{"id":"https://openalex.org/W2133663278","doi":"https://doi.org/10.5075/epfl-thesis-6424","title":"Saliency-based representations and multi-component classifiers for visual scene recognition","display_name":"Saliency-based representations and multi-component classifiers for visual scene recognition","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2133663278","doi":"https://doi.org/10.5075/epfl-thesis-6424","mag":"2133663278"},"language":"en","primary_location":{"id":"pmh:oai:infoscience.epfl.ch:203459","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/203459","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/203459","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033091961","display_name":"Marco Fornoni","orcid":"https://orcid.org/0000-0001-5538-8012"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fornoni, Marco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5033091961"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13681024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9977999925613403,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.9760000109672546,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7930145263671875},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7530781030654907},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6816661357879639},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6373085975646973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6238654851913452},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5486963987350464},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.5107376575469971},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4968715012073517},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4938076436519623},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4603564143180847},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44807225465774536},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.441254198551178},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4340435564517975},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41791510581970215},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3855956196784973},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37908315658569336},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28393280506134033}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7930145263671875},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7530781030654907},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6816661357879639},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6373085975646973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6238654851913452},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5486963987350464},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5107376575469971},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4968715012073517},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4938076436519623},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4603564143180847},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44807225465774536},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.441254198551178},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4340435564517975},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41791510581970215},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3855956196784973},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37908315658569336},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28393280506134033},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:infoscience.epfl.ch:203459","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/203459","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:203531","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/203531","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.5075/epfl-thesis-6424","is_oa":true,"landing_page_url":"https://doi.org/10.5075/epfl-thesis-6424","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dissertation"},{"id":"mag:2133663278","is_oa":false,"landing_page_url":"https://infoscience.epfl.ch/record/203531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:203459","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/203459","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1568091911","https://openalex.org/W1996884424","https://openalex.org/W2000021714","https://openalex.org/W1963863628","https://openalex.org/W306902760","https://openalex.org/W3197258983","https://openalex.org/W2310335681","https://openalex.org/W2734744453","https://openalex.org/W2113393607","https://openalex.org/W104532071","https://openalex.org/W2207655606","https://openalex.org/W2204231418","https://openalex.org/W1999040015","https://openalex.org/W2513750347","https://openalex.org/W2994503067","https://openalex.org/W2088446013","https://openalex.org/W2465428424","https://openalex.org/W2075855295","https://openalex.org/W2406818256","https://openalex.org/W2059923225"],"abstract_inverted_index":{"Visual":[0],"scene":[1,28,411,443,476],"recognition":[2,72,412,444,477],"deals":[3],"with":[4,167,195,238,255,311,313,321,416],"the":[5,10,23,27,35,91,116,120,151,156,191,196,235,278,282