Verfügbarkeit: Learning image and video representations based on sparsity priors

Learning image and video representations based on sparsity priors:

Gespeichert in:

Bibliographische Detailangaben
1. Verfasser:	Wei, Xian (VerfasserIn)
Format:	Abschlussarbeit Buch
Sprache:	English
Veröffentlicht:	München 2017
Schlagworte:	Hochschulschrift
Online-Zugang:	kostenfrei https://nbn-resolving.org/urn:nbn:de:bvb:91-diss-20170428-1335623-1-9 Inhaltsverzeichnis
Beschreibung:	v, ix, 130 Seiten Illustrationen, Diagramme

Internformat

MARC


LEADER	00000nam a2200000 c 4500
001	BV044320892
003	DE-604
005	20170627
007	t
008	170522s2017 a\|\|\| m\|\|\| 00\|\|\| eng d
035			\|a (OCoLC)989516787
035			\|a (DE-599)BVBBV044320892
040			\|a DE-604 \|b ger \|e rda
041	0		\|a eng
049			\|a DE-384 \|a DE-473 \|a DE-703 \|a DE-1051 \|a DE-824 \|a DE-29 \|a DE-12 \|a DE-91 \|a DE-19 \|a DE-1049 \|a DE-92 \|a DE-739 \|a DE-898 \|a DE-355 \|a DE-706 \|a DE-20 \|a DE-1102 \|a DE-860 \|a DE-2174
084			\|a DAT 001d \|2 stub
100	1		\|a Wei, Xian \|e Verfasser \|4 aut
245	1	0	\|a Learning image and video representations based on sparsity priors \|c Xian Wei
264		1	\|a München \|c 2017
300			\|a v, ix, 130 Seiten \|b Illustrationen, Diagramme
336			\|b txt \|2 rdacontent
337			\|b n \|2 rdamedia
338			\|b nc \|2 rdacarrier
502			\|b Dissertation \|c Technische Universität München \|d 2017
655		7	\|0 (DE-588)4113937-9 \|a Hochschulschrift \|2 gnd-content
776	0	8	\|i Erscheint auch als \|n Online-Ausgabe \|o urn:nbn:de:bvb:91-diss-20170428-1335623-1-9
856	4	1	\|u https://mediatum.ub.tum.de/node?id=1335623 \|x Verlag \|z kostenfrei \|3 Volltext
856	4		\|u https://nbn-resolving.org/urn:nbn:de:bvb:91-diss-20170428-1335623-1-9 \|x Resolving-System
856	4	2	\|m DNB Datenaustausch \|q application/pdf \|u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=029724361&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA \|3 Inhaltsverzeichnis
912			\|a ebook
999			\|a oai:aleph.bib-bvb.de:BVB01-029724361

