{"id":"https://openalex.org/W3207101999","doi":"https://doi.org/10.1145/3474085.3475192","title":"Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation","display_name":"Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3207101999","doi":"https://doi.org/10.1145/3474085.3475192","mag":"3207101999"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475192","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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/A5050583798","display_name":"Xiaoqi Zhao","orcid":"https://orcid.org/0009-0003-0332-4748"},"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":"Xiaoqi Zhao","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040300820","display_name":"Youwei Pang","orcid":"https://orcid.org/0000-0002-3950-0956"},"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":"Youwei Pang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101605461","display_name":"Jiaxing Yang","orcid":"https://orcid.org/0000-0003-4914-485X"},"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":"Jiaxing Yang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015500789","display_name":"Lihe Zhang","orcid":"https://orcid.org/0000-0002-9241-1688"},"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":"Lihe Zhang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006986293","display_name":"Huchuan Lu","orcid":"https://orcid.org/0000-0002-6668-9758"},"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":"Huchuan Lu","raw_affiliation_strings":["Dalian University of Technology &amp; Pengcheng Lab, Dalian&amp;Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology &amp; Pengcheng Lab, Dalian&amp;Shenzhen, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9108,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.92593668,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2645","last_page":"2653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"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":1.0,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9994999766349792,"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":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.8410264253616333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7158951759338379},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6798017621040344},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6043583154678345},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5751115083694458},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5750024318695068},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.531132161617279},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.455074667930603},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4386405348777771},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.43016839027404785},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4127340316772461},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4100220203399658},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3797565698623657},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19386714696884155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410264253616333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7158951759338379},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6798017621040344},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6043583154678345},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5751115083694458},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5750024318695068},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.531132161617279},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.455074667930603},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4386405348777771},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.43016839027404785},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4127340316772461},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4100220203399658},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3797565698623657},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19386714696884155},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475192","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4099999964237213,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W20683899","https://openalex.org/W1580389772","https://openalex.org/W1677182931","https://openalex.org/W1954128991","https://openalex.org/W1966025376","https://openalex.org/W1973054923","https://openalex.org/W1976409045","https://openalex.org/W1993713494","https://openalex.org/W2076756823","https://openalex.org/W2113708607","https://openalex.org/W2132083787","https://openalex.org/W2194775991","https://openalex.org/W2518874898","https://openalex.org/W2548527721","https://openalex.org/W2565639579","https://openalex.org/W2566030665","https://openalex.org/W2608825392","https://openalex.org/W2610147486","https://openalex.org/W2737008123","https://openalex.org/W2798825526","https://openalex.org/W2803442140","https://openalex.org/W2894890793","https://openalex.org/W2895340898","https://openalex.org/W2913977709","https://openalex.org/W2955084925","https://openalex.org/W2957408986","https://openalex.org/W2959581809","https://openalex.org/W2963299740","https://openalex.org/W2963782415","https://openalex.org/W2963896186","https://openalex.org/W2967199722","https://openalex.org/W2971252756","https://openalex.org/W2987391422","https://openalex.org/W2997487053","https://openalex.org/W3002301267","https://openalex.org/W3013402579","https://openalex.org/W3035422681","https://openalex.org/W3093213431","https://openalex.org/W3099392664","https://openalex.org/W3100280854","https://openalex.org/W3108043693","https://openalex.org/W3108421143","https://openalex.org/W3108822985","https://openalex.org/W3207172562","https://openalex.org/W4285886409","https://openalex.org/W6602610147"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W4386083130","https://openalex.org/W2023355163","https://openalex.org/W2117442182","https://openalex.org/W3111737715","https://openalex.org/W2069571255","https://openalex.org/W2081707527","https://openalex.org/W4385998088","https://openalex.org/W4367623556","https://openalex.org/W3125517176"],"abstract_inverted_index":{"Location":[0],"and":[1,19,38,89,150],"appearance":[2],"are":[3,94],"the":[4,27,34,57,82,87,91,110,115,120,130,154,161],"key":[5],"cues":[6],"for":[7,51],"video":[8,53],"object":[9,54,122],"segmentation.":[10,55],"Many":[11],"sources":[12],"such":[13],"as":[14],"RGB,":[15],"depth,":[16],"optical":[17,39,136],"flow":[18,137],"static":[20,116],"saliency":[21,117],"can":[22],"provide":[23],"useful":[24],"information":[25],"about":[26],"objects.":[28],"However,":[29],"existing":[30],"approaches":[31],"only":[32],"utilize":[33],"RGB":[35,37],"or":[36,119],"flow.":[40],"In":[41,97],"this":[42],"paper,":[43],"we":[44,73,99],"propose":[45],"a":[46,75],"novel":[47],"multi-source":[48,92],"fusion":[49],"network":[50,106],"zero-shot":[52],"With":[56],"help":[58],"of":[59,67,113],"interoceptive":[60],"spatial":[61,65],"attention":[62],"module":[63,78],"(ISAM),":[64],"importance":[66],"each":[68],"source":[69,164],"is":[70],"highlighted.":[71],"Furthermore,":[72],"design":[74],"feature":[76],"purification":[77],"(FPM)":[79],"to":[80,108,126],"filter":[81],"inter-source":[83],"incompatible":[84],"features.":[85],"By":[86],"ISAM":[88],"FPM,":[90],"features":[93],"effectively":[95],"fused.":[96],"addition,":[98],"put":[100],"forward":[101],"an":[102],"automatic":[103],"predictor":[104,118,123],"selection":[105],"(APS)":[107],"select":[109],"better":[111],"prediction":[112],"either":[114],"moving":[121],"in":[124],"order":[125],"prevent":[127],"over-reliance":[128],"on":[129,141],"failed":[131],"results":[132],"caused":[133],"by":[134],"low-quality":[135],"maps.":[138],"Extensive":[139],"experiments":[140],"three":[142],"challenging":[143],"public":[144],"benchmarks":[145],"(i.e.":[146],"DAVIS$_16":[147],"$,":[148],"Youtube-Objects":[149],"FBMS)":[151],"show":[152],"that":[153],"proposed":[155],"model":[156],"achieves":[157],"compelling":[158],"performance":[159],"against":[160],"state-of-the-arts.":[162],"The":[163],"code":[165],"will":[166],"be":[167],"publicly":[168],"available":[169],"at":[170],"https://github.com/Xiaoqi-Zhao-DLUT/Multi-Source-APS-ZVOS":[171]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
