{"id":"https://openalex.org/W4294311190","doi":"https://doi.org/10.1109/tip.2022.3201603","title":"From Pixels to Semantics: Self-Supervised Video Object Segmentation With Multiperspective Feature Mining","display_name":"From Pixels to Semantics: Self-Supervised Video Object Segmentation With Multiperspective Feature Mining","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4294311190","doi":"https://doi.org/10.1109/tip.2022.3201603","pmid":"https://pubmed.ncbi.nlm.nih.gov/36054396"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2022.3201603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3201603","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5027057491","display_name":"Ruoqi Li","orcid":"https://orcid.org/0000-0003-3730-9370"},"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":true,"raw_author_name":"Ruoqi Li","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398548","display_name":"Yifan Wang","orcid":"https://orcid.org/0000-0002-1911-2526"},"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":"Yifan Wang","raw_affiliation_strings":["School of Innovation and Entrepreneurship, Dalian University of Technology, Dalian, China","Ningbo Institute, Dalian University of Technology, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"School of Innovation and Entrepreneurship, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Ningbo Institute, Dalian University of Technology, Ningbo, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318892","display_name":"Lijun Wang","orcid":"https://orcid.org/0000-0003-2538-8358"},"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":"Lijun Wang","raw_affiliation_strings":["School of Artificial Intelligence, Dalian University of Technology, Dalian, China","Ningbo Institute, Dalian University of Technology, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Ningbo Institute, Dalian University of Technology, Ningbo, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","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":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","Ningbo Institute, Dalian University of Technology, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Ningbo Institute, Dalian University of Technology, Ningbo, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003257736","display_name":"Xiaopeng Wei","orcid":"https://orcid.org/0000-0002-8497-611X"},"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":"Xiaopeng Wei","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100381999","display_name":"Qiang Zhang","orcid":"https://orcid.org/0000-0003-3776-9799"},"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":"Qiang Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5027057491"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.8151,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73065078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"31","issue":null,"first_page":"5801","last_page":"5812"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.8143823146820068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7760941982269287},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6858752965927124},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5859732031822205},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5821175575256348},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5210953950881958},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5147840976715088},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4744994342327118},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47376421093940735},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.47226157784461975},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.45790836215019226},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4493086338043213},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44472256302833557},{"id":"https://openalex.org/keywords/closing","display_name":"Closing (real estate)","score":0.42916280031204224},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.41690653562545776},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.27285993099212646},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08357146382331848}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143823146820068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7760941982269287},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6858752965927124},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5859732031822205},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5821175575256348},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5210953950881958},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5147840976715088},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4744994342327118},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47376421093940735},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.47226157784461975},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.45790836215019226},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4493086338043213},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44472256302833557},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.42916280031204224},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41690653562545776},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27285993099212646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08357146382331848},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2022.3201603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3201603","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:36054396","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36054396","