Datensatz im Suchindex

_version_	1804177539118137344
adam_text	CONTENTS LIST O F SYM BOLS III LIST O F FIGURES V LIST O F TABLES IX 1 INTRODUCTION 1 1.1 THE ROLE OF IMAGE REPRESENTATION IN COMPUTER V ISION ................................... 1 1.2 SPARSE REPRESENTATION IN IMAGE PROCESSING........................................................ 7 1.3 CONTRIBUTIONS AND THE DISSERTATION OUTLINE ..................................................... 10 2 SPARSE CODING AND THE R ELATED O PTIM IZATION A LGORITHM S 13 2.1 SPARSE REPRESENTATION AND THE STATE-OF-THE-ART OPTIMIZATION ALGORITHMS . . . 13 2.1.1 CONVEX RELAXATION A LGORITHM S.............................................................. 14 2.1.2 ITERATIVE SHRINKAGE/ THRESHOLDING A LGORITHM S ...................................... 16 2.1.3 GREEDY PURSUIT A LGORITHM S.................................................................... 16 2.1.4 NON-CONVEX OPTIMIZATION ALGORITHMS..................................................... 17 2.2 DICTIONARY L E A RN IN G ........................................................................................... 19 2.2.1 METHOD OF OPTIMAL DIRECTIONS AND ITS EXTENSIONS .................................... 21 2.2.2 CLUSTERING BASED M ETHODS.......................................................................... 22 2.2.3 LAGRANGE DUAL M ETHOD................................................................................ 23 2.2.4 LEARNING DICTIONARY BASED ON STOCHASTIC GRADIENT DESCENT ALGORITHMS 24 3 A TWO-LAYER R EPRESENTATION LEARNING FRAMEWORK 25 3.1 INTRODUCTION............................................................................................................. 25 3.2 THE MAIN OPTIMIZATION P RO B LE M .......................................................................... 28 3.3 LOCAL DIFFERENTIABILITY OF SPARSE REPRESENTATION WITH CONVEX SPARSITY PRIORS . 30 3.3.1 LOCAL DIFFERENTIABILITY OF SPARSE REPRESENTATION ................................... 30 3.3.2 CONVEX SPARSITY P RIORS................................................................................ 32 3.3.3 LASSO AND ELASTIC N E T ................................................................................ 35 3.3.4 KULLBACK-LEIBLER DIVERGENCE ....................................................................... 36 3.4 RESOLVING THE MAIN PROBLEM USING GEOMETRIC O PTIM IZATION .............................. 37 3.4.1 GEOMETRIC O PTIM IZATION............................................................................. 37 3.4.2 GEOMETRY OF THE PRODUCT OF K UNIT S P H E RE S.............................................40 3.4.3 GEOMETRY OF GRASSMANN MANIFOLD ........................................................... 41 4 SPARSE LINEAR D YNAM ICAL SYSTEM S FOR M ODELING D YNAM IC TEXTURES 45 4.1 INTRODUCTION............................................................................................................. 45 4.2 MODELING DYNAMICAL TEXTURES USING LINEAR DYNAMIC S YSTEM S ........................... 48 4.3 SPARSE LINEAR DYNAMICAL SYSTEMS.......................................................................... 50 4.3.1 A DICTIONARY LEARNING MODEL FOR DYNAMIC S C E N E .................................... 50 4.3.2 OPTIMIZATION ALGORITHM FOR S L D S ........................................................... 55 4.4 DTS CLASSIFICATION USING SLDS MODEL ................................................................. 57 4.4.1 GLOBAL SLDS CLASSIFIER................................................................................ 57 4.4.2 PATCH-BASED SLDS CLASSIFIER .................................................................... 59 4.5 NUMERICAL EXPERIMENTS FOR EVALUATING THE SLDS M O D E L .................................... 61 4.5.1 D ATASETS....................................................................................................... 61 4.5.2 DYNAMIC TEXTURES SYNTHESIS....................................................................... 64 4.5.3 DYNAMIC TEXTURES CLASSIFICATION .............................................................. 65 4.6 S U M M ARY ................................................................................................................ 67 5 SPARSE LOW D IM ENSIONAL R EPRESENTATION LEARNING 69 5.1 INTRODUCTION............................................................................................................. 69 5.2 OPTIMIZATION OF TRACE QUOTIENT CRITERION ........................................................ 70 5.3 THE PROPOSED JOINT LEARNING FRAMEWORK........................................................... 71 5.3.1 A GENERIC COST FUNCTION......................................................................... 71 5.3.2 A GEOMETRIC CONJUGATE GRADIENT ALGORITHM......................................... 72 5.4 APPLICATIONS OF THE SPARLOW M ODEL ................................................................... 76 5.4.1 UNSUPERVISED LEARNING METHODS ........................................................... 76 5.4.2 SUPERVISED LEARNING M ETH O D S ................................................................ 79 5.4.3 SEMI-SUPERVISED LEARNING M E TH O D S ........................................................... 82 5.5 EXPERIMENTAL E VALUATIONS......................................................................................84 5.5.1 EXPERIMENTAL S E TTIN G S................................................................................84 5.5.2 EVALUATION OF UNSUPERVISED SPARLOW ........................................................ 85 5.5.3 EVALUATION OF SUPERVISED S P A RL O W ........................................................... 92 5.5.4 EVALUATION OF SEMI-SUPERVISED SPARLOW ...................................................96 5.5.5 OBJECT C ATEGORIZATION................................................................................97 5.5.6 PARAMETERS SENSITIVITY.............................................................................. 104 5.5.7 OPTIMIZATION PROCESS................................................................................. 106 5.6 S U M M ARY .............................................................................................................. 106 6 C ONCLUSIONS AND FUTURE WORK 109 6.1 CONCLUSIONS............................................................................................................109 6.2 FUTURE WORK .........................................................................................................110 BIBLIOGRAPHY 113
