{"id":"https://openalex.org/W4205268584","doi":"https://doi.org/10.1109/tmm.2022.3141891","title":"Transformer-Based Efficient Salient Instance Segmentation Networks With Orientative Query","display_name":"Transformer-Based Efficient Salient Instance Segmentation Networks With Orientative Query","publication_year":2022,"publication_date":"2022-01-11","ids":{"openalex":"https://openalex.org/W4205268584","doi":"https://doi.org/10.1109/tmm.2022.3141891"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3141891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3141891","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-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/A5082263233","display_name":"Jialun Pei","orcid":"https://orcid.org/0000-0002-2630-2838"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialun Pei","raw_affiliation_strings":["School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-2630-2838","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038287791","display_name":"Tianyang Cheng","orcid":"https://orcid.org/0000-0001-7910-3624"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyang Cheng","raw_affiliation_strings":["School of Software Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102924022","display_name":"He Tang","orcid":"https://orcid.org/0000-0002-8454-1407"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Tang","raw_affiliation_strings":["School of Software Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-8454-1407","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034666765","display_name":"Chuanbo Chen","orcid":"https://orcid.org/0000-0001-8006-7851"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanbo Chen","raw_affiliation_strings":["School of Software Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-8006-7851","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":2.4301,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.90234921,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"1964","last_page":"1978"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9764000177383423,"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/T11094","display_name":"Face Recognition and Perception","score":0.9700000286102295,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8694165945053101},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.7322393655776978},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5763170123100281},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.53493332862854},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5267588496208191},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.5142952799797058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47239017486572266},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.42386671900749207},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41414153575897217},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4123242497444153},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3263637125492096},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32416731119155884},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.14141416549682617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8694165945053101},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.7322393655776978},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5763170123100281},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.53493332862854},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5267588496208191},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.5142952799797058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47239017486572266},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.42386671900749207},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41414153575897217},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4123242497444153},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3263637125492096},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32416731119155884},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.14141416549682617},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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},{"id":"https://openalex.org/C103038307","wikidata":"https://www.wikidata.org/wiki/Q6556360","display_name":"Lipid bilayer fusion","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3141891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3141891","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6298790030","display_name":null,"funder_award_id":"61902139","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1894057436","https://openalex.org/W1903029394","https://openalex.org/W1942214758","https://openalex.org/W1991367009","https://openalex.org/W1996326832","https://openalex.org/W2002781701","https://openalex.org/W2031489346","https://openalex.org/W2039313011","https://openalex.org/W2108598243","https://openalex.org/W2116724443","https://openalex.org/W2126833203","https://openalex.org/W2128340050","https://openalex.org/W2138046011","https://openalex.org/W2160613239","https://openalex.org/W2194775991","https://openalex.org/W2422471819","https://openalex.org/W2522986997","https://openalex.org/W2565639579","https://openalex.org/W2605929543","https://openalex.org/W2740667773","https://openalex.org/W2787091153","https://openalex.org/W2888358068","https://openalex.org/W2938260698","https://openalex.org/W2945809413","https://openalex.org/W2957414648","https://openalex.org/W2962914239","https://openalex.org/W2963032190","https://openalex.org/W2963088785","https://openalex.org/W2963112696","https://openalex.org/W2963150697","https://openalex.org/W2963299740","https://openalex.org/W2963334022","https://openalex.org/W2963351448","https://openalex.org/W2963604034","https://openalex.org/W2963915286","https://openalex.org/W2973058802","https://openalex.org/W2990984982","https://openalex.org/W3020677596","https://openalex.org/W3034185160","https://openalex.org/W3034549805","https://openalex.org/W3035022492","https://openalex.org/W3039991645","https://openalex.org/W3082631269","https://openalex.org/W3095422700","https://openalex.org/W3096609285","https://openalex.org/W3098389804","https://openalex.org/W3113410735","https://openalex.org/W3117450517","https://openalex.org/W3119586106","https://openalex.org/W3132724762","https://openalex.org/W3137142667","https://openalex.org/W3138516171","https://openalex.org/W3140528754","https://openalex.org/W3154314696","https://openalex.org/W3165924482","https://openalex.org/W3169200952","https://openalex.org/W3170841864","https://openalex.org/W4239147634","https://openalex.org/W4250482878","https://openalex.org/W6631943919","https://openalex.org/W6638992375","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6767856356","https://openalex.org/W6776684981","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6788071488"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2743976221"],"abstract_inverted_index":{"Salient":[0],"instance":[1,137],"segmentation":[2],"(SIS)":[3],"can":[4],"be":[5],"considered":[6,112],"as":[7,113],"the":[8,13,19,32,67,81,85,98,114,126,129,162,173,189,193,199],"next":[9],"generation":[10],"task":[11,28],"for":[12,24,91],"saliency":[14,103],"detection":[15],"community.":[16,163],"Most":[17],"of":[18,70,128,131,179,192],"existing":[20],"state-of-the-art":[21],"methods":[22],"used":[23],"this":[25,38,49,203],"novel":[26],"challenging":[27,186],"are":[29,205],"built":[30],"on":[31,42],"mainstream":[33],"Mask":[34],"R-CNN":[35],"architecture.":[36],"However,":[37],"mechanism":[39],"relies":[40],"heavily":[41],"hand-designed":[43],"anchors":[44],"and":[45,87,157,198],"NMS":[46],"post-processing.":[47],"In":[48,122],"paper,":[50],"we":[51,105,139],"provide":[52],"a":[53,72,132,141],"one":[54],"stage":[55],"SIS":[56,143],"framework":[57,170],"with":[58,135,154],"transformers,":[59,71],"termed":[60],"Orientative":[61],"Query":[62],"Transformer":[63],"(OQTR).":[64],"To":[65],"leverage":[66],"long-range":[68],"dependencies":[69],"cross":[73],"fusion":[74],"module":[75],"is":[76,111],"designed":[77],"to":[78,119,124,160],"efficiently":[79],"fuse":[80],"global":[82],"features":[83,90],"in":[84,101,202],"encoder":[86],"salient":[88,92,116,136],"query":[89,109,118],"mask":[93],"prediction.":[94],"Furthermore,":[95],"derived":[96],"from":[97],"center":[99],"prior":[100],"traditional":[102],"models,":[104],"propose":[106],"an":[107,177],"orientative":[108],"that":[110],"initial":[115],"object":[117],"accelerate":[120],"convergence.":[121],"addition,":[123],"mitigate":[125],"issue":[127],"lack":[130],"large-scale":[133],"dataset":[134,144,200],"labels,":[138],"collect":[140],"new":[142],"(SIS10":[145],"K)":[146],"containing":[147],"over":[148],"10":[149],"K":[150],"images":[151],"elaborately":[152],"annotated":[153],"both":[155],"object-":[156],"instance-level":[158],"labels":[159],"promote":[161],"Without":[164],"any":[165],"post-processing,":[166],"our":[167],"end-to-end":[168],"OQTR":[169],"significantly":[171],"surpasses":[172],"top-1":[174],"RDPNet":[175],"by":[176],"average":[178],"13.1%":[180],"AP":[181],"scores":[182],"across":[183],"all":[184],"three":[185],"datasets,":[187],"demonstrating":[188],"strong":[190],"performance":[191],"proposed":[194,201],"OQTR.":[195],"The":[196],"code":[197],"work":[204],"available":[206],"at:":[207],"<uri":[208],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[209],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/ssecv/OQTR</uri>":[210],".":[211]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}