{"id":"https://openalex.org/W2891789699","doi":"https://doi.org/10.13016/m2vt1gs9h","title":"COMPUTER VISION AND DEEP LEARNING WITH APPLICATIONS TO OBJECT DETECTION, SEGMENTATION, AND DOCUMENT ANALYSIS","display_name":"COMPUTER VISION AND DEEP LEARNING WITH APPLICATIONS TO OBJECT DETECTION, SEGMENTATION, AND DOCUMENT ANALYSIS","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2891789699","doi":"https://doi.org/10.13016/m2vt1gs9h","mag":"2891789699"},"language":"en","primary_location":{"id":"pmh:oai:drum.lib.umd.edu:1903/20758","is_oa":true,"landing_page_url":"http://hdl.handle.net/1903/20758","pdf_url":"http://hdl.handle.net/1903/20758","source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1903/20758","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017048711","display_name":"Xianzhi Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Du, Xianzhi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5017048711"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.156700000166893,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.156700000166893,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6763944625854492},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6404114365577698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5824615955352783},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5641868710517883},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.49876856803894043},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49794888496398926},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4272765517234802},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3434918522834778}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6763944625854492},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6404114365577698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5824615955352783},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5641868710517883},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.49876856803894043},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49794888496398926},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4272765517234802},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3434918522834778}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:drum.lib.umd.edu:1903/20758","is_oa":true,"landing_page_url":"http://hdl.handle.net/1903/20758","pdf_url":"http://hdl.handle.net/1903/20758","source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},{"id":"mag:2891789699","is_oa":false,"landing_page_url":"https://drum.lib.umd.edu/handle/1903/20758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null},{"id":"doi:10.13016/m2vt1gs9h","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m2vt1gs9h","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"pmh:oai:drum.lib.umd.edu:1903/20758","is_oa":true,"landing_page_url":"http://hdl.handle.net/1903/20758","pdf_url":"http://hdl.handle.net/1903/20758","source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2891789699.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1028530408","https://openalex.org/W2982010943","https://openalex.org/W2728123246","https://openalex.org/W761653158","https://openalex.org/W2786443043","https://openalex.org/W2757077288","https://openalex.org/W3191548810","https://openalex.org/W3080630303","https://openalex.org/W2972006294","https://openalex.org/W3173251056","https://openalex.org/W3112887005","https://openalex.org/W3146425478","https://openalex.org/W2296614844","https://openalex.org/W2736558453","https://openalex.org/W3152769940","https://openalex.org/W1509221100","https://openalex.org/W3017205068","https://openalex.org/W2937813349","https://openalex.org/W1505928915","https://openalex.org/W3150006719"],"abstract_inverted_index":{"There":[0,211],"are":[1,30,42,66,101,168,185,212,283,453],"three":[2,213,451],"work":[3,214],"on":[4,22,94,215,497,522],"signature":[5,18,90,104,113,152,209],"matching":[6,19,75,91,153],"for":[7,49,203,218,235,247,253,287,336,393,427],"document":[8],"analysis.":[9],"In":[10,82,144,158,223,354,415],"the":[11,34,46,83,109,118,125,141,145,161,171,189,198,201,205,224,304,313,343,351,355,361,371,388,400,416,441,464,473,484,502,527,531,550],"first":[12,225,362],"work,":[13,85,147,163,226,357,363,418],"we":[14,86,148,227,332,419,536],"propose":[15,228,333,420],"a":[16,59,79,88,150,229,296,334,348,364,376,421,468,505],"large-scale":[17],"method":[20,92,154,301,318,335,379],"based":[21,93,298,436,496],"locality":[23],"sensitive":[24],"hashing":[25,41],"(LSH).":[26],"Shape":[27,98],"Context":