{"id":"https://openalex.org/W7131891936","doi":"https://doi.org/10.1109/tmm.2026.3668606","title":"DSPNet: Dual-Path Saliency Prediction With Reconstructed Feature Injection and Discrepancy-Aware KL Loss","display_name":"DSPNet: Dual-Path Saliency Prediction With Reconstructed Feature Injection and Discrepancy-Aware KL Loss","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131891936","doi":"https://doi.org/10.1109/tmm.2026.3668606"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3668606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668606","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/A5041513157","display_name":"Chuanlin Liao","orcid":"https://orcid.org/0000-0002-2375-0686"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanlin Liao","raw_affiliation_strings":["Sichuan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012760166","display_name":"Xiaolin Gou","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Gou","raw_affiliation_strings":["Sichuan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115425497","display_name":"Junyu Fan","orcid":"https://orcid.org/0009-0009-9848-4261"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyu Fan","raw_affiliation_strings":["Sichuan University"],"raw_orcid":"https://orcid.org/0009-0009-9848-4261","affiliations":[{"raw_affiliation_string":"Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127472958","display_name":"Yi Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Lin","raw_affiliation_strings":["Sichuan University"],"raw_orcid":"https://orcid.org/0000-0002-7194-5023","affiliations":[{"raw_affiliation_string":"Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24185976"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":4.6258,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92508956,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"28","issue":null,"first_page":"6852","last_page":"6864"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.35569998621940613,"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":0.35569998621940613,"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":0.17229999601840973,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.12809999287128448,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5751000046730042},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5737000107765198},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5428000092506409},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5188999772071838},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4855000078678131},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4747999906539917},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4586000144481659},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4481000006198883},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4237000048160553},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4050000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8450000286102295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7371000051498413},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5751000046730042},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5737000107765198},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5428000092506409},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5188999772071838},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4855000078678131},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4747999906539917},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4586000144481659},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4009999930858612},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.396699994802475},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3865000009536743},{"id":"https://openalex.org/C202227193","wikidata":"https://www.wikidata.org/wiki/Q6345568","display_name":"Kadir\u2013Brady saliency detector","level":4,"score":0.3806999921798706},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C200106649","wikidata":"https://www.wikidata.org/wiki/Q223683","display_name":"Transpose","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.27090001106262207},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3668606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668606","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":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.41836458444595337}],"awards":[{"id":"https://openalex.org/G6307433967","display_name":null,"funder_award_id":"U2333209","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1510835000","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