{"id":"https://openalex.org/W4383890466","doi":"https://doi.org/10.1109/tmm.2023.3294003","title":"CATNet: A Cascaded and Aggregated Transformer Network for RGB-D Salient Object Detection","display_name":"CATNet: A Cascaded and Aggregated Transformer Network for RGB-D Salient Object Detection","publication_year":2023,"publication_date":"2023-07-11","ids":{"openalex":"https://openalex.org/W4383890466","doi":"https://doi.org/10.1109/tmm.2023.3294003"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3294003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3294003","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/A5100767706","display_name":"Peng Ren","orcid":"https://orcid.org/0009-0007-0821-1039"},"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":"Peng Ren","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian Minzu University Dalian, China"],"raw_orcid":"https://orcid.org/0009-0007-0821-1039","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/A5103063826","display_name":"Bowen Yin","orcid":"https://orcid.org/0009-0004-2532-0462"},"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":"Bowen Yin","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian Minzu University Dalian, China"],"raw_orcid":"https://orcid.org/0009-0004-2532-0462","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/A5016323852","display_name":"Fasheng Wang","orcid":"https://orcid.org/0000-0002-0946-0789"},"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":"Fasheng Wang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian Minzu University Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-0946-0789","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":"https://openalex.org/A5100616471","display_name":"Haojie Li","orcid":"https://orcid.org/0000-0003-3882-2205"},"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":"Haojie Li","raw_affiliation_strings":["DUT-RU International School of Information Science and Engineering, Dalian University of Technology Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-3882-2205","affiliations":[{"raw_affiliation_string":"DUT-RU International School of Information Science and Engineering, 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":14.3496,"has_fulltext":false,"cited_by_count":146,"citation_normalized_percentile":{"value":0.9956011,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"2249","last_page":"2262"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9939000010490417,"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":0.9934999942779541,"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":0.8251205682754517},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5690352320671082},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5254756212234497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4933885633945465},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4533029794692993},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4479045569896698},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3665901720523834},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08492487668991089},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07913452386856079}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251205682754517},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5690352320671082},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5254756212234497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4933885633945465},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4533029794692993},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4479045569896698},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3665901720523834},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08492487668991089},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07913452386856079},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3294003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3294003","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":[{"id":"https://metadata.un.org/sdg/1","score":0.6299999952316284,"display_name":"No poverty"}],"awards":[{"id":"https://openalex.org/G3117123538","display_name":"\u8fd0\u52a8\u7a81\u53d8\u4e0e\u5916\u89c2\u5267\u53d8\u7684\u76ee\u6807\u8ddf\u8e2a\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61972068","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8060929076","display_name":null,"funder_award_id":"61976042","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8770365734","display_name":null,"funder_award_id":"XLYC2007023","funder_id":"https://openalex.org/F4320329895","funder_display_name":"Liaoning Revitalization Talents Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329895","display_name":"Liaoning Revitalization