{"id":"https://openalex.org/W4414404639","doi":"https://doi.org/10.1109/tmm.2025.3613076","title":"A UNet-Like Transformer Network for Camouflaged Object Detection","display_name":"A UNet-Like Transformer Network for Camouflaged Object Detection","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414404639","doi":"https://doi.org/10.1109/tmm.2025.3613076"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3613076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3613076","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/A5014712849","display_name":"Fuming Sun","orcid":"https://orcid.org/0000-0003-3932-2712"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuming Sun","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian Minzu University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-3932-2712","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian Minzu University, Dalian, China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102341476","display_name":"Jinyu Han","orcid":"https://orcid.org/0009-0005-8484-8889"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyu Han","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian Minzu University, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0005-8484-8889","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian Minzu University, Dalian, China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weiyi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiyi Wu","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian Minzu University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian Minzu University, Dalian, China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Sun","orcid":"https://orcid.org/0000-0002-8190-7282"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Sun","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian Minzu University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-8190-7282","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian Minzu University, Dalian, China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mengyin Wang","orcid":"https://orcid.org/0009-0001-1985-7026"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyin Wang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian Minzu University, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0001-1985-7026","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian Minzu University, Dalian, China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"last","author":{"id":null,"display_name":"Haojie Li","orcid":"https://orcid.org/0000-0003-3882-2205"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haojie Li","raw_affiliation_strings":["School of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-3882-2205","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3804,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.95215637,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"27","issue":null,"first_page":"9267","last_page":"9280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9979000091552734,"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":0.9979000091552734,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9926999807357788,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6371999979019165},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5882999897003174},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5309000015258789},{"id":"https://openalex.org/keywords/backbone-network","display_name":"Backbone network","score":0.511900007724762},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4032999873161316},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.375},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.375},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.36730000376701355},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3653999865055084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.875},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6371999979019165},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5882999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5332000255584717},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5309000015258789},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.511900007724762},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.375},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.375},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.36730000376701355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35030001401901245},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.34850001335144043},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31119999289512634},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2948000133037567},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.25360000133514404},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3613076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3613076","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/G1489220992","display_name":null,"funder_award_id":"62472067","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7523094131","display_name":null,"funder_award_id":"04442024061","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","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":67,"referenced_works":["https://openalex.org/W1586903776","https://openalex.org/W1901129140","https