,286,290,295,325,352,367,388,396,420,429,437,449,456,461,468,484,487],"problem":[6],"of":[7,59,90,96,115,134,190,219,277,285,299,324,342,373,439,486],"automatically":[8,215],"recognizing":[9],"high-level":[11],"semantic":[12],"concept":[13],"describing":[14],"a":[15,19,32,42,125,217,227,300,314,322,337],"given":[16],"image":[17,107,127,149,178,303],"as":[18,22,81],"whole,":[20],"such":[21,80],"environment":[24],"in":[25,66,226,383,395],"which":[26,65],"is":[29,38,88,99,193,245,330,446],"occurring":[30],"(e.g.":[31,41],"mountain),":[33],"or":[34],"event":[36],"that":[37],"taking":[39],"place":[40],"rock":[43],"climbing":[44],"event).":[45],"Scene":[46],"categories,":[47],"especially":[48],"those":[49,256],"related":[50],"to":[51,100,214,247,293,309,332,335,426],"man-made":[52],"places":[53],"and":[54,62,70,109,155,176,184,240,271,297,339,349,370,391,401,433,481],"events,":[55],"present":[56,394],"high":[57,275],"degrees":[58],"intra-class":[60],"variability":[61],"inter-class":[63],"similarity,":[64],"turn":[67],"require":[68],"robust":[69,177],"discriminative":[71,338],"systems.":[73],"An":[74],"additional":[75],"requirement":[76],"for":[77,85,182,223,346],"potential":[78],"applications,":[79],"vision-based":[82],"spatial":[83,170],"reasoning":[84],"mobile":[86],"robots,":[87],"efficiency":[89,276,296],"classification":[92,110,197,204,304,404],"procedure.":[93],"The":[94,112,187,360,380,406],"objective":[95],"this":[97,162,384],"thesis":[98,117,192,385],"address":[101],"these":[102],"challenges,":[103],"by":[104,258,358,452],"proposing":[105],"suitable":[106],"representations":[108,400,408],"algorithms.":[111],"first":[113],"part":[114,189,284],"focuses":[118],"on":[119,442,472],"representation":[121],"task.":[122],"We":[123,199],"propose":[124,200],"bottom-up":[126],"descriptor":[128],"capturing":[129],"perceptually":[130,147],"coherent":[131],"structures":[132,393],"independently":[133],"their":[135],"position.":[136],"In":[137,281],"particular,":[138],"our":[139],"method":[140],"separately":[141],"pools":[142],"features":[143,345],"extracted":[144],"from":[145],"two":[146],"different":[148],"regions:":[150],"most":[152],"salient":[153,390],"region":[154],"remaining":[157],"non-salient":[158],"one.":[159],"By":[160,232],"complementing":[161],"Saliency-driven":[163],"Perceptual":[164],"Pooling":[165],"(SPP)":[166],"an":[168,201],"ad-hoc":[169],"pooling":[171],"operation,":[172],"we":[173,288,318],"obtain":[174],"compact":[175,340,399],"representations,":[179],"particularly":[180],"suited":[181],"indoor":[183],"sports":[185],"scenes.":[186],"second":[188],"concerned":[194],"step.":[198],"efficient":[202,403],"multi-component":[203],"algorithm,":[205,305,362],"named":[206,306,363],"Multiclass":[207],"Latent":[208],"Locally":[209],"Linear":[210],"SVM":[211,230],"(ML3),":[212],"able":[213,246],"learn":[216,249,336],"set":[218,341],"sub-categorical":[220,236],"linear":[221,432],"models":[222,237],"each":[224,347],"class,":[225,348],"principled":[228],"latent":[229],"framework.":[231],"linearly":[233],"combining":[234],"sample":[239],"class":[241],"specific":[242],"weights,":[243],"ML3":[244,262,291,334,421],"efficiently":[248],"smooth":[250],"non-linear":[251,417,434],"decision":[252],"boundaries,":[253],"competitive":[254,266,410],"obtained":[257,451],"Gaussian":[259],"kernel":[260],"SVMs.":[261],"also":[263],"shows":[264],"very":[265],"trade-offs":[267],"between":[268,431],"training":[269],"time":[270],"performance,":[272],"while":[273,375,419,464],"ensuring":[274],"prediction":[279],"phase.":[280,470],"last":[283],"thesis,":[287],"use":[289,333],"algorithm":[292,422,459],"improve":[294],"performance":[298,438,462],"recently":[301],"proposed":[302,382,457,488],"NBNN,":[307,374],"designed":[308],"cope":[310],"classes":[312],"large":[315],"diversity.":[316],"Specifically,":[317],"show":[319,483],"how":[320],"modification":[323],"NBNN":[326],"scoring":[327],"function":[328],"it":[329],"possible":[331],"prototypical":[343],"local":[344],"thus":[350],"avoid":[351],"extensive":[353],"Nearest":[354],"Neighbor":[355],"search":[356],"used":[357,425],"NBNN.":[359],"resulting":[361],"NBNL,":[364],"greatly":[365],"reduces":[366,460],"memory":[368],"requirements":[369],"testing":[371,469],"complexity":[372],"significantly":[376,465],"improving":[377],"its":[378],"performance.":[379],"approaches":[381],"effectively":[386],"exploit":[387],"spatial,":[389],"task-driven":[392],"images,":[397],"producing":[398],"relatively":[402],"procedures.":[405],"SPP":[407],"provide":[409],"performances":[413],"when":[414],"coupled":[415],"kernels,":[418],"can":[423],"be":[424],"partially":[427],"fill":[428],"gap":[430],"kernels.":[435],"Although":[436],"NBNN-based":[440],"methods":[441],"tasks":[445],"still":[447],"below":[448],"one":[450],"traditional":[453],"SVM-based":[454],"approaches,":[455],"NBNL":[458],"gap,":[463],"speeding":[466],"up":[467],"Experiments":[471],"three":[473],"publicly":[474],"available":[475],"datasets":[478],"(MIT-Indoor-67,":[479],"15-Scenes":[480],"UIUC-Sports)":[482],"value":[485],"approaches.":[489]},"counts_by_year":[],"updated_date":"2026-08-14T07:06:38.338062","created_date":"2025-10-10T00:00:00"}