45],"high":[46],"computational":[47],"costs,":[48],"whereas":[49],"employing":[50],"sparse":[51],"sampling":[52],"risks":[53],"missing":[54],"optimal":[55],"reference":[56],"frames.":[57],"Furthermore,":[58],"the":[59,106],"subsequent":[60],"mask":[61],"propagation":[62],"lacks":[63],"self-correction":[64],"mechanisms,":[65],"leading":[66],"irreversible":[68],"cumulative":[69],"errors":[70],"over":[71],"time.":[72],"In":[73],"this":[74],"work,":[75],"we":[76],"propose":[77],"LCRP,":[78],"training-free":[80],"framework":[81],"driven":[82],"by":[83,97],"two":[84],"novel":[85],"components.":[86],"The":[87],"Hybrid":[88],"Candidate":[89],"Sampling":[90],"(HCS)":[91],"module":[92,110],"significantly":[93],"improves":[94],"integrating":[98],"lightweight":[99],"semantic":[100],"parsing":[101],"with":[102],"CLIP-based":[103],"filtering.":[104],"Meanwhile,":[105],"Multi-Anchor":[107],"Refinement":[108],"(MAR)":[109],"utilizes":[111],"anchor":[112],"frames":[113],"as":[114],"dynamic":[115],"checkpoints":[116],"detect":[118],"temporal":[119],"drift":[120],"and":[121],"execute":[122],"localized":[123],"re-propagation.":[124],"Extensive":[125],"experiments":[126],"indicate":[127],"that":[128],"our":[129],"proposed":[130],"method":[131],"achieves":[132],"state-of-the-art":[133],"results.":[134],"Code":[135],"is":[136],"available":[137],"at":[138],"https://github.com/Crystal535/Locate-Core-Refine-Path.":[139]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}