{"id":"https://openalex.org/W2073228448","doi":"https://doi.org/10.1109/wacv.2012.6163023","title":"Learning reconfigurable scene representation by tangram model","display_name":"Learning reconfigurable scene representation by tangram model","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2073228448","doi":"https://doi.org/10.1109/wacv.2012.6163023","mag":"2073228448"},"language":"en","primary_location":{"id":"doi:10.1109/wacv.2012.6163023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv.2012.6163023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Workshop on the Applications of Computer Vision (WACV)","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/A5100606995","display_name":"Jun Zhu","orcid":"https://orcid.org/0000-0002-6254-2388"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Zhu","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiaotong University, China","Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiaotong University, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, USA#TAB#","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091159460","display_name":"Tianfu Wu","orcid":"https://orcid.org/0000-0001-8911-5506"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I4210141164","display_name":"Lotus Clinical Research","ror":"https://ror.org/03kzc9a65","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210141164"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianfu Wu","raw_affiliation_strings":["Department of Statistics, University of California, Los Angeles, USA","Lotus Hill Institute for Computer Vision and Information Science, USA"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Lotus Hill Institute for Computer Vision and Information Science, USA","institution_ids":["https://openalex.org/I4210141164"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034228010","display_name":"Song\u2010Chun Zhu","orcid":"https://orcid.org/0009-0008-0876-8117"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I4210141164","display_name":"Lotus Clinical Research","ror":"https://ror.org/03kzc9a65","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210141164"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song-Chun Zhu","raw_affiliation_strings":["Department of Statistics, University of California, Los Angeles, USA","Lotus Hill Institute for Computer Vision and Information Science, USA"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Lotus Hill Institute for Computer Vision and Information Science, USA","institution_ids":["https://openalex.org/I4210141164"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019708391","display_name":"Xiaokang Yang","orcid":"https://orcid.org/0000-0003-4029-3322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiaotong University, China","Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiaotong University, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, USA#TAB#","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100447820","display_name":"Wenjun Zhang","orcid":"https://orcid.org/0000-0002-4497-0688"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Zhang","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiaotong University, China","Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiaotong University, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, USA#TAB#","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100606995"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":3.0536,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.92483517,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"449","last_page":"456"},"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9972000122070312,"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":0.7672604322433472},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6761735677719116},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5850694179534912},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.5235716700553894},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.511358916759491},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4970605671405792},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.49259454011917114},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46521711349487305},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4256012737751007},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.4191415011882782},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37197259068489075},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2360648214817047},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.1993369460105896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12282732129096985}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7672604322433472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6761735677719116},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5850694179534912},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.5235716700553894},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.511358916759491},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4970605671405792},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.49259454011917114},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46521711349487305},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4256012737751007},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.4191415011882782},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37197259068489075},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2360648214817047},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.1993369460105896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12282732129096985},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wacv.2012.6163023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv.2012.6163023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Workshop on the Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.717.9944","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.717.9944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.stat.ucla.edu/%7Ejunzhu/pub/tangram_wacv12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7699999809265137,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6721027143","display_name":null,"funder_award_id":"60932006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6950575921","display_name":null,"funder_award_id":"2010CB731401","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7976160648","display_name":null,"funder_award_id":"2010CB731406","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8975488081","display_name":null,"funder_award_id":"2010CB731406","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W128019999","https://openalex.org/W1566135517","https://openalex.org/W1984049125","https://openalex.org/W2097018403","https://openalex.org/W2099972257","https://openalex.org/W2104825706","https://openalex.org/W2107034620","https://openalex.org/W2130481596","https://openalex.org/W2146022472","https://openalex.org/W2152161678","https://openalex.org/W2154301842","https://openalex.org/W2161969291","https://openalex.org/W2162915993","https://openalex.org/W2168356304","https://openalex.org/W2169177311","https://openalex.org/W2532478580","https://openalex.org/W4205969993","https://openalex.org/W6674642818","https://openalex.org/W6728881802"],"related_works":["https://openalex.org/W2093104230","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W2797752778","https://openalex.org/W2128027845","https://openalex.org/W4386184937","https://openalex.org/W1493875009","https://openalex.org/W4388844349","https://openalex.org/W2105231718","https://openalex.org/W2153939756"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,22,50,122,127],"method":[4],"to":[5,62,88,99],"learn":[6,100],"reconfigurable":[7],"and":[8,19,113,126,154,165],"sparse":[9],"scene":[10,152,163,170],"representation":[11],"in":[12,21,45,55,75,106,120],"the":[13,28,40,46,64,76,101,107,117,136,160,166],"joint":[14,108],"space":[15,65,109],"of":[16,39,66,110,141],"spatial":[17,41,67,111,144],"configuration":[18,112],"appearance":[20,85,149],"principled":[23],"way.":[24],"We":[25,115],"call":[26],"it":[27],"tangram":[29,118,137],"model,":[30],"which":[31],"has":[32],"three":[33],"properties:":[34],"(1)":[35],"Unlike":[36],"fixed":[37],"structure":[38],"pyramid":[42],"widely":[43],"used":[44],"literature,":[47],"we":[48,133],"propose":[49],"compositional":[51],"shape":[52,71],"dictionary":[53,77],"organized":[54],"an":[56],"And-Or":[57],"directed":[58],"acyclic":[59],"graph":[60],"(AOG)":[61],"quantize":[63],"configurations.":[68],"(2)":[69],"The":[70],"primitives":[72],"(called":[73],"tans)":[74],"can":[78],"be":[79],"described":[80],"by":[81],"using":[82],"any":[83],"\u201coff-the-shelf\u201d":[84],"features":[86],"according":[87],"different":[89],"tasks.":[90],"(3)":[91],"A":[92],"dynamic":[93],"programming":[94],"(DP)":[95],"algorithm":[96],"is":[97,139],"utilized":[98],"globally":[102],"optimal":[103],"parse":[104],"tree":[105],"appearance.":[114],"demonstrate":[116],"model":[119,138],"both":[121],"generative":[123],"learning":[124],"formulation":[125],"discriminative":[128],"matching":[129],"kernel.":[130],"In":[131],"experiments,":[132],"show":[134],"that":[135],"capable":[140],"capturing":[142],"meaningful":[143],"configurations":[145],"as":[146,148],"well":[147],"for":[150],"various":[151],"categories,":[153],"achieves":[155],"state-of-the-art":[156],"classification":[157],"performance":[158],"on":[159],"LSP":[161],"15-class":[162],"dataset":[164],"MIT":[167],"67-class":[168],"indoor":[169],"dataset.":[171]},"counts_by_year":[{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}