{"id":"https://openalex.org/W4387951976","doi":"https://doi.org/10.1109/tip.2023.3326395","title":"Hierarchical Graph Pattern Understanding for Zero-Shot Video Object Segmentation","display_name":"Hierarchical Graph Pattern Understanding for Zero-Shot Video Object Segmentation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387951976","doi":"https://doi.org/10.1109/tip.2023.3326395","pmid":"https://pubmed.ncbi.nlm.nih.gov/37883290"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3326395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3326395","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/A5082756213","display_name":"Gensheng Pei","orcid":"https://orcid.org/0000-0002-7677-7487"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gensheng Pei","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-7677-7487","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074492050","display_name":"Fumin Shen","orcid":"https://orcid.org/0000-0001-7303-3231"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fumin Shen","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-7303-3231","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027545344","display_name":"Yazhou Yao","orcid":"https://orcid.org/0000-0002-0337-9410"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yazhou Yao","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0337-9410","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075177714","display_name":"Tao Chen","orcid":"https://orcid.org/0000-0001-8239-1698"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8239-1698","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024965898","display_name":"Xian\u2010Sheng Hua","orcid":"https://orcid.org/0000-0002-8232-5049"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian-Sheng Hua","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8232-5049","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng-Tao Shen","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7859,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74576867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"5909","last_page":"5920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9998000264167786,"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"}},"topics":[{"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9995999932289124,"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":0.8297514915466309},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.8002879023551941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6484865546226501},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6015757322311401},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5765727162361145},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4776962101459503},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4439462423324585},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.43266212940216064},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4246615171432495},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37976109981536865},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.20768731832504272},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1331566870212555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8297514915466309},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.8002879023551941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6484865546226501},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6015757322311401},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5765727162361145},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4776962101459503},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4439462423324585},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.43266212940216064},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4246615171432495},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37976109981536865},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.20768731832504272},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1331566870212555},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"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":2,"locations":[{"id":"doi:10.1109/tip.2023.3326395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3326395","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:37883290","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37883290","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":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G1591232902","display_name":null,"funder_award_id":"62102182","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1807802355","display_name":null,"funder_award_id":"BK20220938","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G1961316658","display_name":null,"funder_award_id":"2022M711635","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G210837444","display_name":null,"funder_award_id":"30923010303","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2855188217","display_name":null,"funder_award_id":"2022M721626","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G5858907394","display_name":null,"funder_award_id":"62202227","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6797194266","display_name":null,"funder_award_id":"BK20220934","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G8553687989","display_name":null,"funder_award_id":"BK20220936","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G8945461412","display_name":null,"funder_award_id":"2022M721628","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W845365781","https