{"id":"https://openalex.org/W4391827269","doi":"https://doi.org/10.1109/tip.2024.3364022","title":"Disentangled Cross-Modal Transformer for RGB-D Salient Object Detection and Beyond","display_name":"Disentangled Cross-Modal Transformer for RGB-D Salient Object Detection and Beyond","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391827269","doi":"https://doi.org/10.1109/tip.2024.3364022","pmid":"https://pubmed.ncbi.nlm.nih.gov/38354080"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3364022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3364022","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/A5100353537","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0002-3138-505X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-3138-505X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103083587","display_name":"Feihong Shen","orcid":"https://orcid.org/0000-0003-2106-2895"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feihong Shen","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-2106-2895","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352099","display_name":"Ding Ding","orcid":"https://orcid.org/0000-0002-0859-8065"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding Ding","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048895548","display_name":"Yongjian Deng","orcid":"https://orcid.org/0000-0001-6253-3564"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjian Deng","raw_affiliation_strings":["College of Computer Science, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6253-3564","affiliations":[{"raw_affiliation_string":"College of Computer Science, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100323316","display_name":"Chao Li","orcid":"https://orcid.org/0000-0002-3539-4295"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3539-4295","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.3735,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.98375075,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"33","issue":null,"first_page":"1699","last_page":"1709"},"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/T11094","display_name":"Face Recognition and Perception","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9710999727249146,"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/modal","display_name":"Modal","score":0.7231338620185852},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6506085991859436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5019431114196777},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4528804421424866},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.41669604182243347},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34029656648635864},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11588582396507263},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09894946217536926}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7231338620185852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6506085991859436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5019431114196777},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4528804421424866},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.41669604182243347},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34029656648635864},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11588582396507263},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09894946217536926},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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.2024.3364022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3364022","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:38354080","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38354080","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G1003364742","display_name":null,"funder_award_id":"62261160576","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2156830850","display_name":null,"funder_award_id":"KM202310005027","funder_id":"https://openalex.org/F4320321793","funder_display_name":"Beijing Municipal Education Commission"},{"id":"https://openalex.org/G5321528465","display_name":null,"funder_award_id":"62102083","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7948515016","display_name":null,"funder_award_id":"92167102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G81991260","display_name":null,"funder_award_id":"BK20210222","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G8881695889","display_name":null,"funder_award_id":"62203024","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"},{"id":"https://openalex.org/F4320321793","display_name":"Beijing Municipal Education