{"id":"https://openalex.org/W3149865514","doi":"https://doi.org/10.1109/icassp.2011.5946566","title":"Beyond bag of words: Combining generative and discriminative models for natural scene categorization","display_name":"Beyond bag of words: Combining generative and discriminative models for natural scene categorization","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W3149865514","doi":"https://doi.org/10.1109/icassp.2011.5946566","mag":"3149865514"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100332669","display_name":"Zhen Li","orcid":"https://orcid.org/0000-0003-2625-5231"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhen Li","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022468480","display_name":"Kim\u2013Hui Yap","orcid":"https://orcid.org/0000-0003-1933-4986"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kim-Hui Yap","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiao-Ming Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiao-Ming Chen","raw_affiliation_strings":["Department of Computing, Curtin University of Technology, Bentley, WA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Curtin University of Technology, Bentley, WA, Australia","institution_ids":["https://openalex.org/I205640436"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"965","last_page":"968"},"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":1.0,"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":1.0,"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":0.996399998664856,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/discriminative-model","display_name":"Discriminative model","score":0.95103919506073},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.8912561535835266},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.7892475128173828},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7741574645042419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7440201044082642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7063083648681641},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.6181559562683105},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5152459740638733},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.484222412109375},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47610270977020264},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47403788566589355},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.47047358751296997},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4387661814689636},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38254886865615845},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.04854115843772888}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.95103919506073},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8912561535835266},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.7892475128173828},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7741574645042419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440201044082642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7063083648681641},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.6181559562683105},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5152459740638733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.484222412109375},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47610270977020264},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47403788566589355},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.47047358751296997},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4387661814689636},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38254886865615845},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.04854115843772888},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5946566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1625255723","https://openalex.org/W2112020727","https://openalex.org/W2131846894","https://openalex.org/W2155490028","https://openalex.org/W2163717286","https://openalex.org/W2166742463","https://openalex.org/W6636494156"],"related_works":["https://openalex.org/W2987280934","https://openalex.org/W2093104230","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W4365211920","https://openalex.org/W2128027845","https://openalex.org/W4386184937","https://openalex.org/W3014948380","https://openalex.org/W2751624083","https://openalex.org/W4241564561"],"abstract_inverted_index":{"This":[0],"paper":[1,66],"proposes":[2],"a":[3,42,75],"simple":[4],"yet":[5],"new":[6,43,76],"and":[7,14,132],"effective":[8],"framework":[9,51,77,143],"by":[10,73],"combining":[11],"generative":[12,118],"model":[13,16,110],"discriminative":[15,109],"for":[17,24,107,144],"natural":[18,38],"scene":[19,25,145],"categorization.":[20,146],"A":[21],"state-of-the-art":[22,139],"approach":[23],"categorization":[26],"is":[27,45,88,94,126,134],"the":[28,47,71,79,97,117,123,138],"Bag-of-Words":[29],"(BoW)":[30],"framework.":[31],"However,":[32],"there":[33],"exist":[34],"many":[35],"categories":[36],"in":[37,49,141],"scenes.":[39],"Often":[40],"when":[41],"category":[44,87],"considered,":[46,89],"codebook":[48],"BoW":[50,142],"needs":[52],"to":[53,68,136],"be":[54],"re-generated,":[55],"which":[56],"will":[57],"involve":[58],"exhaustive":[59],"computation.":[60],"In":[61],"view":[62],"of":[63,81,122],"this,":[64],"this":[65],"tries":[67],"ad":[69],"dress":[70],"issue":[72],"designing":[74],"with":[78],"ability":[80],"incremental":[82],"learning.":[83],"When":[84],"an":[85],"additional":[86],"much":[90],"lower":[91],"computational":[92],"cost":[93],"needed":[95],"while":[96],"resulting":[98],"image":[99,105],"signatures":[100,106],"are":[101,111],"still":[102],"discriminative.":[103],"The":[104,120],"training":[108],"carefully":[112],"de":[113],"signed":[114],"based":[115],"on":[116,128],"model.":[119],"effectiveness":[121],"proposed":[124],"method":[125,140],"validated":[127],"UIUC":[129],"Scene-15":[130],"dataset":[131],"it":[133],"shown":[135],"outperform":[137]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}