://openalex.org/W1982075130","https://openalex.org/W1994922096","https://openalex.org/W2008359794","https://openalex.org/W2021088830","https://openalex.org/W2092792357","https://openalex.org/W2132083787","https://openalex.org/W2151040689","https://openalex.org/W2395611524","https://openalex.org/W2560328367","https://openalex.org/W2928165649","https://openalex.org/W2943545929","https://openalex.org/W2963037989","https://openalex.org/W2963529609","https://openalex.org/W2979515228","https://openalex.org/W2996290406","https://openalex.org/W2997286550","https://openalex.org/W3092344722","https://openalex.org/W3138516171","https://openalex.org/W3164098653","https://openalex.org/W3173782971","https://openalex.org/W3174857663","https://openalex.org/W3175515048","https://openalex.org/W3176152216","https://openalex.org/W3177004386","https://openalex.org/W3202263958","https://openalex.org/W3211937532","https://openalex.org/W3212645988","https://openalex.org/W4285601297","https://openalex.org/W4285728607","https://openalex.org/W4289752563","https://openalex.org/W4306830744","https://openalex.org/W4306833423","https://openalex.org/W4308180443","https://openalex.org/W4313535374","https://openalex.org/W4321021814","https://openalex.org/W4323891945","https://openalex.org/W4362654014","https://openalex.org/W4366082837","https://openalex.org/W4376273993","https://openalex.org/W4383890466","https://openalex.org/W4383988917","https://openalex.org/W4384159664","https://openalex.org/W4386075673","https://openalex.org/W4386076039","https://openalex.org/W4386076083","https://openalex.org/W4386159716","https://openalex.org/W4386172459","https://openalex.org/W4386232833","https://openalex.org/W4387185378","https://openalex.org/W4387968022","https://openalex.org/W4387969595","https://openalex.org/W4387986717","https://openalex.org/W4390492164","https://openalex.org/W4390872693","https://openalex.org/W4391407087","https://openalex.org/W4392346283","https://openalex.org/W4393156066","https://openalex.org/W4399391807","https://openalex.org/W4399618674","https://openalex.org/W4399923948","https://openalex.org/W4401328675","https://openalex.org/W4402727868","https://openalex.org/W4404788888","https://openalex.org/W4405963173","https://openalex.org/W4414110893"],"related_works":[],"abstract_inverted_index":{"The":[0],"role":[1],"of":[2,49,58,65,104,153,165,171,183],"Camouflaged":[3,98],"Object":[4],"Detection":[5],"(COD)":[6],"is":[7],"to":[8,20,113,158,186,193,221],"identify":[9],"the":[10,16,21,26,56,63,125,151,163,208],"objects":[11,27,167,202],"that":[12,110,141,179,200,215],"integrate":[13],"seamlessly":[14],"with":[15,89],"surrounding":[17],"environment.":[18],"Due":[19],"high":[22,52],"intrinsic":[23,115],"similarity":[24],"between":[25,117],"and":[28,51,161,189,226],"their":[29],"background,":[30],"this":[31,72],"task":[32],"presents":[33],"greater":[34],"challenges":[35],"than":[36],"traditional":[37],"object":[38],"detection.":[39],"Most":[40],"existing":[41],"COD":[42,66],"methods":[43],"often":[44],"have":[45,203],"a":[46,76,90,97,105,136,143,176,181],"large":[47],"number":[48],"parameters":[50],"computational":[53],"complexity":[54],"in":[55,67],"pursuit":[57],"detection":[59,87],"accuracy,":[60],"which":[61,84],"hinders":[62],"application":[64],"practical":[68],"scenarios.":[69],"To":[70],"address":[71],"issue,":[73],"we":[74,95,134,174],"propose":[75,96],"UNet-like":[77],"Transformer":[78],"Network":[79],"for":[80,146],"COD,":[81],"termed":[82],"UTNet,":[83],"achieves":[85,217],"competitive":[86,218],"accuracy":[88],"smaller":[91],"parameter":[92],"set.":[93],"Specifically,":[94],"Region":[99],"Awareness":[100],"Module":[101],"(CRAM)":[102],"consisting":[103],"Hierarchical":[106],"Attention":[107],"Mechanism":[108],"(HAM)":[109],"groups":[111],"features":[112,195],"reveal":[114],"consistency":[116],"sub-features.":[118],"This":[119],"CRAM":[120],"can":[121],"be":[122],"embedded":[123],"into":[124],"backbone":[126],"network,":[127],"giving":[128],"it":[129],"powerful":[130],"modeling":[131],"capabilities.":[132],"And,":[133],"present":[135],"Contextual":[137],"Knowledge":[138],"Collector":[139],"(CKC)":[140],"exploits":[142],"cross-aggregation":[144],"approach":[145],"neighboring":[147],"feature":[148],"layers,":[149],"promoting":[150],"flow":[152],"semantic":[154],"information":[155],"from":[156,196],"high-level":[157],"low-level":[159],"features,":[160],"ensuring":[162,199],"integrity":[164],"camouflaged":[166,201],"at":[168,207],"each":[169],"level":[170],"features.":[172],"Furthermore,":[173],"introduce":[175],"progressive":[177],"decoder":[178],"utilizes":[180],"cascade":[182],"attention":[184],"units":[185],"filter":[187],"noise":[188],"explores":[190],"knowledge":[191],"aggregation":[192],"emphasize":[194],"different":[197],"levels,":[198],"complete":[204],"spatial":[205],"details":[206],"local":[209],"level.":[210],"Extensive":[211],"experimental":[212],"results":[213,219,227],"show":[214],"UTNet":[216],"compared":[220],"20":[222],"state-of-the-art":[223],"methods.":[224],"Codes":[225],"are":[228],"released":[229],"on":[230],"<uri":[231],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[232],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/hjy0518/UTNet</uri>.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":8}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}