Muutke küpsiste eelistusi

E-raamat: Advanced Methods and Deep Learning in Computer Vision

3.50/5 (4 hinnangut Goodreads-ist)
Edited by (Professor and Department Chair, Department of Computer Science, University of California, Santa Barbara, CA, USA), Edited by (Emeritus Professor of Machine Vision, Royal Holloway, University of London, UK (deceased))
Teised raamatud teemal:
  • Formaat - EPUB+DRM
  • Hind: 130,97 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Advanced Methods and Deep Learning in Computer VisionSuurem pilt
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

Advanced Methods and Deep Learning in Computer Vision presents advanced computer vision methods, emphasizing machine and deep learning techniques that have emerged during the past 5–10 years. The book provides clear explanations of principles and algorithms supported with applications. Topics covered include machine learning, deep learning networks, generative adversarial networks, deep reinforcement learning, self-supervised learning, extraction of robust features, object detection, semantic segmentation, linguistic descriptions of images, visual search, visual tracking, 3D shape retrieval, image inpainting, novelty and anomaly detection.

This book provides easy learning for researchers and practitioners of advanced computer vision methods, but it is also suitable as a textbook for a second course on computer vision and deep learning for advanced undergraduates and graduate students.

  • Provides an important reference on deep learning and advanced computer methods that was created by leaders in the field
  • Illustrates principles with modern, real-world applications
  • Suitable for self-learning or as a text for graduate courses
List of contributors
xi
About the editors xiii
Preface xv
1 The dramatically changing face of computer vision
E.R. Davies
1.1 Introduction - computer vision and its origins
1(3)
1.2 Part A - Understanding low-level image processing operators
4(11)
1.3 Part B - 2-D object location and recognition
15(14)
1.4 Part C - 3-D object location and the importance of invariance
29(26)
1.5 Part D - Tracking moving objects
55(6)
1.6 Part E - Texture analysis
61(7)
1.7 Part F - From artificial neural networks to deep learning methods
68(18)
1.8 Part G - Summary
86(7)
References
87(6)
2 Advanced methods for robust object detection
Zhaoweicai
Nuno Vasconcelos
2.1 Introduction
93(2)
2.2 Preliminaries
95(1)
2.3 R-CNN
96(1)
2.4 SPP-Net
97(1)
2.5 Fast R-CNN
98(3)
2.6 Faster R-CNN
101(2)
2.7 Cascade R-CNN
103(3)
2.8 Multiscale feature representation
106(4)
2.9 YOLO
110(2)
2.10 SSD
112(1)
2.11 RetinaNet
113(2)
2.12 Detection performances
115(1)
2.13 Conclusion
115(4)
References
116(3)
3 Learning with limited supervision
Sujoy Paul
Amit K. Roy-Chowdhury
3.1 Introduction
119(1)
3.2 Context-aware active learning
120(9)
3.3 Weakly supervised event localization
129(8)
3.4 Domain adaptation of semantic segmentation using weak labels
137(7)
3.5 Weakly-supervised reinforcement learning for dynamical tasks
144(7)
3.6 Conclusions
151(8)
References
153(6)
4 Efficient methods for deep learning
Han Cai
Ji Lin
Song Han
4.1 Model compression
159(11)
4.2 Efficient neural network architectures
170(15)
4.3 Conclusion
185(6)
References
185(6)
5 Deep conditional image generation
Gang Hua
Dongdong Chen
5.1 Introduction
191(3)
5.2 Visual pattern learning: a brief review
194(1)
5.3 Classical generative models
195(2)
5.4 Deep generative models
197(3)
5.5 Deep conditional image generation
200(1)
5.6 Disentanglement for controllable synthesis
201(15)
5.7 Conclusion and discussions
216(5)
References
216(5)
6 Deep face recognition using full and partial face images
Hassan Ugail
6.1 Introduction
221(6)
6.2 Components of deep face recognition
227(4)
6.3 Face recognition using full face images
231(2)
6.4 Deep face recognition using partial face data
233(4)
6.5 Specific model training for full and partial faces
237(2)
6.6 Discussion and conclusions
239(4)
References
240(3)
7 Unsupervised domain adaptation using shallow and deep representations
Yogesh Balaji
Hien Nguyen
Rama Chellapp
7.1 Introduction
243(1)
7.2 Unsupervised domain adaptation using manifolds
244(3)
7.3 Unsupervised domain adaptation using dictionaries
247(11)
7.4 Unsupervised domain adaptation using deep networks
258(12)
7.5 Summary
270(5)
References
270(5)
