Normal view MARC view ISBD view

Advanced Methods and Deep Learning in Computer Vision / (Record no. 7163)

MARC details
000 -LEADER
fixed length control field	07647 a2200241 4500
005 - DATE AND TIME OF LATEST TRANSACTION
control field	20250923114159.0
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field	241210b \|\|\|\|\|\|\|\| \|\|\|\| 00\| 0 eng d
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
ISBN	9780128221099
041 ## - LANGUAGE CODE
Language code of text/sound track or separate title	eng
082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER
Classification number	006.37
Item number	DavA
245 ## - TITLE STATEMENT
Title	Advanced Methods and Deep Learning in Computer Vision /
Statement of responsibility, etc	edited by E. R. Davies and Matthew Turk
260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT)
Place of publication	London:
Name of publisher	Academic Press;
Year of publication	©2022
300 ## - PHYSICAL DESCRIPTION
Number of Pages	xix, 562p.
505 01 - FORMATTED CONTENTS NOTE
Formatted contents note	List of contributors<br/><br/>xi<br/>About the editors<br/><br/>xiii<br/>Preface<br/><br/>xv<br/>1. The dramatically changing face of computer vision<br/><br/>E.R. DAVIES<br/><br/>1.1 Introduction – computer vision and its origins 1<br/><br/>1.2 Part A – Understanding low-level image processing operators 4<br/><br/>1.3 Part B – 2-D object location and recognition 15<br/><br/>1.4 Part C – 3-D object location and the importance of invariance 29<br/><br/>1.5 Part D – Tracking moving objects 55<br/><br/>1.6 Part E – Texture analysis 61<br/><br/>1.7 Part F – From artificial neural networks to deep learning methods 68<br/><br/>1.8 Part G – Summary 86<br/><br/>References 87<br/><br/>2. Advanced methods for robust object detection<br/><br/>ZHAOWEI CAI AND NUNO VASCONCELOS<br/><br/>2.1 Introduction 93<br/><br/>2.2 Preliminaries 95<br/><br/>2.3 R-CNN 96<br/><br/>2.4 SPP-Net 97<br/><br/>2.5 Fast R-CNN 98<br/><br/>2.6 Faster R-CNN 101<br/><br/>2.7 Cascade R-CNN 103<br/><br/>2.8 Multiscale feature representation 106<br/><br/>2.9 YOLO 110<br/><br/>2.10 SSD 112<br/><br/>2.11 RetinaNet 113<br/><br/>2.12 Detection performances 115<br/><br/>2.13 Conclusion 115<br/><br/>References 116<br/><br/>3. Learning with limited supervision<br/><br/>SUJOY PAUL AND AMIT K. ROY-CHOWDHURY<br/><br/>3.1 Introduction 119<br/><br/>3.2 Context-aware active learning 120<br/><br/>3.3 Weakly supervised event localization 129<br/><br/>3.4 Domain adaptation of semantic segmentation using weak labels 137<br/><br/>3.5 Weakly-supervised reinforcement learning for dynamical tasks 144<br/><br/>3.6 Conclusions 151<br/><br/>References 153<br/><br/>4. Efficient methods for deep learning<br/><br/>HAN CAI, JI LIN, AND SONG HAN<br/><br/>4.1 Model compression 159<br/><br/>4.2 Efficient neural network architectures 170<br/><br/>4.3 Conclusion 185<br/><br/>References 185<br/><br/>5. Deep conditional image generation<br/><br/>GANG HUA AND DONGDONG CHEN<br/><br/>5.1 Introduction 191<br/><br/>5.2 Visual pattern learning: a brief review 194<br/><br/>5.3 Classical generative models 195<br/><br/>5.4 Deep generative models 197<br/><br/>5.5 Deep conditional image generation 200<br/><br/>5.6 Disentanglement for controllable synthesis 201<br/><br/>5.7 Conclusion and discussions 216<br/><br/>References 216<br/><br/>6. Deep face recognition using full and partial face images<br/><br/>HASSAN UGAIL<br/><br/>6.1 Introduction 221<br/><br/>6.2 Components of deep face recognition 227<br/><br/>6.3 Face recognition using full face images 231<br/><br/>6.4 Deep face recognition using partial face data 233<br/><br/>6.5 Specific model training for full and partial faces 237<br/><br/>6.6 Discussion and conclusions 239<br/><br/>References 240<br/><br/>7. Unsupervised domain adaptation using shallow and deep representations<br/><br/>YOGESH BALAJI, HIEN NGUYEN, AND RAMA CHELLAPPA<br/><br/>7.1 Introduction 243<br/><br/>7.2 Unsupervised domain adaptation using manifolds 244<br/><br/>7.3 Unsupervised domain adaptation using dictionaries 247<br/><br/>7.4 Unsupervised domain adaptation using deep networks 258<br/><br/>7.5 Summary 270<br/><br/>References 270<br/><br/>8. Domain adaptation and continual learning in semantic segmentation<br/><br/>UMBERTO MICHIELI, MARCO TOLDO, AND PIETRO ZANUTTIGH<br/><br/>8.1 Introduction 275<br/><br/>8.2 Unsupervised domain adaptation 277<br/><br/>8.3 Continual learning 291<br/><br/>8.4 Conclusion 298<br/><br/>References 299<br/><br/>9. Visual tracking<br/><br/>MICHAEL FELSBERG<br/><br/>9.1 Introduction 305<br/><br/>9.2 Template-based methods 308<br/><br/>9.3 Online-learning-based methods 