Talents Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W20683899","https://openalex.org/W1497443722","https://openalex.org/W1522301498","https://openalex.org/W1938386764","https://openalex.org/W1966025376","https://openalex.org/W1976409045","https://openalex.org/W1976754232","https://openalex.org/W1982075130","https://openalex.org/W1993713494","https://openalex.org/W1996326832","https://openalex.org/W2000946514","https://openalex.org/W2039313011","https://openalex.org/W2046835352","https://openalex.org/W2072761058","https://openalex.org/W2100470808","https://openalex.org/W2412782625","https://openalex.org/W2546160422","https://openalex.org/W2569272946","https://openalex.org/W2571295082","https://openalex.org/W2744613561","https://openalex.org/W2807746031","https://openalex.org/W2887503470","https://openalex.org/W2907643346","https://openalex.org/W2938260698","https://openalex.org/W2957414648","https://openalex.org/W2962159375","https://openalex.org/W2963529609","https://openalex.org/W2963868681","https://openalex.org/W2990984982","https://openalex.org/W3002301267","https://openalex.org/W3035422681","https://openalex.org/W3035687312","https://openalex.org/W3040422465","https://openalex.org/W3098504507","https://openalex.org/W3108812909","https://openalex.org/W3114152269","https://openalex.org/W3131500599","https://openalex.org/W3134912427","https://openalex.org/W3135874576","https://openalex.org/W3138516171","https://openalex.org/W3152765238","https://openalex.org/W3170173308","https://openalex.org/W3175515048","https://openalex.org/W3177040887","https://openalex.org/W3207668590","https://openalex.org/W3207804100","https://openalex.org/W3212645988","https://openalex.org/W4205971281","https://openalex.org/W4211161561","https://openalex.org/W4214561053","https://openalex.org/W4239147634","https://openalex.org/W4285163934","https://openalex.org/W4293680532","https://openalex.org/W4295424676","https://openalex.org/W4296285524","https://openalex.org/W4297798655","https://openalex.org/W4307771365","https://openalex.org/W4312887531","https://openalex.org/W4315606099","https://openalex.org/W6739901393","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2486460843","https://openalex.org/W2168109476","https://openalex.org/W1968121071","https://openalex.org/W2061647633","https://openalex.org/W2020254986","https://openalex.org/W2686985752","https://openalex.org/W1992540108","https://openalex.org/W2074225891","https://openalex.org/W2760769977","https://openalex.org/W2165229257"],"abstract_inverted_index":{"Salient":[0],"object":[1],"detection":[2,81],"(SOD)":[3],"is":[4,122,159,180,190],"an":[5],"important":[6],"preprocessing":[7],"operation":[8,238],"for":[9],"various":[10],"computer":[11],"vision":[12],"tasks.":[13],"Most":[14],"of":[15,45,83,100,127,156,174,182,220,231],"existing":[16],"RGB-D":[17,262],"SOD":[18],"models":[19],"employ":[20],"additive":[21],"or":[22,57],"connected":[23],"strategies":[24,50],"to":[25,32,38,54,65,132,160,192,214],"directly":[26],"aggregate":[27],"and":[28,59,93,114,137,147,162,168,198,216],"decode":[29],"multi-scale":[30,134,241],"features":[31,44,69,143,167,197,203,242],"predict":[33],"salient":[34],"maps.":[35,177],"However,":[36],"due":[37],"the":[39,43,74,80,84,120,125,157,165,172,200,208,218,221,229,236,240,253],"large":[40],"differences":[41,201],"between":[42,68,202],"different":[46,71,205],"scales,":[47],"these":[48],"aggregation":[49,243],"adopted":[51],"may":[52],"lead":[53],"information":[55,136,140,232],"loss":[56,233],"redundancy,":[58],"few":[60],"methods":[61,263],"explicitly":[62],"consider":[63],"how":[64],"establish":[66],"connections":[67],"at":[70,204],"scales":[72],"in":[73,141,185,195],"decoding":[75],"process,":[76],"which":[77,98],"consequently":[78],"deteriorates":[79],"performance":[82,258],"models.":[85],"To":[86],"this":[87],"end,":[88],"we":[89],"propose":[90],"a":[91,186,211],"cascaded":[92,115],"aggregated":[94],"Transformer":[95],"Network":[96],"(CATNet)":[97],"consists":[99],"three":[101],"key":[102],"modules,":[103],"i.e.,":[104],"attention":[105],"feature":[106],"enhancement":[107],"module":[108,112],"(AFEM),":[109],"cross-modal":[110],"fusion":[111],"(CMFM)":[113],"correction":[116],"decoder":[117],"(CCD).":[118],"Specifically,":[119],"AFEM":[121],"designed":[123,191],"on":[124,264],"basis":[126],"atrous":[128],"spatial":[129],"pyramid":[130],"pooling":[131],"obtain":[133],"semantic":[135],"global":[138],"context":[139],"high-level":[142,152],"through":[144],"dilated":[145],"convolution":[146],"multi-head":[148],"self-attention":[149],"mechanism,":[150],"enhancing":[151],"features.":[153],"The":[154,178],"role":[155],"CMFM":[158],"enhance":[161],"thereafter":[163],"fuse":[164],"RGB":[166],"depth":[169,176],"features,":[170,226],"alleviating":[171],"problem":[173,230],"poor-quality":[175],"CCD":[179,209],"composed":[181],"two":[183],"subdecoders":[184],"cascading":[187],"fashion.":[188],"It":[189],"suppress":[193],"noise":[194],"low-level":[196],"mitigate":[199],"scales.":[206],"Moreover,":[207],"uses":[210],"feedback":[212],"mechanism":[213],"correct":[215],"repair":[217],"output":[219],"subdecoder":[222],"by":[223,235],"exploiting":[224],"supervised":[225],"so":[227],"that":[228,252],"caused":[234],"upsampling":[237],"during":[239],"process":[244],"can":[245],"be":[246],"mitigated.":[247],"Extensive":[248],"experimental":[249],"results":[250],"demonstrate":[251],"proposed":[254],"CATNet":[255],"achieves":[256],"superior":[257],"over":[259],"14":[260],"state-of-the-art":[261],"7":[265],"challenging":[266],"benchmarks.":[267]},"counts_by_year":[{"year":2026,"cited_by_count":31},{"year":2025,"cited_by_count":70},{"year":2024,"cited_by_count":43},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}