{"id":"https://openalex.org/W2129004009","doi":"https://doi.org/10.1109/iccv.2007.4408965","title":"Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes","display_name":"Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2129004009","doi":"https://doi.org/10.1109/iccv.2007.4408965","mag":"2129004009"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2007.4408965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2007.4408965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE 11th International Conference on Computer Vision","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/A5103187717","display_name":"Liangliang Cao","orcid":"https://orcid.org/0000-0003-0900-1512"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liangliang Cao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA","Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana- Champaign, Urbana, IL"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana- Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"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","Dept. of Computer Science, Princeton University, USA. feifeili@cs.princeton.edu"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Dept. of Computer Science, Princeton University, USA. feifeili@cs.princeton.edu","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103187717"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":29.2593,"has_fulltext":false,"cited_by_count":363,"citation_normalized_percentile":{"value":0.99745745,"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":"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":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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval 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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9993000030517578,"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":0.9988999962806702,"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/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.7666751146316528},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.7436269521713257},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7101837396621704},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7099392414093018},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.637279748916626},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.609316885471344},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5601593852043152},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5497118830680847},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5382553935050964},{"id":"https://openalex.org/keywords/bag-of-words-model-in-computer-vision","display_name":"Bag-of-words model in computer vision","score":0.5137296915054321},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4527372419834137},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4486364722251892},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4414413869380951},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.36488252878189087},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34922558069229126},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.29584306478500366},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.1989888846874237},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.16451841592788696}],"concepts":[{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.7666751146316528},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7436269521713257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7101837396621704},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7099392414093018},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.637279748916626},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.609316885471344},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5601593852043152},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5497118830680847},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5382553935050964},{"id":"https://openalex.org/C167611913","wikidata":"https://www.wikidata.org/wiki/Q6884747","display_name":"Bag-of-words model in computer vision","level":5,"score":0.5137296915054321},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4527372419834137},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4486364722251892},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4414413869380951},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36488252878189087},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34922558069229126},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.29584306478500366},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.1989888846874237},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.16451841592788696},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv.2007.4408965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2007.4408965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE 11th International Conference on Computer Vision","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W190008395","https://openalex.org/W1516111018","https://openalex.org/W1548595933","https://openalex.org/W1590899626","https://openalex.org/W1625255723","https://openalex.org/W1699734612","https://openalex.org/W1880262756","https://openalex.org/W1999478155","https://openalex.org/W2030536784","https://openalex.org/W2057175746","https://openalex.org/W2107034620","https://openalex.org/W2110300379","https://openalex.org/W2112301665","https://openalex.org/W2115733720","https://openalex.org/W2123241287","https://openalex.org/W2124386111","https://openalex.org/W2128197086","https://openalex.org/W2128460414","https://openalex.org/W2134529554","https://openalex.org/W2134731454","https://openalex.org/W2135512949","https://openalex.org/W2141303268","https://openalex.org/W2152942156","https://openalex.org/W2154422044","https://openalex.org/W2156358825","https://openalex.org/W2157244733","https://openalex.org/W2159372453","https://openalex.org/W2164877691","https://openalex.org/W2171706135","https://openalex.org/W2172191903","https://openalex.org/W2296770417","https://openalex.org/W4231510805","https://openalex.org/W4251485470","https://openalex.org/W6607826182","https://openalex.org/W6632941408","https://openalex.org/W6639619044","https://openalex.org/W6678865028","https://openalex.org/W6682671827","https://openalex.org/W6683978607","https://openalex.org/W6684936967"],"related_works":["https://openalex.org/W2921491680","https://openalex.org/W2251863249","https://openalex.org/W4291700620","https://openalex.org/W2132052677","https://openalex.org/W3159709618","https://openalex.org/W4214866631","https://openalex.org/W2110027950","https://openalex.org/W2318387922","https://openalex.org/W2149035855","https://openalex.org/W1964664592"],"abstract_inverted_index":{"We":[0,212],"present":[1],"a":[2,33,99,113,165,220],"novel":[3],"generative":[4,37],"model":[5,16,104,218],"for":[6,168],"simultaneously":[7,179],"recognizing":[8],"and":[9,12,28,45,56,94,123,181,190,193,224],"segmenting":[10],"object":[11,208],"scene":[13],"classes.":[14],"Our":[15],"is":[17,59,68,136],"inspired":[18],"by":[19,116],"the":[20,54,60,66,86,90,124,129,139,146,150,157,186,214],"traditional":[21],"bag":[22,171],"of":[23,26,35,53,120,149,160,172,188,216,222],"words":[24,173],"representation":[25,78,167],"texts":[27],"images":[29,93],"as":[30,32,203,205],"well":[31,204],"number":[34,221],"related":[36],"models,":[38],"including":[39],"probabilistic":[40],"Latent":[41,46],"Semantic":[42],"Analysis":[43],"(pLSA)":[44],"Dirichlet":[47],"Allocation":[48],"(LDA).":[49],"A":[50],"major":[51],"drawback":[52],"pLSA":[55],"LDA":[57],"models":[58],"assumption":[61],"that":[62],"each":[63,143],"patch":[64],"in":[65,112,185,219],"image":[67,109,118,126,140],"independently":[69],"generated":[70],"given":[71],"its":[72],"corresponding":[73],"latent":[74,102,134],"topic.":[75],"While":[76],"such":[77],"provides":[79,164],"an":[80,108],"efficient":[81],"computational":[82],"method,":[83],"it":[84],"lacks":[85],"power":[87],"to":[88,138,156],"describe":[89],"visually":[91],"coherent":[92,101,170],"scenes.":[95],"Instead,":[96],"we":[97],"propose":[98],"spatially":[100,169],"topic":[103,135,174],"(Spatial-LTM).":[105],"Spatial-LTM":[106,163,177,195],"represents":[107],"containing":[110],"objects":[111],"hierarchical":[114],"way":[115],"over-segmented":[117],"regions":[119],"homogeneous":[121],"appearances":[122],"salient":[125],"patches":[127,141],"within":[128,142],"regions.":[130],"Only":[131],"one":[132],"single":[133],"assigned":[137],"region,":[144],"enforcing":[145],"spatial":[147],"coherency":[148],"model.":[151],"This":[152],"idea":[153],"gives":[154],"rise":[155],"following":[158],"merits":[159],"Spatial-LTM:":[161],"(1)":[162],"unified":[166],"models;":[175],"(2)":[176],"can":[178,196],"segment":[180],"classify":[182],"objects,":[183],"even":[184],"case":[187],"occlusion":[189],"multiple":[191],"instances;":[192],"(3)":[194],"be":[197],"trained":[198],"either":[199],"unsupervised":[200],"or":[201],"supervised,":[202],"when":[206],"partial":[207],"labels":[209],"are":[210],"provided.":[211],"verify":[213],"success":[215],"our":[217],"segmentation":[223],"classification":[225],"experiments.":[226]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":18},{"year":2015,"cited_by_count":26},{"year":2014,"cited_by_count":29},{"year":2013,"cited_by_count":40},{"year":2012,"cited_by_count":28}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}