{"id":"https://openalex.org/W4387968376","doi":"https://doi.org/10.1145/3581783.3611983","title":"Recurrent Multi-scale Transformer for High-Resolution Salient Object Detection","display_name":"Recurrent Multi-scale Transformer for High-Resolution Salient Object Detection","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968376","doi":"https://doi.org/10.1145/3581783.3611983"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611983","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103137553","display_name":"Xinhao Deng","orcid":"https://orcid.org/0000-0003-1131-4710"},"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":"Xinhao Deng","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-1131-4710","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451855","display_name":"Pingping Zhang","orcid":"https://orcid.org/0000-0003-1206-1444"},"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":"Pingping Zhang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-1206-1444","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763568","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0001-6351-9019"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Shanghai Jiaotong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6351-9019","affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"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, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-6668-9758","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7413","last_page":"7423"},"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":0.987500011920929,"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":0.9853000044822693,"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":0.8391448855400085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.649644136428833},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6347014307975769},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6211345195770264},{"id":"https://openalex.org/keywords/high-resolution","display_name":"High resolution","score":0.5931555032730103},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5668216347694397},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5243245363235474},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4600209593772888},{"id":"https://openalex.org/keywords/image-resolution","display_name":"Image resolution","score":0.4589768946170807},{"id":"https://openalex.org/keywords/low-resolution","display_name":"Low resolution","score":0.43921148777008057},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32708683609962463},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.076041579246521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8391448855400085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.649644136428833},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6347014307975769},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6211345195770264},{"id":"https://openalex.org/C3020199158","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"High resolution","level":2,"score":0.5931555032730103},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5668216347694397},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5243245363235474},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4600209593772888},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.4589768946170807},{"id":"https://openalex.org/C3019883945","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Low resolution","level":3,"score":0.43921148777008057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32708683609962463},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.076041579246521},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611983","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7611614075","display_name":null,"funder_award_id":"62101092","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1772076007","https://openalex.org/W1861492603","https://openalex.org/W2002781701","https://openalex.org/W2039313011","https://openalex.org/W2055180303","https://openalex.org/W2086791339","https://openalex.org/W2128272608","https://openalex.org/W2132083787","https://openalex.org/W2160613239","https://openalex.org/W2470139095","https://openalex.org/W2740667773","https://openalex.org/W2747329762","https://openalex.org/W2780861787","https://openalex.org/W2938260698","https://openalex.org/W2939217524","https://openalex.org/W2961348656","https://openalex.org/W2963032190","https://openalex.org/W2963334022","https://openalex.org/W2987701848","https://openalex.org/W2989161706","https://openalex.org/W2990201021","https://openalex.org/W2990984982","https://openalex.org/W2998449272","https://openalex.org/W3034185160","https://openalex.org/W3034438741","https://openalex.org/W3035422681","https://openalex.org/W3096609285","https://openalex.org/W3098389804","https://openalex.org/W3107944836","https://openalex.org/W3131182250","https://openalex.org/W3138516171","https://openalex.org/W3170544306","https://openalex.org/W3173370190","https://openalex.org/W3207493400","https://openalex.org/W3211490618","https://openalex.org/W4234552385","https://openalex.org/W4239147634","https://openalex.org/W4313170506"],"related_works":["https://openalex.org/W4296995023","https://openalex.org/W2070173637","https://openalex.org/W3118545013","https://openalex.org/W2133155333","https://openalex.org/W1516116847","https://openalex.org/W2412281349","https://openalex.org/W4212954839","https://openalex.org/W4241811109","https://openalex.org/W4401570279","https://openalex.org/W3169440385"],"abstract_inverted_index":{"Salient":[0],"Object":[1],"Detection":[2],"(SOD)":[3],"aims":[4],"to":[5,55,61,63,147],"identify":[6],"and":[7,30,83,94,143,165,187,193,202],"segment":[8],"the":[9,34,64,128,132,149,177,191,196],"most":[10],"conspicuous":[11],"objects":[12],"in":[13,28,102,141],"an":[14,19],"image":[15],"or":[16],"video.":[17],"As":[18,121],"important":[20],"pre-processing":[21],"step,":[22],"it":[23,126],"has":[24],"many":[25],"potential":[26],"applications":[27],"multimedia":[29],"vision":[31],"tasks.":[32],"With":[33],"advance":[35],"of":[36,44,66,179,195],"imaging":[37],"devices,":[38],"SOD":[39,50,68],"with":[40,176],"high-resolution":[41,170,186],"images":[42,117],"is":[43,127],"great":[45],"demand,":[46],"recently.":[47],"However,":[48],"traditional":[49],"methods":[51,73,88],"are":[52,76,204],"largely":[53],"limited":[54],"low-resolution":[56,188],"images,":[57],"making":[58],"them":[59],"difficult":[60],"adapt":[62],"development":[65],"High-Resolution":[67],"(HRSOD).":[69],"Although":[70],"some":[71],"HRSOD":[72,87,133,150],"emerge,":[74],"there":[75],"no":[77],"large":[78],"enough":[79],"datasets":[80],"for":[81,131],"training":[82,142],"evaluating.":[84],"Besides,":[85],"current":[86],"generally":[89],"produce":[90],"incomplete":[91],"object":[92,96],"regions":[93],"irregular":[95],"boundaries.":[97],"To":[98],"address":[99],"above":[100],"issues,":[101],"this":[103],"work,":[104],"we":[105,124,152],"first":[106],"propose":[107,153],"a":[108,154],"new":[109],"HRS10K":[110],"dataset,":[111],"which":[112,135,160],"contains":[113],"10,500":[114],"high-quality":[115],"annotated":[116],"at":[118],"2K-8K":[119],"resolution.":[120],"far":[122],"as":[123],"know,":[125],"largest":[129],"dataset":[130,203],"task,":[134],"will":[136],"significantly":[137],"help":[138],"future":[139],"works":[140],"evaluating":[144],"models.":[145],"Furthermore,":[146],"improve":[148],"performance,":[151],"novel":[155],"Recurrent":[156],"Multi-scale":[157],"Transformer":[158],"(RMFormer),":[159],"recurrently":[161],"utilizes":[162],"shared":[163],"Transformers":[164],"multi-scale":[166],"refinement":[167],"architectures.":[168],"Thus,":[169],"saliency":[171],"maps":[172],"can":[173],"be":[174],"generated":[175],"guidance":[178],"lower-resolution":[180],"predictions.":[181],"Extensive":[182],"experiments":[183],"on":[184],"both":[185],"benchmarks":[189],"show":[190],"effectiveness":[192],"superiority":[194],"proposed":[197],"framework.":[198],"The":[199],"source":[200],"code":[201],"released":[205],"at:":[206],"https://github.com/DrowsyMon/RMFormer.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}