{"id":"https://openalex.org/W4416404164","doi":"https://doi.org/10.1109/iccv51701.2025.01339","title":"Structure Matters: Revisiting Boundary Refinement in Video Object Segmentation","display_name":"Structure Matters: Revisiting Boundary Refinement in Video Object Segmentation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416404164","doi":"https://doi.org/10.1109/iccv51701.2025.01339"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01339","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.18944","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039064197","display_name":"Guanyi Qin","orcid":"https://orcid.org/0000-0001-8414-9870"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Guanyi Qin","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008644880","display_name":"Ziyue Wang","orcid":"https://orcid.org/0009-0000-6991-2882"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ziyue Wang","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111350501","display_name":"Daiyun Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Daiyun Shen","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054309906","display_name":"Haofeng Liu","orcid":"https://orcid.org/0009-0009-0320-3536"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haofeng Liu","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083942931","display_name":"Hantao Zhou","orcid":"https://orcid.org/0000-0002-0514-0905"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hantao Zhou","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011430407","display_name":"Junde Wu","orcid":"https://orcid.org/0000-0002-7174-9276"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junde Wu","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011299161","display_name":"Runze Hu","orcid":"https://orcid.org/0000-0002-6366-3763"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runze Hu","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050163233","display_name":"Yueming Jin","orcid":"https://orcid.org/0000-0003-3775-3877"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yueming Jin","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"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":0.31216618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14431","last_page":"14442"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.8288999795913696,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.8288999795913696,"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":0.11069999635219574,"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":0.015699999406933784,"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":0.7089999914169312},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6726999878883362},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5127999782562256},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49880000948905945},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4794999957084656},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.45010000467300415},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.44999998807907104},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.43650001287460327},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.42579999566078186}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7716000080108643},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458999752998352},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7215999960899353},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7089999914169312},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6726999878883362},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5127999782562256},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49880000948905945},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4794999957084656},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.45010000467300415},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.44999998807907104},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.42579999566078186},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41850000619888306},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.4041000008583069},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.38449999690055847},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.3327000141143799},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.3280999958515167},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C14705441","wikidata":"https://www.wikidata.org/wiki/Q597183","display_name":"Canny edge detector","level":5,"score":0.2547000050544739},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.25360000133514404},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01339","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:2507.18944","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.18944","pdf_url":"https://arxiv.org/pdf/2507.18944","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.18944","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.18944","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.18944","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.18944","pdf_url":"https://arxiv.org/pdf/2507.18944","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Given":[0],"an":[1,115,146],"object":[2,16,44,73,109],"mask,":[3],"Semi-supervised":[4],"Video":[5],"Object":[6],"Segmentation":[7,74],"(SVOS)":[8],"technique":[9],"aims":[10],"to":[11,91,134,164],"track":[12],"and":[13,46,54,107,119,159,181],"segment":[14],"the":[15,56,96,104,111,121,170],"across":[17],"video":[18,72],"frames,":[19],"serving":[20],"as":[21],"a":[22,68,84,195],"fundamental":[23],"task":[24],"in":[25,42,63,138],"computer":[26],"vision.":[27],"Although":[28],"recent":[29],"memory-based":[30],"methods":[31],"demonstrate":[32,155],"potential,":[33],"they":[34],"often":[35],"struggle":[36],"with":[37,76],"scenes":[38],"involving":[39],"occlusion,":[40],"particularly":[41],"handling":[43],"interactions":[45],"high":[47],"feature":[48],"similarity.":[49],"To":[50],"address":[51,136],"these":[52],"issues":[53],"meet":[55],"real-time":[57],"processing":[58],"requirements":[59],"of":[60,98,173,184,198],"downstream":[61],"applications,":[62],"this":[64],"paper,":[65],"we":[66],"propose":[67],"novel":[69],"bOundary":[70],"Amendment":[71],"method":[75],"Inherent":[77],"Structure":[78],"refinement,":[79],"hereby":[80],"named":[81],"OASIS.":[82],"Specifically,":[83],"lightweight":[85],"structure":[86,117],"refinement":[87],"module":[88,112],"is":[89,132],"proposed":[90,142],"enhance":[92],"segmentation":[93],"accuracy.":[94],"With":[95],"fusion":[97],"rough":[99],"edge":[100],"priors":[101],"captured":[102],"by":[103,123],"Canny":[105],"filter":[106],"stored":[108],"features,":[110],"can":[113],"generate":[114],"object-level":[116],"map":[118],"refine":[120],"representations":[122],"highlighting":[124],"boundary":[125],"features.":[126],"Evidential":[127],"learning":[128],"for":[129],"uncertainty":[130],"estimation":[131],"introduced":[133],"further":[135],"challenges":[137],"occluded":[139],"regions.":[140],"The":[141],"method,":[143],"OASIS,":[144],"maintains":[145],"efficient":[147],"design,":[148],"yet":[149],"extensive":[150],"experiments":[151],"on":[152,177,188,201],"challenging":[153],"benchmarks":[154],"its":[156],"superior":[157],"performance":[158],"competitive":[160,196],"inference":[161],"speed":[162,197],"compared":[163],"other":[165],"state-of-the-art":[166],"methods,":[167],"i.e.,":[168],"achieving":[169],"F":[171],"values":[172,183],"91.6":[174],"(vs.":[175,186],"89.7":[176],"DAVIS-17":[178],"validation":[179,191],"set)":[180,192],"G":[182],"86.6":[185],"86.2":[187],"YouTubeVOS":[189],"2019":[190],"while":[193],"maintaining":[194],"48":[199],"FPS":[200],"DAVIS.":[202]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}