Multi-faceted Deep Learning

Models and Data
1. Auflage 2021
ISBN: 978-3-030-74480-9
Verlag: Springer International Publishing

Buch, Englisch, 316 Seiten, Format (B × H): 155 mm x 235 mm, Gewicht: 499 g

This book covers a large set of methods in the field of Artificial Intelligence - Deep Learning applied to real-world problems. The fundamentals of the Deep Learning approach and different types of Deep Neural Networks (DNNs) are first summarized in this book, which offers a comprehensive preamble for further problem–oriented chapters.

The most interesting and open problems of machine learning in the framework of Deep Learning are discussed in this book and solutions are proposed. This book illustrates how to implement the zero-shot learning with Deep Neural Network Classifiers, which require a large amount of training data. The lack of annotated training data naturally pushes the researchers to implement low supervision algorithms. Metric learning is a long-term research but in the framework of Deep Learning approaches, it gets freshness and originality. Fine-grained classification with a low inter-class variability is a difficult problem for any classification tasks. This book presents how it is solved, by using different modalities and attention mechanisms in 3D convolutional networks.

Researchers focused on Machine Learning, Deep learning, Multimedia and Computer Vision will want to buy this book. Advanced level students studying computer science within these topic areas will also find this book useful.

Zielgruppe

Research

Autoren/Hrsg.

Zemmari, Akka

Benois-Pineau, Jenny

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Computer Vision
• Mathematik | Informatik EDV | Informatik Informatik Bildsignalverarbeitung
• Mathematik | Informatik EDV | Informatik Professionelle Anwendung Multimedia

Inhaltsverzeichnis

1. Introduction.- 2. Deep Neural Networks: Models and methods.- 3. Deep learning for semantic segmentation.- 4. Beyond Full Supervision in Deep Learning.- 5. Similarity Metric Learning.- 6. Zero-shot Learning with Deep Neural Networks for Object Recognition.- 7. Image and Video Captioning using Deep Architectures.- 8. Deep Learning in Video Compression Algorithms.- 9. 3D Convolutional Networks for Action Recognition: Application toSport Gesture Recognition.- 10. Deep Learning for Audio and Music.- 11. Explainable AI for Medical Imaging:Knowledge Matters.- 12. Improving Video Quality with Generative Adversarial Networks.- 13. Conclusion.

Über Autor(innen)

Prof. Jenny Benois-Pineau is a full professor of Computer Science at the University Bordeaux. Her topics of interest include image/multimedia, artificial intelligence in multimedia and healthcare. She is the author and co-author of more than 200 papers in international journals, conference proceedings, books and book chapters. She is associated editor of Eurasip SPIC, ACM MTAP, senior associated editor JEI SPIE journals. She has organized workshops and special sessions at international conferences IEEE ICIP, ACM MM,. She has served in numerous program committees in international conferences: ACM MM, ACM ICMR, ACM CIVR, CBMI, IPTA, ACM MMM. She has been coordinator or leading researcher in EU – funded and French national research projects. She is a member of IEEE TC IVMSP. She has Knight of Academic Palms grade.

Dr. Akka Zemmari has received his Ph.D. degree from the University of Bordeaux 1, France, in 2000. He is an associate professor in computer science since 2001 at University of Bordeaux, France. His research interests include Artificial Intelligence, Deep Learning, Distributed algorithms and systems, Graphs, Randomized Algorithms, and Security. He wrote one book and more than 80 research papers published in international journals and conference proceedings and he is involved in program committees and organization committees of international conferences.