{"id":"https://openalex.org/W4315606099","doi":"https://doi.org/10.1109/tip.2023.3234702","title":"CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection","display_name":"CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4315606099","doi":"https://doi.org/10.1109/tip.2023.3234702","pmid":"https://pubmed.ncbi.nlm.nih.gov/37018701"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3234702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3234702","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/A5040300820","display_name":"Youwei Pang","orcid":"https://orcid.org/0000-0002-3950-0956"},"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":"Youwei Pang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-3950-0956","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050583798","display_name":"Xiaoqi Zhao","orcid":"https://orcid.org/0009-0003-0332-4748"},"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":"Xiaoqi Zhao","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015500789","display_name":"Lihe Zhang","orcid":"https://orcid.org/0000-0002-9241-1688"},"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":"Lihe Zhang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-9241-1688","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"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":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-6668-9758","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.9854,"has_fulltext":false,"cited_by_count":178,"citation_normalized_percentile":{"value":0.99642992,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"892","last_page":"904"},"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":0.9930999875068665,"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":0.9743000268936157,"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":0.6595670580863953},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5299825668334961},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4454077482223511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4395960569381714},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43388354778289795},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4307788610458374},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3955283761024475},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3942856788635254}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6595670580863953},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5299825668334961},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4454077482223511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4395960569381714},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43388354778289795},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4307788610458374},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3955283761024475},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3942856788635254},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3234702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3234702","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:37018701","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37018701","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":[],"awards":[{"id":"https://openalex.org/G2300386902","display_name":null,"funder_award_id":"62276046","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3609165871","display_name":null,"funder_award_id":"61876202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8370507441","display_name":null,"funder_award_id":"2021-KF-12-10","funder_id":"https://openalex.org/F4320323086","funder_display_name":"Natural Science Foundation of Liaoning Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323086","display_name":"Natural Science Foundation of Liaoning Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":96,"referenced_works":["https://openalex.org/W20683899","https://openalex.org/W933200379","https://openalex.org/W1485009520","https://openalex.org/W1686810756","https://openalex.org/W1901129140","https://openalex.org/W1982075130","https://openalex.org/W1993713494","https://openalex.org/W1994922096","https://openalex.org/W1996326832","https://openalex.org/W2039298799","https://openalex.org/W2046835352","https://openalex.org/W2098702446","https://openalex.org/W2100470808","https://openalex.org/W2128272608","https://openalex.org/W2133515615","https://openalex.org/W2160613239","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2412782625","https://openalex.org/W2520640394","https://openalex.org/W2560023338","https://openalex.org/W2752782242","https://openalex.org/W2765838470","https://openalex.org/W2766315367","https://openalex.org/W2799213142","https://openalex.org/W2804743778","https://openalex.org/W2887486131","https://openalex.org/W2887522866","https://openalex.org/W2907643346","https://openalex.org/W2909381593","https://openalex.org/W2922509574","https://openalex.org/W2928165649","https://openalex.org/W2938260698","https://openalex.org/W2942049721","https://openalex.org/W2945809413","https://openalex.org/W2948300571","https://openalex.org/W2957414648","https://openalex.org/W2961348656","https://openalex.org/W2962159375","https://openalex.org/W2963091558","https://openalex.org/W2963524571","https://openalex.org/W2963529609","https://openalex.org/W2963855133","https://openalex.org/W2963868681","https://openalex.org/W2965638232","https://openalex.org/W2987761193","https://openalex.org/W2998449272","https://openalex.org/W3002301267","https://openalex.org/W3022015146","https://openalex.org/W3034185160","https://openalex.org/W3034320133","https://openalex.org/W3034684132","https://openalex.org/W3035422681","https://openalex.org/W3035633116","https://openalex.org/W3049194477","https://openalex.org/W3080223684","https://openalex.org/W3092344722","https://openalex.org/W3092630514","https://openalex.org/W3098389804","https://openalex.org/W3106587394","https://openalex.org/W3107944836","https://openalex.org/W3108421143","https://openalex.org/W3108822985","https://openalex.org/W3109120382","https://openalex.org/W3114152269","https://openalex.org/W3118710621","https://openalex.org/W3120113457","https://openalex.org/W3126725132","https://openalex.org/W3135874576","https://openalex.org/W3138516171","https://openalex.org/W3152765238","https://openalex.org/W3154314696","https://openalex.org/W3159018159","https://openalex.org/W3163132162","https://openalex.org/W3164098653","https://openalex.org/W3166092877","https://openalex.org/W3170841864","https://openalex.org/W3171757599","https://openalex.org/W3177040887","https://openalex.org/W3185043317","https://openalex.org/W3188963955","https://openalex.org/W3202061712","https://openalex.org/W3202263958","https://openalex.org/W3203040502","https://openalex.org/W3204197760","https://openalex.org/W3207101999","https://openalex.org/W3207668590","https://openalex.org/W4206420686","https://openalex.org/W4226017195","https://openalex.org/W4289752563","https://openalex.org/W4308291551","https://openalex.org/W4312258849","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6772381481","https://openalex.org/W6780499500"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2119949815"],"abstract_inverted_index":{"Most":[0],"of":[1,31,38,55,112],"the":[2,13,32,36,39,53,62,83,106,110,153],"existing":[3],"bi-modal":[4],"(RGB-D":[5],"and":[6,16,59,85,94,131],"RGB-T)":[7],"salient":[8],"object":[9],"detection":[10],"methods":[11,41,147],"utilize":[12],"convolution":[14,33],"operation":[15,34],"construct":[17,74],"complex":[18],"interweave":[19],"fusion":[20],"structures":[21],"to":[22,42,73,123],"achieve":[23],"cross-modal":[24,64,70],"information":[25,57,78],"integration.":[26],"The":[27],"inherent":[28],"local":[29],"connectivity":[30],"constrains":[35],"performance":[37],"convolution-based":[40],"a":[43,75,90,99,117,138],"ceiling.":[44],"In":[45],"this":[46],"work,":[47],"we":[48,115],"rethink":[49],"these":[50],"tasks":[51],"from":[52],"perspective":[54],"global":[56],"alignment":[58],"transformation.":[60],"Specifically,":[61],"proposed":[63,154],"view-mixed":[65,101],"transformer":[66],"(CAVER)":[67],"cascades":[68],"several":[69],"integration":[71,88],"units":[72],"top-down":[76],"transformer-based":[77],"propagation":[79,93],"path.":[80],"CAVER":[81],"treats":[82],"multi-scale":[84],"multi-modal":[86],"feature":[87],"as":[89],"sequence-to-sequence":[91],"context":[92],"update":[95],"process":[96],"built":[97],"on":[98,129],"novel":[100],"attention":[102],"mechanism.":[103],"Besides,":[104],"considering":[105],"quadratic":[107],"complexity":[108],"w.r.t.":[109],"number":[111],"input":[113],"tokens,":[114],"design":[116],"parameter-free":[118],"patch-wise":[119],"token":[120],"re-embedding":[121],"strategy":[122],"simplify":[124],"operations.":[125],"Extensive":[126],"experimental":[127],"results":[128],"RGB-D":[130],"RGB-T":[132],"SOD":[133],"datasets":[134],"demonstrate":[135],"that":[136],"such":[137],"simple":[139],"two-stream":[140],"encoder-decoder":[141],"framework":[142],"can":[143],"surpass":[144],"recent":[145],"state-of-the-art":[146],"when":[148],"it":[149],"is":[150],"equipped":[151],"with":[152],"components.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":32},{"year":2025,"cited_by_count":67},{"year":2024,"cited_by_count":56},{"year":2023,"cited_by_count":23}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}