Commission","ror":"https://ror.org/04bpn6s66"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W20683899","https://openalex.org/W125693051","https://openalex.org/W1923184257","https://openalex.org/W1942214758","https://openalex.org/W1966025376","https://openalex.org/W1976409045","https://openalex.org/W1976754232","https://openalex.org/W1981228217","https://openalex.org/W1993713494","https://openalex.org/W2019584258","https://openalex.org/W2098702446","https://openalex.org/W2100470808","https://openalex.org/W2461475918","https://openalex.org/W2520640394","https://openalex.org/W2797761794","https://openalex.org/W2798857366","https://openalex.org/W2909381593","https://openalex.org/W2948300571","https://openalex.org/W2957414648","https://openalex.org/W2963529609","https://openalex.org/W2963685207","https://openalex.org/W2963868681","https://openalex.org/W2963998427","https://openalex.org/W2988916019","https://openalex.org/W2999219213","https://openalex.org/W3002301267","https://openalex.org/W3011305844","https://openalex.org/W3034421924","https://openalex.org/W3035422918","https://openalex.org/W3035687312","https://openalex.org/W3044256341","https://openalex.org/W3049194477","https://openalex.org/W3096609285","https://openalex.org/W3097053213","https://openalex.org/W3097336090","https://openalex.org/W3106587394","https://openalex.org/W3108608656","https://openalex.org/W3108822985","https://openalex.org/W3114152269","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3158901828","https://openalex.org/W3173882198","https://openalex.org/W3204197760","https://openalex.org/W3207537403","https://openalex.org/W3207668590","https://openalex.org/W3209732904","https://openalex.org/W3212645988","https://openalex.org/W4206873376","https://openalex.org/W4214561053","https://openalex.org/W4221001582","https://openalex.org/W4221152259","https://openalex.org/W4283707199","https://openalex.org/W4294550848","https://openalex.org/W4307771365","https://openalex.org/W4311972917","https://openalex.org/W4312366074","https://openalex.org/W4312384316","https://openalex.org/W4312887531","https://openalex.org/W4312941264","https://openalex.org/W4317521269","https://openalex.org/W4319996358","https://openalex.org/W4321236364","https://openalex.org/W4385245566","https://openalex.org/W4386075648","https://openalex.org/W4386813694","https://openalex.org/W6797613833","https://openalex.org/W6837954578","https://openalex.org/W6839589367"],"related_works":["https://openalex.org/W2486460843","https://openalex.org/W2168109476","https://openalex.org/W1968121071","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W2963805028","https://openalex.org/W4301343772","https://openalex.org/W2033914206","https://openalex.org/W4212983513","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Previous":[0],"multi-modal":[1,23,146],"transformers":[2],"for":[3,211],"RGB-D":[4,229],"salient":[5],"object":[6],"detection":[7],"(SOD)":[8],"generally":[9],"directly":[10],"connect":[11],"all":[12],"patches":[13],"from":[14,41],"two":[15,42,152],"modalities":[16,59],"to":[17,30,44,66,74,80,83,92,143],"model":[18,227],"cross-modal":[19,39,46,77,95,106,111,171,205],"correlation":[20],"and":[21,32,88,121,136,149,174,193,196,217,219,222,228],"perform":[22],"combination":[24,104],"without":[25],"differentiation,":[26],"which":[27],"can":[28,208],"lead":[29],"confusing":[31],"inefficient":[33],"fusion.":[34],"Instead,":[35],"we":[36,72,108,130],"disentangle":[37,75,144],"the":[38,67,76,132,140,145,162,188,197],"complementarity":[40],"views":[43],"reduce":[45],"fusion":[47,176],"ambiguity:":[48],"1)":[49],"Context":[50],"disentanglement.":[51,100],"We":[52],"argue":[53],"that":[54,110],"modeling":[55],"long-range":[56],"dependencies":[57],"across":[58,160],"as":[60],"done":[61],"before":[62],"is":[63],"uninformative":[64],"due":[65],"severe":[68],"modality":[69],"gap.":[70],"Differently,":[71],"propose":[73],"complementary":[78,86,153],"contexts":[79],"intra-modal":[81],"self-attention":[82],"explore":[84],"global":[85],"understanding,":[87],"spatial-aligned":[89],"inter-modal":[90],"attention":[91,206],"capture":[93],"local":[94],"correlations,":[96],"respectively.":[97],"2)":[98],"Representation":[99],"Unlike":[101],"previous":[102],"undifferentiated":[103],"of":[105,128,184,190],"representations,":[107],"find":[109],"cues":[112],"complement":[113],"each":[114],"other":[115],"by":[116],"enhancing":[117],"common":[118],"discriminative":[119],"regions":[120],"mutually":[122],"supplement":[123],"modal-specific":[124],"highlights.":[125],"On":[126],"top":[127],"this,":[129],"divide":[131],"tokens":[133],"into":[134],"consistent":[135,198],"private":[137],"ones":[138],"in":[139],"channel":[141],"dimension":[142],"integration":[147,173],"path":[148],"explicitly":[150],"boost":[151],"ways.":[154],"By":[155],"progressively":[156],"propagate":[157],"this":[158,233],"strategy":[159],"layers,":[161],"proposed":[163],"Disentangled":[164],"Feature":[165],"Pyramid":[166],"module":[167],"(DFP)":[168],"enables":[169],"informative":[170],"cross-level":[172],"better":[175],"adaptivity.":[177],"Comprehensive":[178],"experiments":[179,223],"on":[180,224],"a":[181,225],"large":[182],"variety":[183],"public":[185],"datasets":[186],"verify":[187,232],"efficacy":[189],"our":[191,204],"context":[192],"representation":[194],"disentanglement":[195],"improvement":[199],"over":[200],"state-of-the-art":[201],"models.":[202],"Additionally,":[203],"hierarchy":[207],"be":[209],"plug-and-play":[210],"different":[212],"backbone":[213],"architectures":[214],"(both":[215],"transformer":[216],"CNN)":[218],"downstream":[220],"tasks,":[221],"CNN-based":[226],"semantic":[230],"segmentation":[231],"generalization":[234],"ability.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":7}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}