{"id":"https://openalex.org/W2589217321","doi":"https://doi.org/10.13016/m2354t","title":"GEOMETRIC REPRESENTATIONS AND DEEP GAUSSIAN CONDITIONAL RANDOM FIELD NETWORKS FOR COMPUTER VISION","display_name":"GEOMETRIC REPRESENTATIONS AND DEEP GAUSSIAN CONDITIONAL RANDOM FIELD NETWORKS FOR COMPUTER VISION","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2589217321","doi":"https://doi.org/10.13016/m2354t","mag":"2589217321"},"language":"en","primary_location":{"id":"pmh:oai:drum.lib.umd.edu:1903/19036","is_oa":true,"landing_page_url":"https://doi.org/10.13016/M2354T","pdf_url":"http://hdl.handle.net/1903/19036","source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","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":null,"raw_type":"Dissertation"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1903/19036","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071825172","display_name":"Raviteja Vemulapalli","orcid":"https://orcid.org/0000-0003-0425-7797"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vemulapalli, Raviteja","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5071825172"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T10057","display_name":"Face and Expression Recognition","score":0.9835000038146973,"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/T10057","display_name":"Face and Expression Recognition","score":0.9835000038146973,"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":0.9706000089645386,"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":0.9617999792098999,"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/conditional-random-field","display_name":"Conditional random field","score":0.6802425384521484},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5595065355300903},{"id":"https://openalex.org/keywords/gaussian-random-field","display_name":"Gaussian random field","score":0.5211110711097717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.483167827129364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43492555618286133},{"id":"https://openalex.org/keywords/random-field","display_name":"Random field","score":0.4278334677219391},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.34654366970062256},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.345605731010437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3084137439727783},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.30124300718307495},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15096497535705566},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13663437962532043}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6802425384521484},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5595065355300903},{"id":"https://openalex.org/C51267290","wikidata":"https://www.wikidata.org/wiki/Q5527848","display_name":"Gaussian random field","level":4,"score":0.5211110711097717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.483167827129364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43492555618286133},{"id":"https://openalex.org/C130402806","wikidata":"https://www.wikidata.org/wiki/Q5361768","display_name":"Random field","level":2,"score":0.4278334677219391},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.34654366970062256},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.345605731010437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3084137439727783},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.30124300718307495},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15096497535705566},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13663437962532043},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:drum.lib.umd.edu:1903/19036","is_oa":true,"landing_page_url":"https://doi.org/10.13016/M2354T","pdf_url":"http://hdl.handle.net/1903/19036","source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","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":null,"raw_type":"Dissertation"},{"id":"pmh:oai:pqdtoai.proquest.com:10192530","is_oa":false,"landing_page_url":"http://pqdtopen.proquest.com/#viewpdf?dispub=10192530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"thesis"},{"id":"mag:2589217