{"id":"https://openalex.org/W7138859115","doi":"https://doi.org/10.1109/tmm.2026.3668533","title":"Cross-Modal Fusion With Mixture-of-Experts for Efficient RGB-D Salient Object Detection","display_name":"Cross-Modal Fusion With Mixture-of-Experts for Efficient RGB-D Salient Object Detection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7138859115","doi":"https://doi.org/10.1109/tmm.2026.3668533"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3668533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668533","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/A5040080625","display_name":"Jingyu Wu","orcid":"https://orcid.org/0000-0002-2586-330X"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyu Wu","raw_affiliation_strings":["College of Artificial Intelligence, Dalian Maritime University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-3185-0158","affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129939949","display_name":"Fuming Sun","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":"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/A5084050687","display_name":"Mingyu Lu","orcid":"https://orcid.org/0000-0002-3208-0661"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu Lu","raw_affiliation_strings":["College of Artificial Intelligence, Dalian Maritime University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-8663-9870","affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"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/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":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.898,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.98752296,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"28","issue":null,"first_page":"5999","last_page":"6010"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9940999746322632,"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":0.9940999746322632,"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":0.0026000000070780516,"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":0.00019999999494757503,"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/feature-extraction","display_name":"Feature extraction","score":0.5896000266075134},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5478000044822693},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.529699981212616},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5266000032424927},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4893999993801117},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.484499990940094},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4643000066280365},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.44830000400543213},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4293000102043152}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.866100013256073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6219000220298767},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5478000044822693},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.529699981212616},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5266000032424927},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.484499990940094},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3984000086784363},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3312999904155731},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2847999930381775},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28459998965263367},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3668533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668533","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/G6627029586","display_name":null,"funder_award_id":"62372077","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"RGB-D":[1],"salient":[2],"object":[3],"detection":[4],"(SOD)":[5],"models":[6],"are":[7],"plagued":[8],"by":[9,111],"issues,":[10],"including":[11],"excessive":[12],"model":[13,31,52],"parameters":[14],"and":[15,26,38,86,117,152,156],"high":[16],"computational":[17,63],"complexity.":[18],"These":[19],"drawbacks":[20],"impede":[21],"the":[22,28,56,102,175,179],"model's":[23],"efficient":[24,37,51],"deployment":[25],"constrain":[27],"enhancement":[29],"of":[30,105,148],"performance.":[32],"This":[33],"paper":[34],"introduces":[35],"an":[36,50],"lightweight":[39],"cross-modal":[40],"feature":[41,68,159],"cross-fusion":[42],"network,":[43,59],"termed":[44],"CMFNet.":[45],"In":[46],"particular,":[47],"we":[48,72,91,133],"design":[49,92,134],"utilizing":[53],"MobileViT":[54],"as":[55],"dual-stream":[57],"backbone":[58],"thereby":[60],"significantly":[61],"reducing":[62],"complexity":[64],"while":[65],"maintaining":[66],"robust":[67],"extraction":[69],"capabilities.":[70],"Firstly,":[71],"propose":[73],"a":[74,93,113,135,146,165],"Cross-Fusion":[75],"Module":[76,95,139],"(CFM)":[77],"designed":[78],"to":[79,121,127],"integrate":[80],"multi-scale":[81,143],"semantic":[82],"information":[83],"from":[84],"RGB":[85],"depth":[87],"features":[88,107,128],"dynamically.":[89],"Furthermore,":[90],"Lightweight-Mixture-of-Experts":[94],"(L-MoE)":[96],"for":[97],"multi-modal":[98],"features,":[99],"which":[100],"enhances":[101],"representational":[103],"capacity":[104],"fused":[106],"at":[108,129],"various":[109],"levels":[110],"employing":[112],"dynamic":[114],"routing":[115],"mechanism":[116],"balanced":[118],"constraint":[119],"strategy":[120],"allocate":[122],"appropriate":[123],"expert":[124],"processing":[125],"units":[126],"different":[130],"scales.":[131],"Additionally,":[132],"Multi-scale":[136],"Feature":[137],"Refinement":[138],"(MSFR)":[140],"that":[141,174],"captures":[142],"context":[144],"through":[145],"combination":[147],"channel-spatial":[149],"attention":[150],"mechanisms":[151],"depthwise":[153],"separable":[154],"convolution,":[155],"gradually":[157],"eliminates":[158],"distribution":[160],"differences":[161],"between":[162],"modalities":[163],"using":[164],"dual-path":[166],"residual":[167],"learning":[168],"strategy.":[169],"Abundant":[170],"experimental":[171],"findings":[172],"verify":[173],"proposed":[176],"CMFNet":[177],"outperforms":[178],"25":[180],"existing":[181],"State-of-the-art":[182],"(SOTA)":[183],"methods.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2026-03-20T00:00:00"}