314<br/><br/>9.4 Deep learning-based methods 323<br/><br/>9.5 The transition from tracking to segmentation 327<br/><br/>9.6 Conclusions 331<br/><br/>References 332<br/><br/>10. Long-term deep object tracking<br/><br/>EFSTRATIOS GAVVES AND DEEPAK GUPTA<br/><br/>10.1 Introduction 337<br/><br/>10.2 Short-term visual object tracking 341<br/><br/>10.3 Long-term visual object tracking 345<br/><br/>10.4 Discussion 367<br/><br/>References 368<br/><br/>11. Learning for action-based scene understanding<br/><br/>CORNELIA FERMÜLLER AND MICHAEL MAYNORD<br/><br/>11.1 Introduction 373<br/><br/>11.2 Affordances of objects 375<br/><br/>11.3 Functional parsing of manipulation actions 383<br/><br/>11.4 Functional scene understanding through deep learning with language and vision 390<br/><br/>11.5 Future directions 397<br/><br/>11.6 Conclusions 399<br/><br/>References 399<br/><br/>12. Self-supervised temporal event segmentation inspired by cognitive theories<br/><br/>RAMY MOUNIR, SATHYANARAYANAN AAKUR, AND SUDEEP SARKAR<br/><br/>12.1 Introduction 406<br/><br/>12.2 The event segmentation theory from cognitive science 408<br/><br/>12.3 Version 1: single-pass temporal segmentation using prediction 410<br/><br/>12.4 Version 2: segmentation using attention-based event models 421<br/><br/>12.5 Version 3: spatio-temporal localization using prediction loss map 428<br/><br/>12.6 Other event segmentation approaches in computer vision 440<br/><br/>12.7 Conclusions 443<br/><br/>References 444<br/><br/>13. Probabilistic anomaly detection methods using learned models from time-series data for multimedia self-aware<br/><br/>systems<br/><br/>CARLO REGAZZONI, ALI KRAYANI, GIULIA SLAVIC, AND LUCIO MARCENARO<br/><br/>13.1 Introduction 450<br/><br/>13.2 Base concepts and state of the art 451<br/><br/>13.3 Framework for computing anomaly in self-aware systems 458<br/><br/>13.4 Case study results: anomaly detection on multisensory data from a self-aware vehicle 467<br/><br/>13.5 Conclusions 476<br/><br/>References 477<br/><br/>14. Deep plug-and-play and deep unfolding methods for image restoration<br/><br/>KAI ZHANG AND RADU TIMOFTE<br/><br/>14.1 Introduction 481<br/><br/>14.2 Half quadratic splitting (HQS) algorithm 484<br/><br/>14.3 Deep plug-and-play image restoration 485<br/><br/>14.4 Deep unfolding image restoration 492<br/><br/>14.5 Experiments 495<br/><br/>14.6 Discussion and conclusions 504<br/><br/>References 505<br/><br/>15. Visual adversarial attacks and defenses<br/><br/>CHANGJAE OH, ALESSIO XOMPERO, AND ANDREA CAVALLARO<br/><br/>15.1 Introduction 511<br/><br/>15.2 Problem definition 512<br/><br/>15.3 Properties of an adversarial attack 514<br/><br/>15.4 Types of perturbations 515<br/><br/>15.5 Attack scenarios 515<br/><br/>15.6 Image processing 522<br/><br/>15.7 Image classification 523<br/><br/>15.8 Semantic segmentation and object detection 529<br/><br/>15.9 Object tracking 529<br/><br/>15.10 Video classification 531<br/><br/>15.11 Defenses against adversarial attacks 533<br/><br/>15.12 Conclusions 537<br/><br/>References 538<br/><br/>Index<br/><br/>545
520 ## - SUMMARY, ETC.
Summary, etc	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.<br/><br/>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.<br/><br/>Provides an important reference on deep learning and advanced computer methods that was created by leaders in the field<br/>Illustrates principles with modern, real-world applications<br/>Suitable for self-learning or as a text for graduate courses
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical Term	Computer Vision
General subdivision	Mathematical Models
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical Term	Image Processing
General subdivision	Mathematical Models
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical Term	Machine Learning
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical Term	Nueral Network
700 ## - ADDED ENTRY--PERSONAL NAME
Personal name	Davies, E. R. [Ed.]
700 ## - ADDED ENTRY--PERSONAL NAME
Personal name	Turk, Matthew [Ed.]
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Koha item type	Books

Holdings
Withdrawn status	Lost status	Damaged status	Collection code	Home library	Current library	Shelving location	Date acquired	Source of acquisition	Purchase Price	Bill number	Full call number	Accession Number	Copy number	Print Price	Bill Date/Price effective from	Koha item type
			Computer Science	Indian Institute of Technology Tirupati	Indian Institute of Technology Tirupati	General Stacks	30/07/2025	Today and Tomorrows Printers and Publishers	7636.13	TTPP/132/2025-26	006.37 DavA (11516)	11516	Copy 1	10908.75	30/07/2025	Books