國立高雄大學圖資館 |

Language: English

Back

Unsupervised learning in space and t...

Leordeanu, Marius.

Unsupervised learning in space and timea modern approach for computer vision using graph-based techniques and deep neural networks /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Unsupervised learning in space and timeby Marius Leordeanu.
Reminder of title:	a modern approach for computer vision using graph-based techniques and deep neural networks /
Author:	Leordeanu, Marius.
Published:	Cham :Springer International Publishing :2020.
Description:	xxiii, 298 p. :ill., digital ;24 cm.
Contained By:	Springer eBooks
Subject:	Machine learning.
Online resource:	https://doi.org/10.1007/978-3-030-42128-1
ISBN:	9783030421281$q(electronic bk.)

Unsupervised learning in space and timea modern approach for computer vision using graph-based techniques and deep neural networks /
Leordeanu, Marius.

Unsupervised learning in space and timea modern approach for computer vision using graph-based techniques and deep neural networks /[electronic resource] :by Marius Leordeanu. - Cham :Springer International Publishing :2020. - xxiii, 298 p. :ill., digital ;24 cm. - Advances in computer vision and pattern recognition,2191-6586. - Advances in computer vision and pattern recognition..

1. Unsupervised Visual Learning: from Pixels to Seeing -- 2. Unsupervised Learning of Graph and Hypergraph Matching -- 3. Unsupervised Learning of Graph and Hypergraph Clustering -- 4. Feature Selection meets Unsupervised Learning -- 5. Unsupervised Learning of Object Segmentation in Video with Highly Probable Positive Features -- 6. Coupling Appearance and Motion: Unsupervised Clustering for Object Segmentation through Space and Time -- 7. Unsupervised Learning in Space and Time over Several Generations of Teacher and Student Networks -- 8. Unsupervised Learning Towards the Future.

This book addresses one of the most important unsolved problems in artificial intelligence: the task of learning, in an unsupervised manner, from massive quantities of spatiotemporal visual data that are available at low cost. The book covers important scientific discoveries and findings, with a focus on the latest advances in the field. Presenting a coherent structure, the book logically connects novel mathematical formulations and efficient computational solutions for a range of unsupervised learning tasks, including visual feature matching, learning and classification, object discovery, and semantic segmentation in video. The final part of the book proposes a general strategy for visual learning over several generations of student-teacher neural networks, along with a unique view on the future of unsupervised learning in real-world contexts. Offering a fresh approach to this difficult problem, several efficient, state-of-the-art unsupervised learning algorithms are reviewed in detail, complete with an analysis of their performance on various tasks, datasets, and experimental setups. By highlighting the interconnections between these methods, many seemingly diverse problems are elegantly brought together in a unified way. Serving as an invaluable guide to the computational tools and algorithms required to tackle the exciting challenges in the field, this book is a must-read for graduate students seeking a greater understanding of unsupervised learning, as well as researchers in computer vision, machine learning, robotics, and related disciplines. Dr. Marius Leordeanu is an Associate Professor (Senior Lecturer) at the Computer Science & Engineering Department, Polytechnic University of Bucharest and a Senior Researcher at the Institute of Mathematics of the Romanian Academy (IMAR), Bucharest, Romania. In 2014, he was awarded the Grigore Moisil Prize, the most prestigious award in mathematics bestowed by the Romanian Academy, for his work on unsupervised learning.

ISBN: 9783030421281$q(electronic bk.)

Standard No.: 10.1007/978-3-030-42128-1doiSubjects--Topical Terms:

188639
Machine learning.

LC Class. No.: Q325.5 / .L46 2020

Dewey Class. No.: 006.31

Unsupervised learning in space and timea modern approach for computer vision using graph-based techniques and deep neural networks /
LDR:03738nmm a2200349 a 4500 001 571759
003 DE-He213
005 20200420124245.0
006 m d
007 cr nn 008maaau
008 200922s2020 sz s 0 eng d
020 $a 9783030421281$q(electronic bk.)
020 $a 9783030421274$q(paper)
024 7 $a 10.1007/978-3-030-42128-1 $2 doi
035 $a 978-3-030-42128-1
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.5 $b .L46 2020
072 7 $a UYT $2 bicssc
072 7 $a COM012000 $2 bisacsh
072 7 $a UYT $2 thema
072 7 $a UYQV $2 thema
082 0 4 $a 006.31 $2 23
090 $a Q325.5 $b .L587 2020
100 1 $a Leordeanu, Marius. $3 858516
245 1 0 $a Unsupervised learning in space and time $h [electronic resource] : $b a modern approach for computer vision using graph-based techniques and deep neural networks / $c by Marius Leordeanu.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2020.
300 $a xxiii, 298 p. : $b ill., digital ; $c 24 cm.
490 1 $a Advances in computer vision and pattern recognition, $x 2191-6586
505 0 $a 1. Unsupervised Visual Learning: from Pixels to Seeing -- 2. Unsupervised Learning of Graph and Hypergraph Matching -- 3. Unsupervised Learning of Graph and Hypergraph Clustering -- 4. Feature Selection meets Unsupervised Learning -- 5. Unsupervised Learning of Object Segmentation in Video with Highly Probable Positive Features -- 6. Coupling Appearance and Motion: Unsupervised Clustering for Object Segmentation through Space and Time -- 7. Unsupervised Learning in Space and Time over Several Generations of Teacher and Student Networks -- 8. Unsupervised Learning Towards the Future.
520 $a This book addresses one of the most important unsolved problems in artificial intelligence: the task of learning, in an unsupervised manner, from massive quantities of spatiotemporal visual data that are available at low cost. The book covers important scientific discoveries and findings, with a focus on the latest advances in the field. Presenting a coherent structure, the book logically connects novel mathematical formulations and efficient computational solutions for a range of unsupervised learning tasks, including visual feature matching, learning and classification, object discovery, and semantic segmentation in video. The final part of the book proposes a general strategy for visual learning over several generations of student-teacher neural networks, along with a unique view on the future of unsupervised learning in real-world contexts. Offering a fresh approach to this difficult problem, several efficient, state-of-the-art unsupervised learning algorithms are reviewed in detail, complete with an analysis of their performance on various tasks, datasets, and experimental setups. By highlighting the interconnections between these methods, many seemingly diverse problems are elegantly brought together in a unified way. Serving as an invaluable guide to the computational tools and algorithms required to tackle the exciting challenges in the field, this book is a must-read for graduate students seeking a greater understanding of unsupervised learning, as well as researchers in computer vision, machine learning, robotics, and related disciplines. Dr. Marius Leordeanu is an Associate Professor (Senior Lecturer) at the Computer Science & Engineering Department, Polytechnic University of Bucharest and a Senior Researcher at the Institute of Mathematics of the Romanian Academy (IMAR), Bucharest, Romania. In 2014, he was awarded the Grigore Moisil Prize, the most prestigious award in mathematics bestowed by the Romanian Academy, for his work on unsupervised learning.
650 0 $a Machine learning. $3 188639
650 0 $a Computer vision. $3 200113
650 1 4 $a Image Processing and Computer Vision. $3 274051
650 2 4 $a Machine Learning. $3 833608
650 2 4 $a Mathematical Applications in Computer Science. $3 530811
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer eBooks
830 0 $a Advances in computer vision and pattern recognition. $3 559645
856 4 0 $u https://doi.org/10.1007/978-3-030-42128-1
950 $a Computer Science (Springer-11645)