8 Domain adaptation and continual learning in semantic segmentation
Umberto Michieli
Marco Toldo
Pietro Zanuttigh
8.1 Introduction
275(2)
8.2 Unsupervised domain adaptation
277(14)
8.3 Continual learning
291(7)
8.4 Conclusion
298(7)
References
299(6)
9 Visual tracking
Michael Felsberg
9.1 Introduction
305(3)
9.2 Template-based methods
308(6)
9.3 Online-learning-based methods
314(9)
9.4 Deep leaming-based methods
323(4)
9.5 The transition from tracking to segmentation
327(4)
9.6 Conclusions
331(6)
References
332(5)
10 Long-term deep object tracking
Efstratios Gawes
Deepak Gupta
10.1 Introduction
337(4)
10.2 Short-term visual object tracking
341(4)
10.3 Long-term visual object tracking
345(22)
10.4 Discussion
367(6)
References
368(5)
11 Learning for action-based scene understanding
Cornelia Fermuller
Michael Maynord
11.1 Introduction
373(2)
11.2 Affordances of objects
375(8)
11.3 Functional parsing of manipulation actions
383(7)
11.4 Functional scene understanding through deep learning with language and vision
390(7)
11.5 Future directions
397(2)
11.6 Conclusions
399(7)
References
399(7)
12 Self-supervised temporal event segmentation inspired by cognitive theories
Ramy Mounir
Sathyanarayanan Aakur
Sudeep Sarkar
12.1 Introduction
406(2)
12.2 The event segmentation theory from cognitive science
408(2)
12.3 Version 1: single-pass temporal segmentation using prediction
410(11)
12.4 Version 2: segmentation using attention-based event models
421(7)
12.5 Version 3: spatio-temporal localization using prediction loss map
428(12)
12.6 Other event segmentation approaches in computer vision
440(3)
12.7 Conclusions
443(7)
References
444(6)
13 Probabilistic anomaly detection methods using learned models from time-series data for multimedia self-aware systems
Carlo Regazzoni
Ali Krayani
Giulua Slavic
Lucio Marcenaro
13.1 Introduction
450(1)
13.2 Base concepts and state of the art
451(7)
13.3 Framework for computing anomaly in self-aware systems
458(9)
13.4 Case study results: anomaly detection on multisensory data from a self-aware vehicle
467(9)
13.5 Conclusions
476(5)
References
477(4)
14 Deep plug-and-play and deep unfolding methods for image restoration
Kai Zhang
Radu Timofte
14.1 Introduction
481(3)
14.2 Half quadratic splitting (HQS) algorithm
484(1)
14.3 Deep plug-and-play image restoration
485(7)
14.4 Deep unfolding image restoration
492(3)
14.5 Experiments
495(9)
14.6 Discussion and conclusions
504(7)
References
505(6)
15 Visual adversarial attacks and defenses
Changjae Oh
Alessio Xompero
Andrea Cavallaro
15.1 Introduction
511(1)
15.2 Problem definition
512(2)
15.3 Properties of an adversarial attack
514(1)
15.4 Types of perturbations
515(1)
15.5 Attack scenarios
515(7)
15.6 Image processing
522(1)
15.7 Image classification
523(6)
15.8 Semantic segmentation and object detection
529(1)
15.9 Object tracking
529(2)
15.10 Video classification
531(2)
15.11 Defenses against adversarial attacks
533(4)
15.12 Conclusions
537(8)
References
538(7)
Index 545
Roy Davies was Emeritus Professor of Machine Vision at Royal Holloway, University of London. He worked on many aspects of vision, from feature detection to robust, real-time implementations of practical vision tasks. His interests included automated visual inspection, surveillance, vehicle guidance, crime detection and neural networks. He has published more than 200 papers, and three books. Machine Vision: Theory, Algorithms, Practicalities (1990) has been widely used internationally for more than 25 years, and is now out in this much enhanced fifth edition. Roy held a DSc at the University of London and was awarded Distinguished Fellow of the British Machine Vision Association, and Fellow of the International Association of Pattern Recognition. Matthew Turk is a professor and department chair of the Department of Computer Science at the University of California, Santa Barbara, California. He was named a Fellow of the Institute of Electrical and Electronics Engineers (IEEE) in 2013[ 1] for his contributions to computer vision and perceptual interfaces. Starting on July 1st, he will be the president of the Toyota Technological Institute at Chicago[ 2]. In 2014, Turk was named a Fellow of the International Association for Pattern Recognition (IAPR)[ 3] for his contributions to computer vision and vision based interaction.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97801282214956e.html
Märksõnad: