{"id":"https://openalex.org/W2106624428","doi":"https://doi.org/10.1109/cvpr.2009.5206718","title":"Towards total scene understanding: Classification, annotation and segmentation in an automatic framework","display_name":"Towards total scene understanding: Classification, annotation and segmentation in an automatic framework","publication_year":2009,"publication_date":"2009-06-01","ids":{"openalex":"https://openalex.org/W2106624428","doi":"https://doi.org/10.1109/cvpr.2009.5206718","mag":"2106624428"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2009.5206718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2009.5206718","pdf_url":null,"source":{"id":"https://openalex.org/S4363607795","display_name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2009 IEEE Conference on Computer Vision and Pattern Recognition","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/A5009049500","display_name":"Li-Jia Li","orcid":"https://orcid.org/0000-0001-5850-7013"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Li-Jia Li","raw_affiliation_strings":["Department of Computer Science, Princeton University, USA","Department of Computer Science, Princeton University, Princeton , NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Department of Computer Science, Princeton University, Princeton , NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059955534","display_name":"Richard Socher","orcid":"https://orcid.org/0000-0002-3577-639X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Socher","raw_affiliation_strings":["Department of Computer Science, Princeton University, USA","Department of Computer Science, Princeton University, Princeton , NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Department of Computer Science, Princeton University, Princeton , NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100450462","display_name":"Li Fei-Fei","orcid":"https://orcid.org/0000-0002-7481-0810"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Fei-Fei","raw_affiliation_strings":["Department of Computer Science, Princeton University, USA","Department of Computer Science, Princeton University, Princeton , NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Department of Computer Science, Princeton University, Princeton , NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009049500"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":20.0307,"has_fulltext":false,"cited_by_count":496,"citation_normalized_percentile":{"value":0.99281867,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2036","last_page":"2043"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998999834060669,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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":0.9997000098228455,"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":0.8206733465194702},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7065277099609375},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5815389156341553},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5057146549224854},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4839625656604767},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4671791195869446},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42761823534965515},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4259685277938843},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4166209399700165},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39777302742004395},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3196718096733093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8206733465194702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7065277099609375},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5815389156341553},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5057146549224854},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4839625656604767},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4671791195869446},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42761823534965515},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4259685277938843},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4166209399700165},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39777302742004395},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3196718096733093}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cvpr.2009.5206718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2009.5206718","pdf_url":null,"source":{"id":"https://openalex.org/S4363607795","display_name":"2009 IEEE Conference on Computer Vision and Pattern Recognition","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2009 IEEE Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.155.3663","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.155.3663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.stanford.edu/groups/vision/documents/LiSocherFei-Fei_CVPR2009.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1578226009","https://openalex.org/W1584193343","https://openalex.org/W1666447063","https://openalex.org/W1997600326","https://openalex.org/W1999478155","https://openalex.org/W2005455151","https://openalex.org/W2020842694","https://openalex.org/W2056860348","https://openalex.org/W2080289064","https://openalex.org/W2080972498","https://openalex.org/W2081293863","https://openalex.org/W2081580037","https://openalex.org/W2098355199","https://openalex.org/W2103630129","https://openalex.org/W2107034620","https://openalex.org/W2112301665","https://openalex.org/W2123053055","https://openalex.org/W2124386111","https://openalex.org/W2126747264","https://openalex.org/W2128197086","https://openalex.org/W2129004009","https://openalex.org/W2131743987","https://openalex.org/W2134135198","https://openalex.org/W2137471889","https://openalex.org/W2143854982","https://openalex.org/W2146352414","https://openalex.org/W2147625498","https://openalex.org/W2149035855","https://openalex.org/W2150692003","https://openalex.org/W2162820221","https://openalex.org/W2172191903","https://openalex.org/W2296770417","https://openalex.org/W4241222664","https://openalex.org/W4248892431","https://openalex.org/W4285719527","https://openalex.org/W6634576794","https://openalex.org/W6634846276","https://openalex.org/W6637249095","https://openalex.org/W6654952580","https://openalex.org/W6672443193","https://openalex.org/W6674646328","https://openalex.org/W6678637433","https://openalex.org/W6678865028","https://openalex.org/W6681508479","https://openalex.org/W6681769576","https://openalex.org/W6682458996"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Given":[0],"an":[1],"image,":[2],"we":[3],"propose":[4,126],"a":[5,27,50,53,75,96,100,127],"hierarchical":[6],"generative":[7,90],"model":[8,38,91,98,177],"that":[9,39,132],"classifies":[10],"the":[11,24,36,121,154],"overall":[12,122],"scene,":[13],"recognizes":[14],"and":[15,99,110,147,163],"segments":[16],"each":[17],"object":[18],"component,":[19],"as":[20,22,62,145],"well":[21],"annotates":[23],"image":[25],"with":[26,74],"list":[28,76],"of":[29,52,57,77,156],"tags.":[30,88],"To":[31],"our":[32,157,176],"knowledge,":[33],"this":[34],"is":[35,133],"first":[37],"performs":[40],"all":[41,173],"three":[42,174],"tasks":[43],"in":[44],"one":[45],"coherent":[46],"framework.":[47],"For":[48],"instance,":[49],"scene":[51,123,138],"`polo":[54],"game'":[55],"consists":[56],"several":[58],"visual":[59,97],"objects":[60,105],"such":[61,144],"`human',":[63],"`horse',":[64],"`grass',":[65],"etc.":[66],"In":[67,172],"addition,":[68],"it":[69],"can":[70],"be":[71],"further":[72],"annotated":[73],"more":[78],"abstract":[79],"(e.g.":[80,86],"`dusk')":[81],"or":[82],"visually":[83,113],"less":[84],"salient":[85],"`saddle')":[87],"Our":[89],"jointly":[92],"explains":[93],"images":[94,146,165],"through":[95],"textual":[101,115],"model.":[102],"Visually":[103],"relevant":[104],"are":[106,117],"represented":[107],"by":[108,120,159],"regions":[109],"patches,":[111],"while":[112],"irrelevant":[114],"annotations":[116],"influenced":[118],"directly":[119],"class.":[124],"We":[125,152],"fully":[128],"automatic":[129],"learning":[130],"framework":[131,158],"able":[134],"to":[135],"learn":[136],"robust":[137],"models":[139],"from":[140,150,166],"noisy":[141],"Web":[142],"data":[143],"user":[148],"tags":[149],"Flickr.com.":[151],"demonstrate":[153],"effectiveness":[155],"automatically":[160],"classifying,":[161],"annotating":[162],"segmenting":[164],"eight":[167],"classes":[168],"depicting":[169],"sport":[170],"scenes.":[171],"tasks,":[175],"significantly":[178],"outperforms":[179],"state-of-the-art":[180],"algorithms.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":44},{"year":2017,"cited_by_count":26},{"year":2016,"cited_by_count":43},{"year":2015,"cited_by_count":51},{"year":2014,"cited_by_count":40},{"year":2013,"cited_by_count":47},{"year":2012,"cited_by_count":53}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}