{"id":"https://openalex.org/W2158331285","doi":"https://doi.org/10.1109/icme.2010.5583852","title":"Multiple instance learning using visual phrases for object classification","display_name":"Multiple instance learning using visual phrases for object classification","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2158331285","doi":"https://doi.org/10.1109/icme.2010.5583852","mag":"2158331285"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2010.5583852","doi":"https://doi.org/10.1109/icme.2010.5583852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2010.5583852","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068","observed_orcids":["https://orcid.org/0000-0002-5668-9068","https://orcid.org/0009-0008-7981-0757"]},"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":"Yan Song","raw_affiliation_strings":["MOE-Microsoft Key Laboratory of MCC and Department of EEIS, University of Science and Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-Microsoft Key Laboratory of MCC and Department of EEIS, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111504451","display_name":"Qi Tian","orcid":"https://orcid.org/0000-0002-5165-4325","observed_orcids":["https://orcid.org/0000-0002-5165-4325","https://orcid.org/0000-0002-7252-5047"]},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Department of Computer Science, University of Texas, San Antonio, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas, San Antonio, TX, USA","institution_ids":["https://openalex.org/I45438204"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101534435","display_name":"Mengyue Wang","orcid":"https://orcid.org/0000-0002-2319-3664","observed_orcids":["https://orcid.org/0000-0002-2319-3664"]},"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":"Mengyue Wang","raw_affiliation_strings":["MOE-Microsoft Key Laboratory of MCC and Department of EEIS, University of Science and Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-Microsoft Key Laboratory of MCC and Department of EEIS, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392547","display_name":"Heng Liu","orcid":"https://orcid.org/0009-0006-7407-1196","observed_orcids":["https://orcid.org/0009-0006-7407-1196","https://orcid.org/0009-0006-4959-6062"]},"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":"Heng Liu","raw_affiliation_strings":["MOE-Microsoft Key Laboratory of MCC and Department of EEIS, University of Science and Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-Microsoft Key Laboratory of MCC and Department of EEIS, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827","observed_orcids":["https://orcid.org/0000-0002-0859-2827"]},"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":"Lirong Dai","raw_affiliation_strings":["MOE-Microsoft Key Laboratory of MCC and Department of EEIS, University of Science and Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-Microsoft Key Laboratory of MCC and Department of EEIS, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.276,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.38327074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"649","last_page":"654"},"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":0.9829000234603882,"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":0.9829000234603882,"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":0.015799999237060547,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0008999999845400453,"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/multiple-instance-learning","display_name":"multiple instance learning","score":0.9980000257492065},{"id":"https://openalex.org/keywords/object-classification","display_name":"object classification","score":0.9570000171661377},{"id":"https://openalex.org/keywords/weakly-labeled-images","display_name":"weakly labeled images","score":0.8600000143051147},{"id":"https://openalex.org/keywords/bag-of-words","display_name":"bag-of-words","score":0.7509999871253967},{"id":"https://openalex.org/keywords/visual-words","display_name":"visual words","score":0.8899999856948853},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"image segmentation","score":0.6129999756813049},{"id":"https://openalex.org/keywords/spatial-coherence","display_name":"spatial coherence","score":0.859000027179718},{"id":"https://openalex.org/keywords/background-clutter","display_name":"background clutter","score":0.6610000133514404},{"id":"https://openalex.org/keywords/appearance-variation","display_name":"appearance