About this book series
The field of computer vision and pattern recognition has a rich history of nearly 50 years. In the past decade, however, the field has experienced remarkable advances in scene understanding and image generation. This advancement is driven by three key factors: (a) the availability of large, diverse datasets, (b) the accessibility of cloud and personal computing, and (c) the open release of advanced neural network architectures and models. These breakthroughs have led to significant successes across numerous application domains, including intelligent transportation, augmented reality, healthcare, agriculture, oceanography, and more. The ACVPR book series aims to introduce, analyze, and synthesize recent and foundational research, offering valuable references to both beginners and expert practitioners. The series covers timely topics such as:
- Deep Learning for Vision
- Large-scale Foundational Models
- Generative Methods
- Multimodal Learning (vision, audio, language, action, etc.)
- Neural Fields for Vision
- 3D Computer Vision
- Computational Photography, Display and Illumination
- Video Understanding and Synthesis
- Virtual, Mixed and Augmented Reality
- Biological and Human Vision
- Physics-based Vision
- Vision for Graphics
- Ethics in Computer Vision
- Applications (Robotics, Agriculture, Health, Intelligent Transportation, Oceanography, Safety/Security, etc.)
This series includes monographs, introductory and advanced textbooks, and state-of-the-art collections. Furthermore, it supports Open Access publication mode.
- Electronic ISSN
- 2191-6594
- Print ISSN
- 2191-6586
- Series Editor
-
- Srinivasa Narasimhan
Book titles in this series
Abstracted and indexed in
-
- DBLP
- Norwegian Register for Scientific Journals and Series
- SCImago
- SCOPUS
- zbMATH