://openalex.org/W1943880421","https://openalex.org/W1973054923","https://openalex.org/W2027899226","https://openalex.org/W2115886973","https://openalex.org/W2116341502","https://openalex.org/W2161236525","https://openalex.org/W2194775991","https://openalex.org/W2212077366","https://openalex.org/W2412782625","https://openalex.org/W2470139095","https://openalex.org/W2550553598","https://openalex.org/W2574253917","https://openalex.org/W2610147486","https://openalex.org/W2769833683","https://openalex.org/W2792215676","https://openalex.org/W2889986507","https://openalex.org/W2895340898","https://openalex.org/W2916743882","https://openalex.org/W2921536280","https://openalex.org/W2955084925","https://openalex.org/W2957408986","https://openalex.org/W2963150697","https://openalex.org/W2963176022","https://openalex.org/W2963253279","https://openalex.org/W2963395775","https://openalex.org/W2963503215","https://openalex.org/W2963782415","https://openalex.org/W2963983744","https://openalex.org/W2967199722","https://openalex.org/W2967622921","https://openalex.org/W2981342784","https://openalex.org/W2986056979","https://openalex.org/W2987391422","https://openalex.org/W2990205821","https://openalex.org/W2999458807","https://openalex.org/W3009672847","https://openalex.org/W3009890678","https://openalex.org/W3035295069","https://openalex.org/W3035502324","https://openalex.org/W3049318984","https://openalex.org/W3080422828","https://openalex.org/W3094664776","https://openalex.org/W3102457447","https://openalex.org/W3108043693","https://openalex.org/W3109120382","https://openalex.org/W3109372619","https://openalex.org/W3109908659","https://openalex.org/W3111891682","https://openalex.org/W3117097536","https://openalex.org/W3118753716","https://openalex.org/W3119780697","https://openalex.org/W3126751243","https://openalex.org/W3127690492","https://openalex.org/W3139267983","https://openalex.org/W3166738350","https://openalex.org/W3168978642","https://openalex.org/W3170511209","https://openalex.org/W3174598330","https://openalex.org/W3174851543","https://openalex.org/W3175373394","https://openalex.org/W3175890016","https://openalex.org/W3202858245","https://openalex.org/W3203092180","https://openalex.org/W3203511368","https://openalex.org/W3204640376","https://openalex.org/W3207101999","https://openalex.org/W3212622989","https://openalex.org/W3212881378","https://openalex.org/W3212953023","https://openalex.org/W4200631531","https://openalex.org/W4226268139","https://openalex.org/W4304098211","https://openalex.org/W4312526532","https://openalex.org/W4319300199","https://openalex.org/W4366350967","https://openalex.org/W6685670348","https://openalex.org/W6736685754","https://openalex.org/W6759534164","https://openalex.org/W6779197543","https://openalex.org/W6782657842","https://openalex.org/W6784713722"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W579810227","https://openalex.org/W2952780262","https://openalex.org/W2181948922","https://openalex.org/W2979495269","https://openalex.org/W2384362569","https://openalex.org/W2754155766","https://openalex.org/W2963192850","https://openalex.org/W4287854977","https://openalex.org/W2769151336"],"abstract_inverted_index":{"The":[0,51],"optical":[1,26,34,43,57,109],"flow":[2,44,58],"guidance":[3],"strategy":[4],"is":[5,17,131,149],"ideal":[6],"for":[7,47,86,151],"obtaining":[8],"motion":[9,106,138],"information":[10],"of":[11,97,119,137],"objects":[12],"in":[13,20,38,65,99,142],"the":[14,42,56,94,113,117,156],"video.":[15],"It":[16],"widely":[18],"utilized":[19],"video":[21,88],"segmentation":[22,90],"tasks.":[23],"However,":[24],"existing":[25],"flow-based":[27],"methods":[28],"have":[29],"a":[30,48,66,72,123,143,147],"significant":[31],"dependency":[32],"on":[33,171],"flow,":[35],"which":[36],"results":[37],"poor":[39],"performance":[40,170],"when":[41],"estimation":[45],"fails":[46],"particular":[49],"scene.":[50],"temporal":[52],"consistency":[53],"provided":[54],"by":[55,63,93],"could":[59],"be":[60,186],"effectively":[61],"supplemented":[62],"modeling":[64],"structural":[67,101],"form.":[68],"This":[69],"paper":[70],"proposes":[71],"new":[73],"hierarchical":[74,81,124],"graph":[75,82,125],"neural":[76],"network":[77],"(GNN)":[78],"architecture,":[79],"dubbed":[80],"pattern":[83,126],"understanding":[84,155],"(HGPU),":[85],"zero-shot":[87],"object":[89],"(ZS-VOS).":[91],"Inspired":[92],"strong":[95],"ability":[96],"GNNs":[98],"capturing":[100],"relations,":[102],"HGPU":[103,167],"innovatively":[104],"leverages":[105],"cues":[107],"(i.e.,":[108],"flow)":[110],"to":[111,133,160],"enhance":[112],"high-order":[114],"representations":[115],"from":[116],"neighbors":[118],"target":[120],"frames.":[121],"Specifically,":[122],"encoder":[127],"with":[128],"message":[129],"aggregation":[130],"introduced":[132],"acquire":[134],"different":[135],"levels":[136],"and":[139,154,164,179,182],"appearance":[140],"features":[141],"sequential":[144],"manner.":[145],"Furthermore,":[146],"decoder":[148],"designed":[150],"hierarchically":[152],"parsing":[153],"transformed":[157],"multi-modal":[158],"contexts":[159],"achieve":[161],"more":[162],"accurate":[163],"robust":[165],"results.":[166],"achieves":[168],"state-of-the-art":[169],"four":[172],"publicly":[173],"available":[174],"benchmarks":[175],"(DAVIS-16,":[176],"YouTube-Objects,":[177],"Long-Videos":[178],"DAVIS-17).":[180],"Code":[181],"pre-trained":[183],"model":[184],"can":[185],"found":[187],"at":[188],"https://github.com/NUST-Machine-Intelligence-Laboratory/HGPU.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}