{"id":"https://openalex.org/W2049332387","doi":"https://doi.org/10.1145/1646396.1646441","title":"Spatial extensions to bag of visual words","display_name":"Spatial extensions to bag of visual words","publication_year":2009,"publication_date":"2009-07-08","ids":{"openalex":"https://openalex.org/W2049332387","doi":"https://doi.org/10.1145/1646396.1646441","mag":"2049332387"},"language":"en","primary_location":{"id":"doi:10.1145/1646396.1646441","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1646396.1646441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Image and Video Retrieval","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/A5021021968","display_name":"Ville Viitaniemi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ville Viitaniemi","raw_affiliation_strings":["Helsinki University of Technology (TKK), TKK, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Helsinki University of Technology (TKK), TKK, Finland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036133390","display_name":"Jorma Laaksonen","orcid":"https://orcid.org/0000-0001-7218-3131"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jorma Laaksonen","raw_affiliation_strings":["Helsinki University of Technology (TKK), TKK, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Helsinki University of Technology (TKK), TKK, Finland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4135,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.91027986,"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":"1","last_page":"8"},"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":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.994700014591217,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7659085988998413},{"id":"https://openalex.org/keywords/bag-of-words-model-in-computer-vision","display_name":"Bag-of-words model in computer vision","score":0.7491008043289185},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6741263270378113},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6645749807357788},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5682101249694824},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5649059414863586},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5191382765769958},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.46718695759773254},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4484736919403076},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.37229347229003906},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.31519991159439087},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2742498219013214},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.24118700623512268}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7659085988998413},{"id":"https://openalex.org/C167611913","wikidata":"https://www.wikidata.org/wiki/Q6884747","display_name":"Bag-of-words model in computer vision","level":5,"score":0.7491008043289185},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6741263270378113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6645749807357788},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5682101249694824},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5649059414863586},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5191382765769958},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.46718695759773254},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4484736919403076},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.37229347229003906},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.31519991159439087},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2742498219013214},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.24118700623512268},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1646396.1646441","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1646396.1646441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Image and Video Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G7478037009","display_name":null,"funder_award_id":"FP7/2007.2013216529","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W255846030","https://openalex.org/W1484682289","https://openalex.org/W1566768190","https://openalex.org/W1587444475","https://openalex.org/W2036718463","https://openalex.org/W2106097867","https://openalex.org/W2111352094","https://openalex.org/W2112020727","https://openalex.org/W2128017662","https://openalex.org/W2131846894","https://openalex.org/W2145406111","https://openalex.org/W2151103935","https://openalex.org/W2153635508","https://openalex.org/W2154683974","https://openalex.org/W2162915993","https://openalex.org/W2172188317","https://openalex.org/W2435338979","https://openalex.org/W3120421331"],"related_works":["https://openalex.org/W1615295117","https://openalex.org/W2158102958","https://openalex.org/W2035094092","https://openalex.org/W2277784908","https://openalex.org/W2045213079","https://openalex.org/W2938717424","https://openalex.org/W2587721114","https://openalex.org/W2032791227","https://openalex.org/W2179703327","https://openalex.org/W2518262377"],"abstract_inverted_index":{"The":[0,23,71],"Bag":[1],"of":[2,77,83,93],"Visual":[3],"Words":[4],"(BoV)":[5],"paradigm":[6],"has":[7],"successfully":[8],"been":[9],"applied":[10],"to":[11,38],"image":[12,18,48],"content":[13],"analysis":[14],"tasks":[15],"such":[16],"as":[17],"classification":[19],"and":[20,40,88],"object":[21],"detection.":[22],"basic":[24],"BoV":[25,39],"approach":[26],"overlooks":[27],"spatial":[28,36],"descriptor":[29],"distribution":[30],"within":[31],"images.":[32],"Here":[33],"we":[34,54],"describe":[35],"extensions":[37],"experimentally":[41],"compare":[42,55],"them":[43],"in":[44],"the":[45,66,84,91],"VOC2007":[46],"benchmark":[47],"category":[49],"detection":[50],"task.":[51],"In":[52],"particular,":[53],"two":[56,75],"ways":[57],"for":[58],"tiling":[59,63,69],"images":[60],"geometrically:":[61],"soft":[62],"approach---proposed":[64],"here---and":[65],"traditional":[67],"hard":[68],"technique.":[70],"experiments":[72],"also":[73],"address":[74],"methods":[76],"fusing":[78],"information":[79],"from":[80],"several":[81],"tilings":[82],"images:":[85],"post-classifier":[86],"fusion":[87,89],"on":[90],"level":[92],"a":[94],"SVM":[95],"kernel.":[96]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"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":7},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}