[28,99],"features":[29,100,128,167],"used":[31,284,510],"to":[32,44,123,131,160,175,187,267,302,311,350,360,369,382,387,476,481,490,501,515,519,525,541,548],"describe":[33,176],"structure":[35],"of":[36,40,120,140,173,191,200,250,273,290,402,404,410,530,553],"signatures.":[37,51,181],"Two":[38],"stages":[39],"performed":[43],"find":[45],"nearest":[47],"neighbors":[48],"query":[50],"We":[52,115,134,294],"show":[53,197],"that":[54],"our":[55,554],"algorithm":[56],"can":[57],"achieve":[58],"high":[60],"accuracy":[61],"even":[62],"when":[63,76,325,493,511],"few":[64],"signatures":[65,174],"collected":[67],"from":[68,103,170,307,399],"one":[69,523],"same":[70],"person":[71],"and":[72,179,207,221,237,276,328,433,471],"perform":[73],"fast":[74,236],"dealing":[77],"with":[78,408],"large":[80],"dataset.":[81],"second":[84,162,356],"present":[87,149],"novel":[89,377],"supervised":[95],"topic":[96,121],"models.":[97,157],"extracted":[102,169],"shape":[105,126,165,529],"contours":[106],"which":[107,129],"capture":[108],"local":[110],"variations":[111],"in":[112,285,358,483],"properties.":[114],"then":[116],"use":[117],"concept":[119],"models":[122],"learn":[124],"context":[127,166],"correspond":[130],"individual":[132,457],"authors.":[133],"demonstrate":[135],"considerable":[136],"improvement":[137],"over":[138],"state":[139],"art":[142],"methods.":[143],"third":[146,417],"partial":[151,180,206],"using":[155,472],"graphical":[156],"additional":[159],"modified":[164],"contour":[172],"both":[177,204],"full":[178,208],"Hierarchical":[182],"Dirichlet":[183],"processes":[184],"implemented":[186],"infer":[188],"number":[190],"salient":[192],"regions":[193],"needed.":[194],"The":[195,241],"results":[196],"effectiveness":[199],"approach":[202],"matching.":[210],"deep":[216,230,258,280,423],"learning":[217,551],"object":[219,265],"detection":[220,396],"segmentation.":[222,429],"neural":[231,281,424],"network":[232,243,260,299,341,344,366,425,432],"fusion":[233,244,300,345,365],"architecture":[234,245,346,426],"robust":[238],"pedestrian":[239,271,292,352,389],"detection.":[240],"proposed":[242],"allows":[246],"parallel":[248,286],"processing":[249],"multiple":[251,279,372,491,538],"networks":[252,282,309],"speed.":[254],"A":[255,430],"single":[256],"shot":[257],"convolutional":[259],"is":[261,367,380,397,438,460,509],"trained":[262,368,439],"as":[263,347,440,467,547],"an":[264,456],"detector":[266],"generate":[268,312],"all":[269,308],"possible":[270],"candidates":[272],"different":[274,517],"sizes":[275],"occlusions.":[277],"Next,":[278],"further":[288],"refinement":[289],"these":[291],"candidates.":[293,390],"introduce":[295],"soft-rejection":[297],"fuse":[303,370],"soft":[305],"metrics":[306],"together":[310],"final":[314],"confidence":[315],"scores.":[316],"Our":[317],"performs":[319],"better":[320,447],"than":[321],"existing":[322],"state-of-the-arts,":[323],"especially":[324],"detecting":[326],"small-size":[327],"occluded":[329],"pedestrians.":[330],"Furthermore,":[331,375],"integrating":[337],"pixel-wise":[338],"semantic":[339],"segmentation":[340,444,533],"into":[342],"reinforcement":[349],"detector.":[353],"addition":[359],"classification":[373],"networks.":[374],"soft-label":[378,474],"devised":[381],"assign":[383,477,516],"floating":[384],"point":[385],"labels":[386],"This":[391],"metric":[392],"each":[394],"candidate":[395],"derived":[398],"percentage":[401],"overlap":[403],"its":[405,498],"bounding":[406],"box":[407],"those":[409],"other":[411],"ground":[412],"truth":[413],"classes.":[414],"boundary-sensitive":[422,458,507,543],"portrait":[428,443,544],"residual":[431],"atrous":[434],"convolution":[435],"framework":[437],"base":[442],"network.":[445],"To":[446],"solve":[448],"boundary":[449,465,485],"segmentation,":[450],"techniques":[452],"introduced.":[454],"First,":[455],"kernel":[459,508],"introduced":[461],"by":[462],"labeling":[463],"pixels":[466,482],"separate":[469],"class":[470],"strategy":[475],"floating-point":[478],"label":[479],"vectors":[480],"class.":[486],"Each":[487],"pixel":[488,520],"contributes":[489],"classes":[492],"updating":[494,512],"loss":[495,513],"relative":[499],"position":[500],"contour.":[503],"Second,":[504],"global":[506,528],"function":[514],"weights":[518],"locations":[521],"image":[524],"constrain":[526],"resulted":[532],"map.":[534],"Third,":[535],"add":[537],"binary":[539],"classifiers":[540],"classify":[542],"attributes,":[545],"so":[546],"refine":[549],"process":[552],"model.":[555]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}