any_adam_object	1
author	Wei, Xian
author_facet	Wei, Xian
author_role	aut
author_sort	Wei, Xian
author_variant	x w xw
building	Verbundindex
bvnumber	BV044320892
classification_tum	DAT 001d
collection	ebook
ctrlnum	(OCoLC)989516787 (DE-599)BVBBV044320892
discipline	Informatik
format	Thesis Book
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01546nam a2200337 c 4500</leader><controlfield tag="001">BV044320892</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20170627 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">170522s2017 a\|\|\| m\|\|\| 00\|\|\| eng d</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)989516787</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV044320892</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-384</subfield><subfield code="a">DE-473</subfield><subfield code="a">DE-703</subfield><subfield code="a">DE-1051</subfield><subfield code="a">DE-824</subfield><subfield code="a">DE-29</subfield><subfield code="a">DE-12</subfield><subfield code="a">DE-91</subfield><subfield code="a">DE-19</subfield><subfield code="a">DE-1049</subfield><subfield code="a">DE-92</subfield><subfield code="a">DE-739</subfield><subfield code="a">DE-898</subfield><subfield code="a">DE-355</subfield><subfield code="a">DE-706</subfield><subfield code="a">DE-20</subfield><subfield code="a">DE-1102</subfield><subfield code="a">DE-860</subfield><subfield code="a">DE-2174</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 001d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Wei, Xian</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Learning image and video representations based on sparsity priors</subfield><subfield code="c">Xian Wei</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">München</subfield><subfield code="c">2017</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">v, ix, 130 Seiten</subfield><subfield code="b">Illustrationen, Diagramme</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="502" ind1=" " ind2=" "><subfield code="b">Dissertation</subfield><subfield code="c">Technische Universität München</subfield><subfield code="d">2017</subfield></datafield><datafield tag="655" ind1=" " ind2="7"><subfield code="0">(DE-588)4113937-9</subfield><subfield code="a">Hochschulschrift</subfield><subfield code="2">gnd-content</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Erscheint auch als</subfield><subfield code="n">Online-Ausgabe</subfield><subfield code="o">urn:nbn:de:bvb:91-diss-20170428-1335623-1-9</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://mediatum.ub.tum.de/node?id=1335623</subfield><subfield code="x">Verlag</subfield><subfield code="z">kostenfrei</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="856" ind1="4" ind2=" "><subfield code="u">https://nbn-resolving.org/urn:nbn:de:bvb:91-diss-20170428-1335623-1-9</subfield><subfield code="x">Resolving-System</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">DNB Datenaustausch</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=029724361&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ebook</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-029724361</subfield></datafield></record></collection>
genre	(DE-588)4113937-9 Hochschulschrift gnd-content
genre_facet	Hochschulschrift
id	DE-604.BV044320892
illustrated	Illustrated
indexdate	2024-07-10T07:49:41Z
institution	BVB
language	English
oai_aleph_id	oai:aleph.bib-bvb.de:BVB01-029724361
oclc_num	989516787
open_access_boolean	1
owner	DE-384 DE-473 DE-BY-UBG DE-703 DE-1051 DE-824 DE-29 DE-12 DE-91 DE-BY-TUM DE-19 DE-BY-UBM DE-1049 DE-92 DE-739 DE-898 DE-BY-UBR DE-355 DE-BY-UBR DE-706 DE-20 DE-1102 DE-860 DE-2174
owner_facet	DE-384 DE-473 DE-BY-UBG DE-703 DE-1051 DE-824 DE-29 DE-12 DE-91 DE-BY-TUM DE-19 DE-BY-UBM DE-1049 DE-92 DE-739 DE-898 DE-BY-UBR DE-355 DE-BY-UBR DE-706 DE-20 DE-1102 DE-860 DE-2174
physical	v, ix, 130 Seiten Illustrationen, Diagramme
psigel	ebook
publishDate	2017
publishDateSearch	2017
publishDateSort	2017
record_format	marc
spelling	Wei, Xian Verfasser aut Learning image and video representations based on sparsity priors Xian Wei München 2017 v, ix, 130 Seiten Illustrationen, Diagramme txt rdacontent n rdamedia nc rdacarrier Dissertation Technische Universität München 2017 (DE-588)4113937-9 Hochschulschrift gnd-content Erscheint auch als Online-Ausgabe urn:nbn:de:bvb:91-diss-20170428-1335623-1-9 https://mediatum.ub.tum.de/node?id=1335623 Verlag kostenfrei Volltext https://nbn-resolving.org/urn:nbn:de:bvb:91-diss-20170428-1335623-1-9 Resolving-System DNB Datenaustausch application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=029724361&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis
spellingShingle	Wei, Xian Learning image and video representations based on sparsity priors
subject_GND	(DE-588)4113937-9
title	Learning image and video representations based on sparsity priors
title_auth	Learning image and video representations based on sparsity priors
title_exact_search	Learning image and video representations based on sparsity priors
title_full	Learning image and video representations based on sparsity priors Xian Wei
title_fullStr	Learning image and video representations based on sparsity priors Xian Wei
title_full_unstemmed	Learning image and video representations based on sparsity priors Xian Wei
title_short	Learning image and video representations based on sparsity priors
title_sort	learning image and video representations based on sparsity priors
topic_facet	Hochschulschrift
url	https://mediatum.ub.tum.de/node?id=1335623 https://nbn-resolving.org/urn:nbn:de:bvb:91-diss-20170428-1335623-1-9 http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=029724361&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA
work_keys_str_mv	AT weixian learningimageandvideorepresentationsbasedonsparsitypriors

Verfügbarkeit

Es ist kein Print-Exemplar vorhanden.

Fernleihe Bestellen Achtung: Nicht im THWS-Bestand! Volltext öffnen

MARC

Datensatz im Suchindex

Es ist kein Print-Exemplar vorhanden.

Ähnliche Einträge