2041719651","https://openalex.org/W2078903912","https://openalex.org/W2086791339","https://openalex.org/W2112796928","https://openalex.org/W2128272608","https://openalex.org/W2133589685","https://openalex.org/W2135957164","https://openalex.org/W2160613239","https://openalex.org/W2192271525","https://openalex.org/W2194775991","https://openalex.org/W2212216676","https://openalex.org/W2293332611","https://openalex.org/W2558906385","https://openalex.org/W2612135493","https://openalex.org/W2753641513","https://openalex.org/W2756728425","https://openalex.org/W2798322248","https://openalex.org/W2884775172","https://openalex.org/W2944643774","https://openalex.org/W2963503775","https://openalex.org/W2964444661","https://openalex.org/W2979442772","https://openalex.org/W2980565715","https://openalex.org/W3005401190","https://openalex.org/W3011978462","https://openalex.org/W3022565501","https://openalex.org/W3081633908","https://openalex.org/W3083947974","https://openalex.org/W3126721752","https://openalex.org/W3132652652","https://openalex.org/W3135252983","https://openalex.org/W3194945615","https://openalex.org/W3196750734","https://openalex.org/W3208061059","https://openalex.org/W4224281996","https://openalex.org/W4226074673","https://openalex.org/W4239147634","https://openalex.org/W4312443924","https://openalex.org/W4367279925","https://openalex.org/W4381198783","https://openalex.org/W4386065983","https://openalex.org/W4386076080","https://openalex.org/W4387249902","https://openalex.org/W4389328725","https://openalex.org/W4393932075","https://openalex.org/W4405931317","https://openalex.org/W4405986878","https://openalex.org/W4409369976"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"saliency":[1,89],"prediction":[2,90,174],"(VSP)":[3],"is":[4,41,93,126,156],"a":[5,113,132],"fundamental":[6],"task":[7,33],"in":[8,47,76,147],"computer":[9],"vision,":[10],"which":[11,163],"enables":[12],"efficient":[13],"sensing":[14],"and":[15,27,65,109,143,184,197],"computation":[16],"by":[17,121],"prioritizing":[18],"informative":[19],"regions,":[20,79],"such":[21,191],"as":[22,192],"object":[23],"detection,":[24],"scene":[25],"understanding,":[26],"video":[28],"compression.":[29],"However,":[30],"the":[31,82,97,160],"VSP":[32],"still":[34],"faces":[35],"three":[36],"challenges:":[37],"(i)":[38],"fine-grained":[39],"texture":[40,125,208],"irreversibly":[42],"lost":[43,118],"during":[44],"repeated":[45],"down-sampling":[46],"single-stream":[48],"convolutional":[49],"networks;":[50],"(ii)":[51],"traditional":[52],"attention":[53,136,170],"modules":[54],"apply":[55],"fixed,":[56],"simplistic":[57],"weights":[58],"that":[59,203],"adapt":[60],"poorly":[61],"to":[62,72,95,116,158,168,171],"complex":[63,148],"scenes;":[64],"(iii)":[66],"standard":[67],"Kullback-Leibler":[68],"(KL)":[69],"divergence":[70],"fails":[71],"sufficiently":[73],"amplify":[74],"gradients":[75],"weakly":[77],"activated":[78],"thereby":[80],"hindering":[81],"learning":[83],"of":[84],"hard":[85],"samples.":[86],"A":[87,100,150],"dual-path":[88],"network":[91],"(DSPNet)":[92],"proposed":[94],"address":[96],"aforementioned":[98],"challenges.":[99],"vector-quantized":[101],"variational":[102],"autoencoder":[103],"(VQ-VAE)":[104],"branch":[105],"discretizes":[106],"local":[107,207],"textures":[108],"reinjects":[110],"them":[111],"into":[112],"U-Net":[114],"backbone":[115],"recover":[117],"details":[119],"caused":[120],"down-sampling.":[122],"The":[123],"restored":[124],"integrated":[127],"with":[128,173,210],"high-level":[129],"semantics":[130],"via":[131],"bidirectional":[133],"mutual":[134],"transpose":[135],"(BMTA)":[137],"decoder,":[138],"enabling":[139],"nonlinear":[140],"cross-layer":[141],"interactions":[142],"enhancing":[144],"spatial":[145],"discrimination":[146],"scenes.":[149],"discrepancy-aware":[151],"focal":[152],"KL":[153,195],"(F-KL)":[154],"loss":[155],"designed":[157],"optimize":[159],"model":[161],"training,":[162],"adaptively":[164],"emphasizes":[165],"discrepant":[166],"regions":[167],"improve":[169],"areas":[172],"gaps.":[175],"Evaluations":[176],"on":[177],"four":[178],"public":[179],"benchmarks":[180],"(MIT300,":[181],"SALICON,":[182],"PASCAL-S,":[183],"TORONTO)":[185],"show":[186],"state-of-the-art":[187],"results":[188],"across":[189],"metrics":[190],"Similarity":[193],"(SIM),":[194],"divergence,":[196],"Normalized":[198],"Scanpath":[199],"Saliency":[200],"(NSS),":[201],"confirming":[202],"DSPNet":[204],"effectively":[205],"balances":[206],"fidelity":[209],"global":[211],"semantic":[212],"understanding.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-02-28T00:00:00"}