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4132881375","display_name":null,"funder_award_id":"61725202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4246685449","display_name":null,"funder_award_id":"61906031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5100944270","display_name":null,"funder_award_id":"61829102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6247817811","display_name":null,"funder_award_id":"U1903215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G698290307","display_name":null,"funder_award_id":"62006036","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8273014382","display_name":null,"funder_award_id":"2018AAA0102001","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W1586994488","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2221625691","https://openalex.org/W2470139095","https://openalex.org/W2550553598","https://openalex.org/W2564998703","https://openalex.org/W2595280704","https://openalex.org/W2597655663","https://openalex.org/W2610147486","https://openalex.org/W2706729717","https://openalex.org/W2752782242","https://openalex.org/W2794669410","https://openalex.org/W2798441772","https://openalex.org/W2884585870","https://openalex.org/W2889658408","https://openalex.org/W2890447039","https://openalex.org/W2895340641","https://openalex.org/W2916743882","https://openalex.org/W2916797271","https://openalex.org/W2921536280","https://openalex.org/W2955058313","https://openalex.org/W2955084925","https://openalex.org/W2962825871","https://openalex.org/W2963091558","https://openalex.org/W2963131444","https://openalex.org/W2963227409","https://openalex.org/W2963253279","https://openalex.org/W2963325280","https://openalex.org/W2963426332","https://openalex.org/W2963495494","https://openalex.org/W2963732700","https://openalex.org/W2963773230","https://openalex.org/W2963827464","https://openalex.org/W2964157492","https://openalex.org/W2964218467","https://openalex.org/W2964343881","https://openalex.org/W2964700958","https://openalex.org/W2967622921","https://openalex.org/W2987761193","https://openalex.org/W2990205821","https://openalex.org/W3034915791","https://openalex.org/W3046449233","https://openalex.org/W3049318984","https://openalex.org/W3102457447","https://openalex.org/W3110030584","https://openalex.org/W3111891682","https://openalex.org/W3112815474","https://openalex.org/W3121052760","https://openalex.org/W3126751243","https://openalex.org/W3145659481","https://openalex.org/W3158464135","https://openalex.org/W3159481202","https://openalex.org/W3186378100","https://openalex.org/W3202858245","https://openalex.org/W4226071614","https://openalex.org/W4302374929","https://openalex.org/W6618372016","https://openalex.org/W6680171035","https://openalex.org/W6704241340","https://openalex.org/W6735377749","https://openalex.org/W6739520758","https://openalex.org/W6739901393","https://openalex.org/W6743731764","https://openalex.org/W6743811873","https://openalex.org/W6753038380","https://openalex.org/W6754033419","https://openalex.org/W6754852571","https://openalex.org/W6758168472","https://openalex.org/W6759534164","https://openalex.org/W6762196805","https://openalex.org/W6767026726","https://openalex.org/W6780180733","https://openalex.org/W6781554172","https://openalex.org/W6788280241","https://openalex.org/W6794071484","https://openalex.org/W6799072846"],"related_works":["https://openalex.org/W2116422677","https://openalex.org/W2517007886","https://openalex.org/W2383994331","https://openalex.org/W1522019333","https://openalex.org/W278047738","https://openalex.org/W2076369646","https://openalex.org/W2373884197","https://openalex.org/W4244817184","https://openalex.org/W2961923709","https://openalex.org/W2516969888"],"abstract_inverted_index":{"Existing":[0],"self-supervised":[1,48,129,145],"methods":[2,147],"pose":[3],"one-shot":[4],"video":[5],"object":[6],"segmentation":[7,14,88],"(O-VOS)":[8],"as":[9],"pixel-level":[10,52,59],"matching":[11],"to":[12,116],"enable":[13],"mask":[15],"propagation":[16],"across":[17],"frames.":[18],"However,":[19],"the":[20,86,124,127,142],"two":[21],"tasks":[22],"are":[23],"not":[24,106],"fully":[25,150],"equivalent":[26],"since":[27],"O-VOS":[28],"is":[29,62],"more":[30,118],"reliant":[31],"on":[32,135],"semantic":[33],"correspondence":[34,53,60],"rather":[35],"than":[36],"accurate":[37],"pixel":[38],"matching.":[39,121],"To":[40],"remedy":[41],"this":[42],"issue,":[43],"we":[44,92,131],"explore":[45],"a":[46,82,95],"new":[47,96],"framework":[49],"that":[50],"integrates":[51],"learning":[54,61,146],"with":[55,99],"semantic-level":[56,75],"adaptation.":[57],"The":[58],"performed":[63],"through":[64],"photometric":[65],"reconstruction":[66],"of":[67,85],"adjacent":[68],"RGB":[69],"frames":[70],"during":[71],"offline":[72],"training,":[73],"while":[74],"adaption":[76],"operates":[77],"at":[78],"test-time":[79],"by":[80],"enforcing":[81],"bi-directional":[83],"agreement":[84],"predicted":[87],"masks.":[89],"In":[90],"addition,":[91],"further":[93,139],"propose":[94],"network":[97,125],"architecture":[98],"multi-perspective":[100],"feature":[101],"mining":[102],"mechanism":[103],"which":[104],"can":[105],"only":[107],"enhance":[108],"reliable":[109],"features":[110],"but":[111],"also":[112],"suppress":[113],"noisy":[114],"ones":[115],"facilitate":[117],"robust":[119],"image":[120],"By":[122],"training":[123],"using":[126],"proposed":[128],"framework,":[130],"achieve":[132],"state-of-the-art":[133],"performance":[134],"widely":[136],"adopted":[137],"datasets,":[138],"closing":[140],"up":[141],"gap":[143],"between":[144],"and":[148],"their":[149],"supervised":[151],"counterparts.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}