321","is_oa":false,"landing_page_url":"https://drum.lib.umd.edu/handle/1903/19036","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/m2354t","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m2354t","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":"Collection"}],"best_oa_location":{"id":"pmh:oai:drum.lib.umd.edu:1903/19036","is_oa":true,"landing_page_url":"https://doi.org/10.13016/M2354T","pdf_url":"http://hdl.handle.net/1903/19036","source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","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":null,"raw_type":"Dissertation"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2589217321.pdf","grobid_xml":"https://content.openalex.org/works/W2589217321.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2042412783","https://openalex.org/W1968766281","https://openalex.org/W804563486","https://openalex.org/W3135257336","https://openalex.org/W2727687425","https://openalex.org/W2023734581","https://openalex.org/W2762042638","https://openalex.org/W67158600","https://openalex.org/W2147282933","https://openalex.org/W2576017358","https://openalex.org/W3205900445","https://openalex.org/W2561273565","https://openalex.org/W3040856903","https://openalex.org/W2770179306","https://openalex.org/W2727783244","https://openalex.org/W2580204788","https://openalex.org/W2038134709","https://openalex.org/W2763076670","https://openalex.org/W2070659771","https://openalex.org/W3080999257"],"abstract_inverted_index":{"Representation":[0],"and":[1,55,73,112,121,138,181,252,267,319,341,391,437,452,472,566,601,719],"context":[2,80,113,153],"modeling":[3,54,77,114],"are":[4,9,35,185],"two":[5,465,581],"important":[6,82,678],"factors":[7],"that":[8,29,148,278,400,588,624],"critical":[10],"in":[11,20,67,247,337,365,612,735],"the":[12,31,46,52,59,78,88,101,110,151,156,159,172,202,212,228,279,290,299,327,346,352,362,366,372,382,403,418,423,447,454,470,473,482,491,514,527,557,562,590,598,609,625,633,645,661,671,706,716,739],"design":[13],"of":[14,45,58,64,174,214,259,308,430,449,456,484,493,516,570,574,580,648,663,692],"computer":[15,118],"vision":[16,119],"algorithms.":[17],"For":[18],"example,":[19],"applications":[21,68,96],"such":[22,69,177,433,683],"as":[23,70,178,224,245,335,434,499,684],"skeleton-based":[24,215],"human":[25,133,216,243,333],"action":[26,40,60,217,254,274,367,378],"recognition,":[27],"representations":[28,130,210,281],"capture":[30,227],"3D":[32,128,208,230,237,295,301,310],"skeletal":[33,136,287,315],"geometry":[34,231],"crucial":[36],"for":[37,83,94,116,131,171,188,211,446,467,513,539,640,660,679,704,714,727],"achieving":[38,84],"good":[39,85,496],"recognition":[41,61,191,255,275,379],"accuracy.":[42],"However,":[43,87],"most":[44],"existing":[47,286,511,553],"approaches":[48],"focus":[49,108,427],"mainly":[50],"on":[51,109,272,326,428,543,597,620,630],"temporal":[53,264,388],"classification":[56,173,429,448,515,524],"steps":[57],"pipeline":[62],"instead":[63,307],"representations.":[65,288],"Similarly,":[66],"image":[71,75,189,522,540,665],"enhancement":[72],"semantic":[74,664,685,745],"segmentation,":[76],"spatial":[79,102,152],"is":[81,317,568,677,690],"performance.":[86],"standard":[89],"deep":[90,145,536,657],"network":[91,146,537,559,578,587,605,639,658,668,689,703,713,726,741],"architectures":[92,147],"used":[93,187],"these":[95,248,343],"do":[97],"not":[98],"explicitly":[99,149,560,669],"model":[100,150,242,332],"context.":[103],"In":[104,162,201,289,422,481,526,644],"this":[105,338,649],"dissertation,":[106,650],"we":[107,164,205,293,376,409,426,489,530,651],"representation":[111,266,316,390],"issues":[115],"some":[117],"problems":[120],"make":[122],"novel":[123,533],"contributions":[124],"by":[125,154,350,380,401,475],"proposing":[126],"new":[127],"geometry-based":[129,209],"recognizing":[132],"actions":[134,244,334],"from":[135],"sequences,":[137],"introducing":[139],"Gaussian":[140,545,591,615,654,722,729],"conditional":[141],"random":[142],"field":[143,724],"model-based":[144,656],"considering":[155],"interactions":[157,672],"among":[158],"output":[160,674],"variables.":[161],"addition,":[163],"also":[165],"propose":[166