{"id":"https://openalex.org/W4408353912","doi":"https://doi.org/10.1109/icassp49660.2025.10887964","title":"Camouflaged Object Detection with CNN-Transformer Harmonization and Calibration","display_name":"Camouflaged Object Detection with CNN-Transformer Harmonization and Calibration","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353912","doi":"https://doi.org/10.1109/icassp49660.2025.10887964"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5101361471","display_name":"Yilin Zhao","orcid":"https://orcid.org/0000-0001-5324-332X"},"institutions":[{"id":"https://openalex.org/I67001856","display_name":"Shanghai Institute of Technology","ror":"https://ror.org/00fjzqj15","country_code":"CN","type":"education","lineage":["https://openalex.org/I67001856"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yilin Zhao","raw_affiliation_strings":["Shanghai Institute of Technology,College of Information Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Technology,College of Information Engineering,Shanghai,China","institution_ids":["https://openalex.org/I67001856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101596772","display_name":"Qing Zhang","orcid":"https://orcid.org/0000-0001-6815-1954"},"institutions":[{"id":"https://openalex.org/I67001856","display_name":"Shanghai Institute of Technology","ror":"https://ror.org/00fjzqj15","country_code":"CN","type":"education","lineage":["https://openalex.org/I67001856"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Zhang","raw_affiliation_strings":["Shanghai Institute of Technology,College of Information Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Technology,College of Information Engineering,Shanghai,China","institution_ids":["https://openalex.org/I67001856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022853722","display_name":"Yuetong Li","orcid":"https://orcid.org/0009-0005-2353-4886"},"institutions":[{"id":"https://openalex.org/I67001856","display_name":"Shanghai Institute of Technology","ror":"https://ror.org/00fjzqj15","country_code":"CN","type":"education","lineage":["https://openalex.org/I67001856"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuetong Li","raw_affiliation_strings":["Shanghai Institute of Technology,College of Information Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Technology,College of Information Engineering,Shanghai,China","institution_ids":["https://openalex.org/I67001856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101361471"],"corresponding_institution_ids":["https://openalex.org/I67001856"],"apc_list":null,"apc_paid":null,"fwci":2.2732,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86724124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9437000155448914,"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":0.9437000155448914,"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":0.9125000238418579,"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/computer-science","display_name":"Computer science","score":0.6588842868804932},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5464410781860352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5309678316116333},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.5181921124458313},{"id":"https://openalex.org/keywords/harmonization","display_name":"Harmonization","score":0.47389712929725647},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46777263283729553},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.44513237476348877},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3385867476463318},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12316596508026123},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10193759202957153},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09128773212432861},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07994833588600159}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6588842868804932},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5464410781860352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5309678316116333},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5181921124458313},{"id":"https://openalex.org/C2779962950","wikidata":"https://www.wikidata.org/wiki/Q5659376","display_name":"Harmonization","level":2,"score":0.47389712929725647},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46777263283729553},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.44513237476348877},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3385867476463318},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12316596508026123},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10193759202957153},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09128773212432861},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07994833588600159},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1968773971","https://openalex.org/W1982075130","https://openalex.org/W1994922096","https://openalex.org/W2943545929","https://openalex.org/W2963529609","https://openalex.org/W2963604034","https://openalex.org/W2963868681","https://openalex.org/W2990391993","https://openalex.org/W2998449272","https://openalex.org/W3034684132","https://openalex.org/W3092344722","https://openalex.org/W3164098653","https://openalex.org/W3168112135","https://openalex.org/W3173782971","https://openalex.org/W3176152216","https://openalex.org/W4312258849","https://openalex.org/W4384938792","https://openalex.org/W4386075673","https://openalex.org/W4386076039","https://openalex.org/W4387968414","https://openalex.org/W4387969595","https://openalex.org/W4391407087","https://openalex.org/W4401328675","https://openalex.org/W4402727814","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2006073222","https://openalex.org/W2488916264","https://openalex.org/W2323573032","https://openalex.org/W198625436","https://openalex.org/W1908077024","https://openalex.org/W2095388346","https://openalex.org/W2379751185","https://openalex.org/W2379404183","https://openalex.org/W2004509987","https://openalex.org/W2185986540"],"abstract_inverted_index":{"Camouflaged":[0],"object":[1],"detection":[2,44],"(COD)":[3],"aims":[4],"to":[5,31,66,83,127],"segment":[6],"objects":[7,20,70],"that":[8,118,139],"visually":[9],"blend":[10],"into":[11],"their":[12],"surroundings.":[13],"However,":[14],"the":[15,22,58,68,89,140],"subtle":[16],"differences":[17],"between":[18,92],"camouflaged":[19,69],"and":[21,33,37,63,71,103],"background":[23],"make":[24],"this":[25,47],"task":[26],"highly":[27],"challenging.":[28],"Therefore,":[29],"how":[30],"represent":[32],"learn":[34],"local":[35,62,101],"details":[36],"global":[38,64,108],"contexts":[39],"is":[40],"crucial":[41],"for":[42],"improving":[43],"performance.":[45],"In":[46],"paper,":[48],"we":[49,76,111],"propose":[50,112],"a":[51,78,113],"novel":[52],"COD":[53,135],"network":[54,95,142],"which":[55,98,106],"synergistically":[56],"leverages":[57],"distinct":[59],"but":[60],"complementary":[61],"knowledge":[65,90],"capture":[67,107],"identify":[72],"imperceptible":[73],"boundaries.":[74],"Specifically,":[75],"design":[77],"Feature":[79,115],"Coherence":[80],"Harmonization":[81],"module":[82],"integrate":[84],"intra-layer":[85],"features":[86],"by":[87],"bridging":[88],"gap":[91],"convolutional":[93],"neural":[94],"(CNN)":[96],"features,":[97,105,122],"focus":[99],"on":[100,134],"patterns,":[102],"Transformer":[104],"relationships.":[109],"Furthermore,":[110],"Cross-layer":[114],"Calibration":[116],"Module":[117],"adaptively":[119],"aligns":[120],"inter-layer":[121],"progressively":[123],"aggregating":[124],"diverse":[125],"information":[126],"achieve":[128],"an":[129],"accurate":[130],"prediction.":[131],"Experimental":[132],"results":[133],"benchmark":[136],"datasets":[137],"demonstrate":[138],"proposed":[141],"significantly":[143],"outperforms":[144],"state-of-the-art":[145],"approaches.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}