{"id":"https://openalex.org/W1999931200","doi":"https://doi.org/10.1145/1290082.1290101","title":"Visual language modeling for image classification","display_name":"Visual language modeling for image classification","publication_year":2007,"publication_date":"2007-09-24","ids":{"openalex":"https://openalex.org/W1999931200","doi":"https://doi.org/10.1145/1290082.1290101","mag":"1999931200"},"language":"en","primary_location":{"id":"doi:10.1145/1290082.1290101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1290082.1290101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the international workshop on Workshop on multimedia information retrieval","raw_type":"proceedings-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":["University of Science and Technology of China, Hefei, China",", University of Science and Technology of China, Hefei, China#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":", University of Science and Technology of China, Hefei, China#TAB#","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/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":"Mingjing Li","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409101","display_name":"Zhiwei Li","orcid":"https://orcid.org/0000-0003-2716-2002"},"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":"Zhiwei Li","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103733614","display_name":"Wei\u2010Ying Ma","orcid":"https://orcid.org/0000-0002-7384-0735"},"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":"Wei-Ying Ma","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","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":["University of Science and Technology of China, Hefei, China",", University of Science and Technology of China, Hefei, China#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":", University of Science and Technology of China, Hefei, China#TAB#","institution_ids":["https://openalex.org/I126520041"]}]}],"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":5.5176,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.95945414,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"124"},"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":0.9991999864578247,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9955999851226807,"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/bigram","display_name":"Bigram","score":0.8416991233825684},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.8232302665710449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7440222501754761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6871705055236816},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.659368097782135},{"id":"https://openalex.org/keywords/bag-of-words-model-in-computer-vision","display_name":"Bag-of-words model in computer vision","score":0.6368007659912109},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6059622764587402},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5931891202926636},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5339378714561462},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.5204291939735413},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5089719295501709},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4518933594226837},{"id":"https://openalex.org/keywords/standard-test-image","display_name":"Standard test image","score":0.43520402908325195},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35088372230529785},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.25739505887031555},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.22207725048065186},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2111063301563263}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.8416991233825684},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.8232302665710449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7440222501754761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6871705055236816},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.659368097782135},{"id":"https://openalex.org/C167611913","wikidata":"https://www.wikidata.org/wiki/Q6884747","display_name":"Bag-of-words model in computer vision","level":5,"score":0.6368007659912109},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6059622764587402},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5931891202926636},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5339378714561462},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.5204291939735413},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5089719295501709},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4518933594226837},{"id":"https://openalex.org/C180462255","wikidata":"https://www.wikidata.org/wiki/Q3559736","display_name":"Standard test image","level":4,"score":0.43520402908325195},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35088372230529785},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25739505887031555},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.22207725048065186},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2111063301563263},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":1,"locations":[{"id":"doi:10.1145/1290082.1290101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1290082.1290101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the international workshop on Workshop on multimedia information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"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":40,"referenced_works":["https://openalex.org/W57814663","https://openalex.org/W1537642266","https://openalex.org/W1549285799","https://openalex.org/W1592301647","https://openalex.org/W1625255723","https://openalex.org/W1676552347","https://openalex.org/W1880262756","https://openalex.org/W1935837848","https://openalex.org/W1966812932","https://openalex.org/W2007709031","https://openalex.org/W2016871293","https://openalex.org/W2040271314","https://openalex.org/W2093990122","https://openalex.org/W2097333193","https://openalex.org/W2100316723","https://openalex.org/W2104825706","https://openalex.org/W2107743791","https://openalex.org/W2109868644","https://openalex.org/W2113169966","https://openalex.org/W2116908796","https://openalex.org/W2117074709","https://openalex.org/W2124386111","https://openalex.org/W2127370936","https://openalex.org/W2129758682","https://openalex.org/W2134237567","https://openalex.org/W2143314306","https://openalex.org/W2147237076","https://openalex.org/W2150692003","https://openalex.org/W2154301842","https://openalex.org/W2154318594","https://openalex.org/W2154422044","https://openalex.org/W2155904486","https://openalex.org/W2157465536","https://openalex.org/W2161472331","https://openalex.org/W2171706135","https://openalex.org/W2172191903","https://openalex.org/W2819775595","https://openalex.org/W2872346004","https://openalex.org/W3149830556","https://openalex.org/W4233135949"],"related_works":["https://openalex.org/W2065905229","https://openalex.org/W4288374102","https://openalex.org/W2950765678","https://openalex.org/W2938810646","https://openalex.org/W2106036226","https://openalex.org/W2401094681","https://openalex.org/W2399159263","https://openalex.org/W3212974055","https://openalex.org/W2729514902","https://openalex.org/W1999931200"],"abstract_inverted_index":{"Although":[0],"it":[1,123],"has":[2],"been":[3],"studied":[4],"for":[5,25],"many":[6,81],"years,":[7],"image":[8,27,32,53,153,181],"classification":[9,195],"is":[10,45,59,117,124],"still":[11],"a":[12,20,34,55,62,105,112,127,171],"challenging":[13],"problem.":[14],"In":[15,155],"this":[16],"paper,":[17],"we":[18,157],"propose":[19,158],"visual":[21,37,43,56,76,149],"language":[22,57,90],"modeling":[23],"method":[24,142,188],"content-based":[26],"classification.":[28,154,182],"It":[29],"transforms":[30],"each":[31,42,52,100],"into":[33],"matrix":[35],"of":[36,64,75,89,101,108,148],"words,":[38,163],"and":[39,72,98],"assumes":[40],"that":[41,134,186],"word":[44],"conditionally":[46],"dependent":[47],"on":[48,137],"its":[49,115],"neighbors.":[50],"For":[51],"category,":[54],"model":[58,109],"constructed":[60],"using":[61],"set":[63],"training":[65],"images,":[66],"which":[67,102,164],"captures":[68],"both":[69],"the":[70,140,145,161,176],"co-occurrence":[71],"proximity":[73],"information":[74],"words.":[77],"According":[78],"to":[79,104,159,166,179],"how":[80,121],"neighbors":[82],"are":[83,135],"taken":[84],"in":[85,152,170,175],"consideration,":[86],"three":[87],"kinds":[88],"models":[91],"can":[92,143,189],"be":[93],"trained,":[94],"including":[95],"unigram,":[96],"bigram":[97],"trigram,":[99],"corresponds":[103],"different":[106],"level":[107],"complexity.":[110],"Given":[111],"test":[113],"image,":[114,178],"category":[116,172],"determined":[118],"by":[119],"estimating":[120],"likely":[122],"generated":[125],"under":[126],"specific":[128],"category.":[129],"Compared":[130],"with":[131],"traditional":[132],"methods":[133],"based":[136],"bag-of-words":[138],"models,":[139],"proposed":[141],"utilize":[144],"spatial":[146],"correlation":[147],"words":[150],"effectively":[151],"addition,":[156],"use":[160],"absent":[162],"refer":[165],"those":[167],"appearing":[168],"frequently":[169],"but":[173],"not":[174],"target":[177],"help":[180],"Experimental":[183],"results":[184],"show":[185],"our":[187],"achieve":[190],"comparable":[191],"accuracy":[192],"while":[193],"performing":[194],"much":[196],"more":[197],"quickly.":[198]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}