{"id":"https://openalex.org/W7052808501","doi":null,"title":"Street Scenes : towards scene understanding in still images","display_name":"Street Scenes : towards scene understanding in still images","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W7052808501"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.3289","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.3289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cbcl.mit.edu/projects/cbcl/publications/theses/thesis-bileschi.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5089687759","display_name":"Stanley Bileschi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bileschi, Stanley M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5089687759"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7097,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.80644274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.8852999806404114,"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":0.8852999806404114,"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":0.07450000196695328,"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":0.027300000190734863,"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/scene-understanding","display_name":"scene understanding","score":0.9660000205039978},{"id":"https://openalex.org/keywords/street-scenes","display_name":"street scenes","score":0.8339999914169312},{"id":"https://openalex.org/keywords/object-recognition","display_name":"object recognition","score":0.7360000014305115},{"id":"https://openalex.org/keywords/object-detection","display_name":"object detection","score":0.8450000286102295},{"id":"https://openalex.org/keywords/image-annotation","display_name":"image annotation","score":0.42100000381469727},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"human visual system model","score":0.871999979019165},{"id":"https://openalex.org/keywords/imaging-features","display_name":"imaging features","score":0.5979999899864197},{"id":"https://openalex.org/keywords/success-indicators","display_name":"success indicators","score":0.5370000004768372},{"id":"https://openalex.org/keywords/object-relations","display_name":"object relations","score":0.5080000162124634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6840999722480774},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6593000292778015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.65829998254776},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6517999768257141},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6031000018119812},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5558000206947327},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4724000096321106},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.45989999175071716},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.447299987077713},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.36000001430511475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3366999924182892},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.29760000109672546},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.26589998602867126},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.3289","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.3289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cbcl.mit.edu/projects/cbcl/publications/theses/thesis-bileschi.pdf","raw_type":"text"},{"id":"pmh:ADA454810","doi":null,"is_oa":false,"landing_page_url":"http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA454810","pdf_url":null,"source":{"id":"https://openalex.org/S4406923043","display_name":"Defense Technical Information Center (DTIC)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"DTIC","raw_type":"Text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/37896","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/1721.1/37896","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.5142999887466431}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7015745250","https://openalex.org/W3182154933","https://openalex.org/W1558349653","https://openalex.org/W2288658809","https://openalex.org/W4405916713","https://openalex.org/W7015773522","https://openalex.org/W2207177639","https://openalex.org/W2279557532","https://openalex.org/W6989975854","https://openalex.org/W2516277427"],"abstract_inverted_index":{"This":[0],"thesis":[1],"describes":[2],"an":[3,167],"effort":[4],"to":[5,14,27,30,180,218,239],"construct":[6],"a":[7,90,135,143,258],"scene":[8],"understanding":[9],"system":[10,24,81,130,149,185,206,253],"that":[11,36,139,156],"is":[12,82,89,207],"able":[13],"analyze":[15],"the":[16,23,33,47,52,57,60,63,69,72,83,105,146,192,199,202,232,279,284,298],"content":[17],"of":[18,32,39,49,54,59,65,71,94,137,145,176,195,224,261],"real":[19],"images.":[20],"While":[21],"constructing":[22],"we":[25],"had":[26],"provide":[28],"solutions":[29],"many":[31],"fundamental":[34],"questions":[35],"every":[37],"student":[38],"object":[40,171],"recognition":[41],"deals":[42],"with":[43,163],"daily.":[44],"These":[45],"include":[46],"choice":[48,53],"data":[50,86,101,114],"set,":[51],"success":[55],"measurement,":[56],"representation":[58,70,169,288],"image":[61,111,133,160,264],"content,":[62],"selection":[64],"inference":[66],"engine,":[67],"and":[68,127,227,255,263,276,278],"relations":[73,241,280],"between":[74,242,281],"objects.":[75],"The":[76,251,286],"main":[77],"test-bed":[78],"for":[79,118,170],"our":[80,152,184],"CBCL":[84],"StreetScenes":[85],"base.":[87],"It":[88],"carefully":[91],"labeled":[92,117],"set":[93,102,115,136,260],"images,":[95],"much":[96],"larger":[97],"than":[98],"any":[99],"similar":[100],"available":[103],"at":[104],"time":[106],"it":[107],"was":[108,116,215],"collected.":[109],"Each":[110],"in":[112,151,221,244,291,294],"this":[113,157],"9":[119],"common":[120],"classes":[121],"such":[122,268,273],"as":[123,246,269,274],"cars,":[124,270],"pedestrians,":[125],"roads":[126],"trees.":[128],"Our":[129,205],"represents":[131],"each":[132],"using":[134,209,257],"features":[138],"are":[140],"based":[141],"on":[142],"model":[144,240],"human":[147],"visual":[148],"constructed":[150],"lab.":[153],"We":[154,189,229],"demonstrate":[155,230],"biologically":[158],"motivated":[159],"representation,":[161],"along":[162],"its":[164],"extensions,":[165],"constitutes":[166],"effective":[168],"detection,":[172],"facilitating":[173],"unprecedented":[174],"levels":[175],"detection":[177],"accuracy.":[178],"Similarly":[179],"biological":[181],"vision":[182,220],"systems,":[183],"uses":[186],"hierarchical":[187],"representations.":[188],"therefore":[190],"explore":[191],"possible":[193],"ways":[194],"combining":[196],"information":[197],"across":[198],"hierarchy":[200],"into":[201],"final":[203],"perception.":[204],"trained":[208],"standard":[210,234],"machine":[211],"learning":[212],"machinery,":[213],"which":[214],"first":[216],"applied":[217],"computer":[219],"earlier":[222],"work":[223],"Prof.":[225],"Poggio":[226],"others.":[228],"how":[231],"same":[233,287],"methods":[235],"can":[236],"be":[237],"used":[238],"objects":[243,267,272,282,293],"images":[245],"well,":[247],"capturing":[248],"context":[249],"information.":[250],"resulting":[252],"detects":[254],"localizes,":[256],"unified":[259],"tools":[262],"representations,":[265],"compact":[266],"amorphous":[271],"trees":[275],"roads,":[277],"within":[283],"scene.":[285],"also":[289],"excels":[290],"identifying":[292],"clutter":[295],"without":[296],"scanning":[297],"image.":[299]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}