variation","score":0.8429999947547913}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7746418118476868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7345200777053833},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.719968318939209},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.62978595495224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5978745222091675},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5871813893318176},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.56224524974823},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5373989343643188},{"id":"https://openalex.org/C167611913","wikidata":"https://www.wikidata.org/wiki/Q6884747","display_name":"Bag-of-words model in computer vision","level":5,"score":0.5315995216369629},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5015439987182617},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.468107670545578},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46053528785705566},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45280224084854126},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.41871386766433716},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4111332893371582},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.340994656085968},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33494263887405396},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.15034663677215576},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1423863172531128},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2010.5583852","doi":"https://doi.org/10.1109/icme.2010.5583852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2010.5583852","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1540386283","https://openalex.org/W1570918423","https://openalex.org/W1880262756","https://openalex.org/W1975001816","https://openalex.org/W2030536784","https://openalex.org/W2097018403","https://openalex.org/W2097323414","https://openalex.org/W2098166271","https://openalex.org/W2107034620","https://openalex.org/W2112301665","https://openalex.org/W2115729631","https://openalex.org/W2115733720","https://openalex.org/W2118585731","https://openalex.org/W2129004009","https://openalex.org/W2136595724","https://openalex.org/W2139882995","https://openalex.org/W2151103935","https://openalex.org/W2151259137","https://openalex.org/W2154318594","https://openalex.org/W2154422044","https://openalex.org/W2162915993","https://openalex.org/W2168133252","https://openalex.org/W2170146448","https://openalex.org/W2172191903"],"related_works":["https://openalex.org/W2356991337","https://openalex.org/W2795136082","https://openalex.org/W1966233349","https://openalex.org/W2011085767","https://openalex.org/W2313226226","https://openalex.org/W1980061733","https://openalex.org/W2002173128","https://openalex.org/W2786994615","https://openalex.org/W2544405876","https://openalex.org/W1570918423"],"abstract_inverted_index":{"Recently,":[0],"bag":[1],"of":[2,25,31,106],"words":[3,111],"(BoW)":[4],"model":[5],"has":[6],"led":[7],"to":[8,18,38,132],"many":[9],"significant":[10],"results":[11],"in":[12,41],"visual":[13,26,32,85,97,110],"object":[14,33,59],"classification.":[15],"However,":[16],"due":[17],"the":[19,28,96,123,136],"limited":[20],"descriptive":[21,119],"and":[22,73,109,163],"discriminative":[23],"ability":[24,120],"words,":[27],"resulting":[29],"performance":[30],"classification":[34],"is":[35,60,99,130],"still":[36],"incomparable":[37],"its":[39],"analogy":[40],"text":[42],"domain,":[43],"i.e.":[44],"document":[45],"categorization.":[46],"Furthermore,":[47],"for":[48],"weakly":[49,137],"labeled":[50,138],"image":[51,104,139],"data,":[52],"where":[53],"we":[54,81],"only":[55],"know":[56],"whether":[57],"an":[58],"present":[61],"or":[62],"not,":[63],"traditional":[64],"learning":[65],"based":[66,87],"methods":[67],"may":[68,116],"suffer":[69],"from":[70,102,135],"background":[71],"clutters":[72],"large":[74],"appearance":[75,108],"variations.":[76],"To":[77],"address":[78],"these":[79],"issues,":[80],"propose":[82],"a":[83,127],"novel":[84],"phrase":[86,98],"Multiple":[88],"Instance":[89],"Learning":[90],"(MIL)":[91],"method.":[92],"In":[93],"this":[94],"method,":[95],"first":[100],"generated":[101],"over-segmented":[103],"regions":[105],"homogeneous":[107],"within":[112],"each":[113],"region,":[114],"which":[115],"provide":[117],"enhanced":[118],"by":[121],"enforcing":[122],"spatial":[124],"coherency.":[125],"Then":[126],"MIL":[128],"algorithm":[129],"applied":[131],"efficiently":[133],"learn":[134],"data.":[140],"The":[141],"experiments":[142],"on":[143],"benchmark":[144],"datasets":[145],"show":[146],"that":[147],"our":[148],"proposed":[149],"method":[150],"always":[151],"significantly":[152],"outperforms":[153],"several":[154],"state-of-the-art":[155],"algorithms,":[156],"such":[157],"as":[158],"Spatial":[159],"Pyramid":[160],"Matching":[161],"(SPM)":[162],"Spatial-LTM.":[164]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}