{"id":"https://openalex.org/W2151632536","doi":"https://doi.org/10.1109/tmm.2008.2009692","title":"Scale-Invariant Visual Language Modeling for Object Categorization","display_name":"Scale-Invariant Visual Language Modeling for Object Categorization","publication_year":2009,"publication_date":"2009-01-20","ids":{"openalex":"https://openalex.org/W2151632536","doi":"https://doi.org/10.1109/tmm.2008.2009692","mag":"2151632536"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2008.2009692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2008.2009692","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/A5101685050","display_name":"Lei Wu","orcid":"https://orcid.org/0000-0001-7924-9498"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Wu","raw_affiliation_strings":["MOE-Microsoft Key Laboratory of Multimedia Computing and Communication (MCC), Department of Electrical Engineering and Information Science, University of Science and Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"MOE-Microsoft Key Laboratory of Multimedia Computing and Communication (MCC), Department of Electrical Engineering and Information Science, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089921601","display_name":"Yang Hu","orcid":"https://orcid.org/0000-0003-0379-1525"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Hu","raw_affiliation_strings":["MOE-Microsoft Key Laboratory of Multimedia Computing and Communication (MCC), Department of Electrical Engineering and Information Science, University of Science and Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"MOE-Microsoft Key Laboratory of Multimedia Computing and Communication (MCC), Department of Electrical Engineering and Information Science, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061131131","display_name":"Mingjing Li","orcid":"https://orcid.org/0000-0002-5290-8104"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjing Li","raw_affiliation_strings":["MOE-Microsoft Key Laboratory of Multimedia Computing and Communication (MCC), Department of Electrical Engineering and Information Science, University of Science and Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"MOE-Microsoft Key Laboratory of Multimedia Computing and Communication (MCC), Department of Electrical Engineering and Information Science, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064573190","display_name":"Nenghai Yu","orcid":"https://orcid.org/0000-0003-4417-9316"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nenghai Yu","raw_affiliation_strings":["MOE-Microsoft Key Laboratory of Multimedia Computing and Communication (MCC), Department of Electrical Engineering and Information Science, University of Science and Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"MOE-Microsoft Key Laboratory of Multimedia Computing and Communication (MCC), Department of Electrical Engineering and Information Science, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024965898","display_name":"Xian\u2010Sheng Hua","orcid":"https://orcid.org/0000-0002-8232-5049"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian-Sheng Hua","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101685050"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":8.7364,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.98137212,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"11","issue":"2","first_page":"286","last_page":"294"},"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":0.9994000196456909,"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":0.9994000196456909,"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":0.9972000122070312,"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":0.9944999814033508,"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/computer-science","display_name":"Computer science","score":0.8273078799247742},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6644129753112793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6435471773147583},{"id":"https://openalex.org/keywords/bag-of-words-model-in-computer-vision","display_name":"Bag-of-words model in computer vision","score":0.6073318719863892},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5982943177223206},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5811761021614075},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.4911932647228241},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43583518266677856},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.41734176874160767},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4129793047904968},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41186583042144775},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39600658416748047},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37098464369773865},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22168239951133728},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.16481003165245056},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08621394634246826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8273078799247742},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6644129753112793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6435471773147583},{"id":"https://openalex.org/C167611913","wikidata":"https://www.wikidata.org/wiki/Q6884747","display_name":"Bag-of-words