,531,652],"a":[167,257,322,392,442,477,495,500,532,544,572,584,637,653,696,710,721,736],"kernel":[168,457,461,471],"learning-based":[169],"framework":[170,445],"manifold":[175,431,450,517],"features":[176,432,451,518],"linear":[179,435],"subspaces":[180,436],"covariance":[182,438],"matrices":[183],"which":[184,676],"widely":[186],"set-based":[190,523],"tasks.":[192],"This":[193,314,577,667],"dissertation":[194],"has":[195],"been":[196],"divided":[197],"into":[198],"five":[199],"parts.":[200],"first":[203],"part,":[204,292,425,529],"introduce":[206,464],"various":[207,233,304,743],"problem":[213,492],"recognition.":[218],"The":[219,504,687],"proposed":[220,280,505,558,626,688,740],"representations,":[221],"referred":[222],"to":[223,321,345,371,416,521,552],"R3DG":[225,249],"features,":[226],"relative":[229,300],"between":[232,303,673],"body":[234,239,305,312],"parts":[235,306],"using":[236,256,297,386,417,459],"rigid":[238,311],"transformations.":[240,313],"We":[241,331,440,463],"curves":[246,336,344,368,385],"feature":[250],"spaces,":[251],"perform":[253,282,377,608],"combination":[258,498],"dynamic":[260],"time":[261],"warping,":[262],"Fourier":[263,387],"pyramid":[265,389],"support":[268,393,485],"vector":[269,394,486],"machines.":[270],"Experiments":[271,619],"several":[273,621],"datasets":[276],"show":[277,399,623],"better":[283,508],"than":[284,509],"many":[285,510],"second":[291],"represent":[294],"skeletons":[296],"only":[298],"rotations":[302],"full":[309],"scale-invariant":[318],"belongs":[320],"Lie":[323,339,348,373,383],"group":[324,340],"based":[325,542,596,701],"special":[328],"orthogonal":[329],"group.":[330],"map":[342,354,405,420],"corresponding":[347],"algebra":[349,384],"combining":[351,402],"logarithm":[353,404,419],"with":[355,406,632],"rolling":[356,359,407],"maps.":[357],"Using":[358],"maps":[360],"reduces":[361],"distortions":[363],"introduced":[364],"while":[369],"mapping":[370],"algebra.":[374],"Finally,":[375],"classifying":[381],"machines":[395],"classifier.":[396],"Experimental":[397],"results":[398,629],"maps,":[408],"can":[410],"get":[411],"improved":[412],"performance":[413],"when":[414,519],"compared":[415],"alone.":[421],"third":[424],"matrices.":[439],"present":[441],"kernel-based":[443],"extrinsic":[444],"address":[453],"issue":[455],"selection":[458],"multiple":[460],"learning.":[462],"criteria":[466],"jointly":[468],"learning":[469,494],"classifier":[474],"solving":[476],"single":[478],"optimization":[479,502],"problem.":[480,503],"case":[483],"machine":[487],"classifier,":[488],"formulate":[490],"kernel-classifier":[497],"convex":[501],"approach":[506,627],"performs":[507],"methods":[512],"applied":[520],"task.":[525],"fourth":[528],"end-to-end":[534,734],"trainable":[535],"architecture":[538,659],"denoising":[541,555],"Conditional":[546],"Random":[547],"Field":[548],"(CRF)":[549],"model.":[550],"Contrary":[551],"discriminative":[554,737],"approaches,":[556],"models":[561,670],"input":[563,599],"noise":[564,575,642],"variance":[565],"hence":[567],"capable":[569],"handling":[571],"range":[573],"levels.":[576],"consists":[579],"sub-networks:":[582,694],"(i)":[583,695],"parameter":[585],"generation":[586],"generates":[589],"CRF":[592,616,655,730],"pairwise":[593,712,717],"potential":[594],"parameters":[595],"image,":[600],"(ii)":[602,709],"an":[603,613],"inference":[604,617,725],"whose":[606],"layers":[607],"computations":[610],"involved":[611],"iterative":[614],"procedure.":[618],"images":[622],"produces":[628],"par":[631],"state-of-the-art":[634],"without":[635],"training":[636],"separate":[638],"each":[641],"level.":[643],"final":[646],"part":[647],"task":[662],"segmentation.":[666,686],"variables":[675],"structured":[680],"prediction":[681],"tasks":[682],"composed":[691],"three":[693],"Convolutional":[697],"Neural":[698],"Network":[699],"(CNN)":[700],"unary":[702,707],"generating":[705,715],"potentials,":[708,718],"CNN-based":[711,744],"(iii)":[720],"mean":[723],"performing":[728],"inference.":[731],"When":[732],"trained":[733],"fashion":[738],"outperforms":[742],"segmentation":[746],"approaches.":[747]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}