{"id":"https://openalex.org/W7138101363","doi":"https://doi.org/10.1609/aaai.v40i12.37959","title":"Taming Cascaded Mixture-of-Experts for Modality-missing Multi-modal Salient Object Detection","display_name":"Taming Cascaded Mixture-of-Experts for Modality-missing Multi-modal Salient Object Detection","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138101363","doi":"https://doi.org/10.1609/aaai.v40i12.37959"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i12.37959","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37959","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37959/41921","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37959/41921","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129678498","display_name":"Kunpeng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kunpeng Wang","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, 230601, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, 230601, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129753091","display_name":"Feifan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feifan Sun","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, 230601, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, 230601, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129664520","display_name":"Keke Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keke Chen","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, 230601, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, 230601, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"12","first_page":"9939","last_page":"9947"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9858999848365784,"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":0.9858999848365784,"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":0.006500000134110451,"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/T11714","display_name":"Multimodal Machine Learning 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"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.6362000107765198},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6254000067710876},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6161999702453613},{"id":"https://openalex.org/keywords/router","display_name":"Router","score":0.5914999842643738},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.552299976348877},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43140000104904175},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.42910000681877136},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.4074999988079071},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35600000619888306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6743999719619751},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6362000107765198},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6254000067710876},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6161999702453613},{"id":"https://openalex.org/C2775896111","wikidata":"https://www.wikidata.org/wiki/Q642560","display_name":"Router","level":2,"score":0.5914999842643738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5591999888420105},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.552299976348877},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.42910000681877136},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38850000500679016},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35499998927116394},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2858999967575073},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2782999873161316},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.27309998869895935},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2718000113964081},{"id":"https://openalex.org/C2780505938","wikidata":"https://www.wikidata.org/wiki/Q17093282","display_name":"Unavailability","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i12.37959","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37959","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37959/41921","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37959","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i12.37959","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37959","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37959/41921","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138101363.pdf","grobid_xml":"https://content.openalex.org/works/W7138101363.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-modal":[0],"Salient":[1],"Object":[2],"Detection":[3],"(SOD)":[4],"shows":[5],"an":[6,133],"improvement":[7,21],"over":[8],"its":[9],"uni-modal":[10,155],"counterpart":[11],"by":[12,94,132],"exploiting":[13],"the":[14,55,65,109,139,171,181,195,198],"complementary":[15],"benefits":[16],"between":[17],"modalities.":[18],"However,":[19],"this":[20,44,88,92],"relies":[22],"on":[23,189],"complete":[24],"multi-modal":[25,50,79,106,150],"information,":[26],"which":[27,166],"is":[28,85],"difficult":[29],"to":[30,36,57,120,141,146],"be":[31],"guaranteed":[32],"in":[33,64,81],"practice":[34],"due":[35],"sensor":[37],"failures":[38],"and":[39,72,75,105,128,191],"transmission":[40],"errors.":[41],"To":[42,87],"address":[43],"issue,":[45],"we":[46,90],"propose":[47],"a":[48,82,96,117],"robust":[49],"SOD":[51],"framework":[52,84,93],"that":[53,101,137],"enhances":[54],"adaptability":[56],"modality-missing":[58,71,190],"conditions,":[59],"while":[60],"maintaining":[61],"comparable":[62],"performance":[63],"modality-complete":[66,73,192],"condition.":[67],"Nevertheless,":[68],"flexibly":[69],"handling":[70],"cases":[74],"integrating":[76,163],"their":[77],"corresponding":[78],"features":[80],"unified":[83],"non-trivial.":[86],"end,":[89],"achieve":[91],"designing":[95],"Cascaded":[97],"Mixture-of-Experts":[98],"(CMoE)":[99],"network":[100],"sequentially":[102],"incorporates":[103],"missing-aware":[104,110],"MoE.":[107],"Specifically,":[108],"MoE":[111,151],"employs":[112],"three":[113],"modality-reconstruction":[114],"experts":[115,156],"with":[116,157,180],"soft":[118,172],"router":[119,140],"adaptively":[121],"reconstruct":[122],"feature":[123],"representations":[124],"for":[125,162],"both":[126],"missing":[127,147],"available":[129],"modalities,":[130],"assisted":[131],"expert":[134,143],"modulation":[135],"loss":[136],"guides":[138],"assign":[142],"weights":[144],"according":[145],"conditions.":[148],"The":[149,174],"adopts":[152],"two":[153],"homogeneous":[154],"learned":[158],"modality-specific":[159],"knowledge":[160],"tailored":[161],"modality":[164],"features,":[165],"are":[167],"dynamically":[168],"combined":[169],"via":[170],"router.":[173],"cascaded":[175],"architecture":[176],"fully":[177],"empowers":[178],"CMoE":[179],"flexibility":[182],"across":[183],"varying":[184],"input":[185],"cases.":[186],"Extensive":[187],"experiments":[188],"conditions":[193],"demonstrate":[194],"effectiveness":[196],"of":[197],"proposed":[199],"method.":[200]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}