model in computer vision","level":5,"score":0.6073318719863892},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5982943177223206},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5811761021614075},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4911932647228241},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43583518266677856},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41734176874160767},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4129793047904968},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41186583042144775},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39600658416748047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37098464369773865},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22168239951133728},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.16481003165245056},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08621394634246826},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2008.2009692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2008.2009692","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":[{"score":0.699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320333993","display_name":"Microsoft Research Asia","ror":"https://ror.org/0300m5276"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1549285799","https://openalex.org/W1625255723","https://openalex.org/W1651266332","https://openalex.org/W1676552347","https://openalex.org/W1880262756","https://openalex.org/W2013252827","https://openalex.org/W2095844239","https://openalex.org/W2099930951","https://openalex.org/W2103658758","https://openalex.org/W2105536903","https://openalex.org/W2107034620","https://openalex.org/W2107743791","https://openalex.org/W2108927102","https://openalex.org/W2109868644","https://openalex.org/W2112301665","https://openalex.org/W2113169966","https://openalex.org/W2116908796","https://openalex.org/W2117074709","https://openalex.org/W2124386111","https://openalex.org/W2129004009","https://openalex.org/W2134237567","https://openalex.org/W2143314306","https://openalex.org/W2147880316","https://openalex.org/W2150692003","https://openalex.org/W2153509747","https://openalex.org/W2154301842","https://openalex.org/W2163766261","https://openalex.org/W2166049352","https://openalex.org/W2166118928","https://openalex.org/W2170146448","https://openalex.org/W2171706135","https://openalex.org/W2172191903","https://openalex.org/W4233135949","https://openalex.org/W4237791300","https://openalex.org/W6637324600","https://openalex.org/W6676267127","https://openalex.org/W6684614623"],"related_works":["https://openalex.org/W2158102958","https://openalex.org/W2028757524","https://openalex.org/W1995462736","https://openalex.org/W2938717424","https://openalex.org/W2548286644","https://openalex.org/W2009049007","https://openalex.org/W2588241640","https://openalex.org/W2045213079","https://openalex.org/W2465112410","https://openalex.org/W2616303661"],"abstract_inverted_index":{"<para":[0],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[1],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[2],"In":[3,54,95],"recent":[4],"years,":[5],"\u201cbag-of-words\u201d":[6,161],"models,":[7],"which":[8,65,134],"treat":[9],"an":[10],"image":[11,121],"as":[12],"a":[13,59],"collection":[14],"of":[15,33,70,89,110],"unordered":[16],"visual":[17,38,60,127,157],"words,":[18],"have":[19,92],"been":[20,93],"widely":[21],"applied":[22],"in":[23],"the":[24,34,67,71,76,82,97,101,132],"multimedia":[25],"and":[26,116,140,160,171],"computer":[27],"vision":[28],"fields.":[29],"However,":[30],"their":[31],"ignorance":[32],"spatial":[35,52,68],"structure":[36],"among":[37],"words":[39],"makes":[40,103],"them":[41],"indiscriminative":[42],"for":[43,144],"objects":[44],"with":[45,86,168],"similar":[46],"word":[47,51],"frequencies":[48],"but":[49],"different":[50,87],"distributions.":[53],"this":[55],"paper,":[56],"we":[57],"propose":[58],"language":[61,78,128,158],"modeling":[62],"method":[63],"(VLM),":[64],"incorporates":[66],"context":[69],"local":[72],"appearance":[73],"features":[74],"into":[75],"statistical":[77,90],"model.":[79],"To":[80],"represent":[81],"object":[83,145],"categories,":[84],"models":[85,129,143,159],"orders":[88],"dependencies":[91],"exploited.":[94],"addition,":[96],"multilayer":[98],"extension":[99],"to":[100,107,118],"VLM":[102],"it":[104],"more":[105],"resistant":[106],"scale":[108,120,125],"variations":[109],"objects.":[111],"The":[112],"model":[113],"is":[114],"effective":[115],"applicable":[117],"large":[119],"categorization.":[122,146],"We":[123],"train":[124],"invariant":[126],"based":[130],"on":[131],"images":[133],"are":[135],"grouped":[136],"by":[137],"Flickr":[138],"tags,":[139],"use":[141],"these":[142],"Experimental":[147],"results":[148],"show":[149],"they":[150],"achieve":[151,165],"better":[152],"performance":[153,167],"than":[154],"single":[155],"layer":[156],"models.":[162],"They":[163],"also":[164],"comparable":[166],"2-D":[169],"MHMM":[170],"SVM-based":[172],"methods,":[173],"while":[174],"costing":[175],"much":[176],"less":[177],"computational":[178],"time.":[179],"</para>":[180]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}