{"id":"https://openalex.org/W7166082288","doi":"https://doi.org/10.48550/arxiv.2606.26849","title":"Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection","display_name":"Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W7166082288","doi":"https://doi.org/10.48550/arxiv.2606.26849"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.26849","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26849","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.26849","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139414318","display_name":"Ke Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139389118","display_name":"Ling Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Ling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139455458","display_name":"Guangqi Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Guangqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059068585","display_name":"Gengshen Wu","orcid":"https://orcid.org/0000-0003-3201-002X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Gengshen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139390332","display_name":"Yi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053837667","display_name":"S Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Shoukun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9865999817848206,"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":0.9865999817848206,"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":0.006200000178068876,"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":0.0010999999940395355,"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/upsampling","display_name":"Upsampling","score":0.6883000135421753},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5515000224113464},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4749000072479248},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.45559999346733093},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.44530001282691956},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4429999887943268},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4293000102043152},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4163999855518341},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.3984000086784363},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.3921000063419342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401999831199646},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.6883000135421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6732000112533569},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5515000224113464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.44530001282691956},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4293000102043152},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4138000011444092},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.3984000086784363},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.3921000063419342},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29109999537467957},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2816999852657318},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.26849","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26849","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.26849","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26849","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"General":[0],"Salient":[1],"Object":[2],"Detection":[3],"(SOD)":[4],"aims":[5],"to":[6,49,84,113,125,162,164,179,183,192],"identify":[7],"and":[8,59,82,122,137,143,209,224],"segment":[9],"visually":[10],"interesting":[11],"objects":[12],"from":[13,80,117],"uni-modality":[14],"or":[15],"multi-modality":[16],"scenes,":[17],"recently":[18],"advanced":[19],"by":[20,42,74,98,131],"cutting-edge":[21],"State":[22],"Space":[23],"Models":[24],"(SSMs).":[25],"However,":[26],"a":[27,110,149,174,189,218],"critical":[28],"limitation":[29],"of":[30,36,54,103],"current":[31],"approaches":[32],"is":[33],"their":[34,61,69,86],"neglect":[35],"the":[37,50,99,133,181,184],"inherent":[38],"spectral":[39,52,87],"biases":[40,88],"exhibited":[41],"different":[43],"neural":[44],"network":[45],"paradigms.":[46],"By":[47],"digging":[48],"dataset-level":[51],"analysis":[53],"Convolutional":[55],"Neural":[56,105],"Networks":[57,106],"(CNNs)":[58],"SSMs,":[60],"semantic":[62],"representations":[63,79],"are":[64],"inherently":[65],"complementary":[66,70],"based":[67],"on":[68],"frequency":[71],"preferences.":[72],"Inspired":[73],"this,":[75],"we":[76,108],"harmonize":[77],"heterogeneous":[78],"SSMs":[81],"CNNs":[83],"bridge":[85],"for":[89,153],"general":[90,171],"salient":[91],"object":[92],"detection.":[93],"To":[94],"this":[95,158],"end,":[96],"inspired":[97],"dynamic":[100,150],"information":[101],"propagation":[102],"Liquid":[104,126],"(LNNs),":[107],"introduce":[109],"liquid":[111],"fusion":[112],"dynamically":[114],"integrates":[115],"features":[116,136,139,182],"two":[118],"backbones,":[119],"including":[120],"VMamba":[121,135],"ConvNeXt,":[123],"referred":[124],"Fusion":[127],"Network":[128],"(LFNet).":[129],"Concretely,":[130],"treating":[132],"continuous":[134],"ConvNeXt":[138],"as":[140],"evolving":[141],"states":[142],"exogenous":[144],"stimulus,":[145],"respectively,":[146],"LFNet":[147,213],"employs":[148],"gating":[151],"mechanism":[152],"content-aware":[154],"feature":[155],"aggregation.":[156],"Crucially,":[157],"state-stimulus":[159],"paradigm":[160],"enables":[161],"scale":[163],"multi-modal":[165],"cues,":[166],"resulting":[167],"in":[168,170],"flexibility":[169],"SOD.":[172],"Besides,":[173],"Saliency-Guided":[175],"Upsampling":[176],"(SGU)":[177],"operator":[178],"propagate":[180],"shallow":[185],"layer,":[186],"which":[187],"leverages":[188],"spectral-spatial":[190],"co-design":[191],"suppress":[193],"upsampling":[194],"artifacts":[195],"while":[196],"preserving":[197],"semantics.":[198],"Extensive":[199],"experiments":[200],"across":[201],"five":[202],"diverse":[203],"tasks":[204],"(RGB,":[205],"RGB-D,":[206],"RGB-T,":[207],"VSOD,":[208],"VDT)":[210],"demonstrate":[211],"that":[212],"achieves":[214],"state-of-the-art":[215],"performance,":[216],"offering":[217],"superior":[219],"trade-off":[220],"between":[221],"detection":[222],"accuracy":[223],"model":[225],"efficiency.":[226],"Code":[227],"has":[228],"been":[229],"released":[230],"at":[231],"https://github.com/cke520/LFNet.":[232]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-27T00:00:00"}